Skip to yearly menu bar Skip to main content


Show Detail
Schedule Sat Sun Mon Tue
Timezone: Africa/Casablanca
 
Filter Rooms:  

SAT 2 MAY
7:30 a.m.
Registration
(ends 5:00 PM)
8:30 a.m.
Opening Remarks:
Opening remarks
(ends 9:00 AM)
9 a.m.
Invited Talk:
Keynote: Eric Xing
Eric Xing
(ends 10:00 AM)
10 a.m.
Break:
Break
(ends 10:30 AM)
10:30 a.m.
Oral Session 1: Bayesian & Probabilistic Modeling [10:30-11:30]
Orals -
Rethinking Probabilistic Circuit Parameter Learning
Spotlights -
Standard Acquisition Is Sufficient for Asynchronous Bayesian Optimization
Learning Hyperparameters via a Data-Emphasized Variational Objective
On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors
Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models
Hellinger Multimodal Variational Autoencoders
Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency Without Model Sweeps
Laplace approximation for Bayesian variable selection via Le Cam's one-step procedure
(ends 11:30 AM)
11:30 a.m.
Oral Session 2: Learning Theory & High-Dimensional Statistics [11:30-12:30]
Orals -
Gaussian Equivalence for Self-Attention: Asymptotic Spectral Analysis of Attention Matrix
Spotlights -
PAC-Bayesian Bounds on Constrained $f$-Entropic Risk Measures
Empirical PAC-Bayes Bounds for Markov Chains
Support Basis: Fast Attention Beyond Bounded Entries
Minimax Generalized Cross-Entropy
Near-Optimal Sample Complexities of Divergence-based S-rectangular Distributionally Robust Reinforcement Learning
Beyond Johnson-Lindenstrauss: Uniform Bounds for Sketched Bilinear Forms
High Effort, Low Gain: Fundamental Limits of Active Learning for Linear Dynamical Systems
(ends 12:30 PM)
12:30 p.m.
Break:
Lunch
(ends 2:00 PM)
2 p.m.
Oral Session 3: Optimization, Training Methods & Learning Dynamics [2:00-3:00]
Orals -
A Proof of Learning Rate Transfer under $\mu$P
Spotlights -
Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory
A projection-based framework for gradient-free and parallel learning
Generalized and Optimal Straight-Through Estimators
GiVA: Gradient-Informed Bases for Vector-Based Adaptation
Tyler’s M-estimator Through the Lens Of Convex-Concave Programming
Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent
Composable Coresets for Constrained Determinant Maximization and Beyond
(ends 3:00 PM)
3 p.m.
Poster Session 1 [3:00-6:00]
Posters -
Robust Estimation of a Sparse Linear Model: Provable Guarantees with Non-convexity
Prior shift estimation for positive unlabeled data through the lens of kernel embedding
Enhancing LLM Safety through a Theoretical Minimax Game Lens
Amortized Safe Active Learning for Real-Time Data Acquisition: Pretrained Neural Policies from Simulated Nonparametric Functions
Beyond Pooling: Matching for Robust Generalization Under Data Heterogeneity
Influence Attributions can be Systematically Altered by Model Manipulation
Structured Difference-of-Q via Orthogonal Learning
Consistent PCA and Spectral Clustering
Unsupervised Ensemble Learning Through Deep Energy-based Models
Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction Between Feature Alignment and Target Fitting
Implicit Updates for Average-Reward Temporal Difference Learning
Bandit-based Maximum Inner Product Search with Data-Dependent Confidence Intervals
RoseCDL: Robust and Scalable Convolutional Dictionary Learning for rare-event and anomaly detection
Linear Convergence of the Frank-Wolfe Algorithm over Product Polytopes
On the Weight Density of L2-Regularized Linear Classification and Regression
Non-Asymptotic Generalization and Optimization Bounds for Stochastic Gauss-Newton in Deep Neural Networks
Mixture Proportion Estimation and Weakly-supervised Kernel Test for Conditional Independence
Dyno-Net: A Dynamic Feature Extraction Model for Gastrointestinal Polyp Detection
Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity
SFBD Flow: A Continuous-Optimization Framework for Training Diffusion Models with Noisy Samples
FedDuA: Doubly Adaptive Federated Learning
Active learning for stochastic contextual linear bandits
Linearly Separable Features in Shallow Nonlinear Networks: Width Scales Polynomially with Intrinsic Data Dimension
Revisiting Social Welfare in Bandits: UCB is (Nearly) All You Need
On the hardness of Reinforcement Learning with Transition Lookahead
Differentially Private Algorithms for the Stochastic Compositional Optimization Problem
Learning in Continuous State-Space MDPs for Network Inventory Management
Topological Alignment of Shared Vision-Language Embedding Space
Where You Place the Norm Matters: From Prejudiced to Neutral Initializations
Regularized Operator Extrapolation Method For Stochastic Hierarchical Variational Inequality Problems
Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time Methods
From Guess2Graph: When and How Can Unreliable Experts Safely Boost Causal Discovery in Finite Samples?
Towards Motion-aware Referring Image Segmentation
Learning with Incomplete Context: Linear Contextual Bandits with Pretrained Imputation
DeepRV: Accelerating spatiotemporal inference with pre-trained neural priors
A Covering Framework for Offline POMDPs Learning using Belief Space Metric
Partially Lazy Gradient Descent for Smoothed Online Learning
Variance Reduction Methods Do Not Need to Compute Full Gradients: Improved Efficiency through Shuffling
On Relation-Aware Slicing in Cross-Domain Alignment
FIELDING: Clustered Federated Learning with Data Drift
Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Text-Guided Generative AI Models
Secretary Problem with Predictions and Ordering
Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity
Rethinking Intrinsic Dimension Estimation in Neural Representations
Optimal rates for density and mode estimation with expand-and-sparsify representations
Duality-based Residual Estimation for Fully Offline Value-based Reinforcement Learning
SPIRE: Conditional Personalization for Federated Diffusion Generative Models
Improving Semantic Uncertainty Quantification in Question-Answering via Token-Level Temperature Scaling
Optimal Variance and Covariance Estimation under Differential Privacy in the Add-Remove Model and Beyond
Dashed Line Defense: Plug-And-Play Defense Against Adaptive Score-Based Query Attacks
Sparse Offline Reinforcement Learning with Corruption Robustness
When Can Federated Learning Match Centralized Learning? A PAC-Bayesian Generalization Gap Analysis
Almost Sure Convergence of Differential Temporal Difference Learning for Average Reward Markov Decision Processes
An Indicator of Membership Inference Security in Post-Training Quantized Models
Beyond Binary Out of Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories
DISPO: Enhancing Training Efficiency and Stability in Reinforcement Learning for Large Language Model Mathematical Reasoning
Examining the Bias of In-Batch Sampling in Similarity Learning with Two-Tower Models
Regularizing Extrapolation in Causal Inference
Low-Complexity and Consistent Graphon Estimation from Multiple Networks
A Scalable Lift-and-Project Differentiable Approach For the Maximum Cut Problem
Information Hidden in Gradients of Regression with Target Noise
Harnessing the Power of Reinforcement Learning for Adaptive MCMC
Semi-Implicit Variational Inference via Kernelized Path Gradient Descent
Brenier Isotonic Regression
Causal Partial Identification via Conditional Optimal Transport
Scalable Spatiotemporal Inference with Biased Scan Attention Transformer Neural Processes
Conformal Robust Control of Linear Systems
Policy-Oriented Binary Classification: Improving (KD-)CART Final Splits for Subpopulation Targeting
Variance Constrained Distribution Alignment in Few-shot Models
Practical and Efficient Rashomon Set Sampling for Model Interpretability
Causal-DRF: Conditional Kernel Treatment Effect Estimation using Distributional Random Forest
MLorc: Momentum Low-rank Compression for Large Language Model Adaptation
Laplace approximation for Bayesian variable selection via Le Cam's one-step procedure
A Geometric Approach to Optimal Experimental Design
Balanced and Robust Multi-Treatment Experimental Designs via Randomized Differencing
Doctor Rashomon and the UNIVERSE of Madness: Variable Importance with Unobserved Confounding and the Rashomon Effect
RL-finetuning LLMs from on- and off-policy data with a single algorithm
Likelihood-Free Inference via Structured Score Matching
Regret Guarantees for Linear Contextual Stochastic Shortest Path
A pure hypothesis test for inhomogeneous random graph models based on a kernelised Stein discrepancy
Graphon Mixtures
Root Cause Analysis of Outliers in Unknown Cyclic Graphs
Random Features for Operator-Valued Kernels: Bridging Kernel Methods and Neural Operators
Optimal Arm Elimination Algorithms for Combinatorial Bandits
Spectral Clustering for Directed Graphs via Likelihood Estimation on Stochastic Block Models
Meta Sparse Principal Component Analysis
Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration
Off-policy Distributional Q($\lambda$): Distributional RL without Importance Sampling
Gaussian Equivalence for Self-Attention: Asymptotic Spectral Analysis of Attention Matrix
Rate-optimal Design for Anytime Best Arm Identification
A Proof of Learning Rate Transfer under $\mu$P
Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory
A projection-based framework for gradient-free and parallel learning
Generalized and Optimal Straight-Through Estimators
Standard Acquisition Is Sufficient for Asynchronous Bayesian Optimization
GiVA: Gradient-Informed Bases for Vector-Based Adaptation
PAC-Bayesian Bounds on Constrained $f$-Entropic Risk Measures
Rethinking Probabilistic Circuit Parameter Learning
Tyler’s M-estimator Through the Lens Of Convex-Concave Programming
Improved Algorithms for Clustering with Noisy Distance Oracles
Support Basis: Fast Attention Beyond Bounded Entries
Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent
Learning Hyperparameters via a Data-Emphasized Variational Objective
On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors
Composable Coresets for Constrained Determinant Maximization and Beyond
Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models
Minimax Generalized Cross-Entropy
Hellinger Multimodal Variational Autoencoders
Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency Without Model Sweeps
Near-Optimal Sample Complexities of Divergence-based S-rectangular Distributionally Robust Reinforcement Learning
Scalable Learning of Multivariate Distributions via Coresets
General Weighted Averaging in Stochastic Gradient Descent: CLT and Adaptive Optimality
Beyond Johnson-Lindenstrauss: Uniform Bounds for Sketched Bilinear Forms
High Effort, Low Gain: Fundamental Limits of Active Learning for Linear Dynamical Systems
Predictive performance of power posteriors
Scalable resampling in massive generalized linear models via subsampled residual bootstrap
Distributed estimation and inference for semiparametric binary response models
DAG-Informed Structure Learning from Multi-Dimensional Point Processes
Boltzmann Exploration for Heavy-Tailed Bandits
The Majority Vote Paradigm Shift: When Popular Meets Optimal
High-dimensional Learning with Noisy Labels
Split-Flows: Measure Transport and Information Loss Across Molecular Resolutions
FocusViT: Faithful Explanations for Vision Transformers via Gradient-Guided Layer-Skipping
Structural Alignment Improves Graph Test-Time Adaptation
Dualformer: Time-Frequency Dual Domain Learning for Long-term Time Series Forecasting
Weighted quantization using MMD: From mean field to mean shift using gradient flows
In-memory Training on Analog Devices with Limited Conductance States via Multi-tile Residual Learning
Integrating Feature Correlation in Differential Privacy with Applications in DP-ERM
Preference-based Conditional Treatment Effects and Policy Learning
On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial Approach
Fair Clustering via Hierarchical Fair-Dirichlet Prior
Incorporating Expert Knowledge into Bayesian Causal Discovery of Mixtures of Directed Acyclic Graphs
Stochastic Bandits on Mixture Distributions: Metrics & Regret Bounds
Differentially Private Clustering in Data Streams
Efficient Learning of Stationary Diffusions with Stein-type Discrepancies
Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective
On the Latent Information Geometry of the Grassmann Manifold
FedCCA: Federated Canonical Correlation Analysis
Welfare-Centric Clustering
Causal Additive Models with Unobserved Causal Paths and Backdoor Paths
TAS-EGNN: Task-Aware Spectral Ego-Graphs for Efficient GNNs-Based Classification
Orientability of Causal Relations in Time Series using Summary Causal Graphs and Faithful Distributions
ADOPT: Additive Optimal Transport Regression
Noise-Free Dynamic Rank-Adaptation via Riemannian Methods in Federated Fine-Tuning
Optimal Posterior Sampling for Policy Identification in Tabular Markov Decision Processes
Sample Average Approximation for Alpha-Divergence Minimization with Exponential Convergence Guarantees
Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids
On Barycenter Computation: Analyzing Semi-Unbalanced Optimal Transport-based Method on Bures-Wasserstein manifold.
Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixing
Beyond Black-Box Predictions: Identifying Marginal Feature Effects in Tabular Transformer Networks
Robust Generalization with Adaptive Optimal Transport Priors for Decision-Focused Learning
Low-Rank Bias, Weight Decay, and Model Merging in Neural Networks
Meet Me at the Arm: The Cooperative Multi Armed Bandits Problem with Shareable Arms
Convergence of projected stochastic natural gradient variational inference: Balancing speed, computational effort, and accuracy
Sparse Linear Bandits with Fixed Sparsity Support: Adversarial and Stochastic Regimes
On Computational Limits of FlowAR Models: Expressivity and Efficiency
A Recovery Theory for Diffusion Priors: Deterministic Analysis of the Implicit Prior Algorithm
A Finite Time Analysis of Thompson Sampling for Bayesian Optimization with Preferential Feedback
On Different Notions of Redundancy in Conditional-Independence-Based Discovery of Graphical Models
High-dimensional Level Set Estimation with Trust Regions and Double Acquisition Functions
Lloyd's $K$-Means Clustering Algorithm is Frank-Wolfe in Disguise
Lyapunov-Guided Self-Alignment: Test-Time Adaptation for Offline Safe Reinforcement Learning
High-Dimensional Analysis of Bootstrap Ensemble Classifiers
LLMs Judging LLMs: A Simplex Perspective
Convexified Message-Passing Graph Neural Networks
MDPs with a State Sensing Cost
Feature Importance via Sets of Locally Performant Linear Models
Accelerating Byzantine-Robust Distributed Learning with Compressed Communication via Double Momentum and Variance Reduction
Multi-Component VAE with Gaussian Markov Random Field
The Minimax Lower Bound of Kernel Stein Discrepancy Estimation
Design-Based Finite-Sample Analysis for Regression Adjustment
Sparse Linear Bandits with Blocking Constraints
Provable Guarantees for Estimating Covariances between Latent Variables with Application to Precision Matrix Estimation
Policy Testing in Markov Decision Processes
Narrowing Action Choices with AI Improves Human Sequential Decisions
Provable Target Sample Complexity Improvements as Pre‑Trained Models Scale
Counterfactual Credit Guided Bayesian Optimization
Deconfounding Scores and Representation Learning for Causal Effect Estimation with Weak Overlap
On Kernel based Variational Autoencoders
An Information-Theoretic Approach to Understanding Transformers' In-Context Learning of Variable-Order Markov Chains
Contraction rates for generalized posteriors based on $f$-divergences: a diffusion process approach
Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning
$k$-PCA for (non-squared) Euclidean Distances: Deterministic Polynomial Time Approximation
Differentially Private Minimum Spanning Tree in Euclidean Graphs
A Consequentialist Critique of Binary Classification Evaluation: Theory, Practice, and Tools
E-Scores for (In)Correctness Assessment of Generative Model Outputs
Filter, Augment, Forecast: Online Data Selection for Robust Time Series Forecasting
Catoni-Style Change Point Detection for Regret Minimization in Piecewise-Stationary Heavy-Tailed Bandits
Understanding Generalization in Node and Link Prediction
Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks
Efficient Subgroup Analysis via Optimal Trees with Global Parameter Fusion
Preconditioned Attention: Enhancing Efficiency in Transformer Blocks
Improving Coverage in Combined Prediction Sets with Weighted p-values
Happiness as a Measure of Fairness
Probabilistic multi-dimensional classification with incomplete data at the prediction time
Sequential 1-bit Mean Estimation with Near-Optimal Sample Complexity
Projection-free Algorithms for Online Convex Optimization with Adversarial Constraints
Structured Matrix Scaling for Multi-Class Calibration
Explanation Design in Strategic Learning: Sufficient Explanations that Induce Non-harmful Responses
A Hessian-Free Actor-Critic Algorithm for Bi-Level Reinforcement Learning with Applications to LLM Fine-Tuning
Corruption Robust Thompson Sampling for Gaussian Bandits
GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification
PENGUIN: Enhancing Transformer with Periodic-Nested Group Attention for Long-term Time Series Forecasting
Conformal Prediction in Hierarchical Classification with Constrained Representation Complexity
(ends 6:00 PM)
6 p.m.
Reception:
Opening reception
(ends 8:00 PM)

SUN 3 MAY
8:30 a.m.
Registration
(ends 5:00 PM)
9 a.m.
Invited Talk:
Keynote: Emma Brunskill
Emma Brunskill
(ends 10:00 AM)
10 a.m.
Break:
Break
(ends 10:30 AM)
10:30 a.m.
Oral Session 4: RL, Bandits & Online Decision-Making [10:30-11:30]
Orals -
Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits
Spotlights -
Pure Exploration with Infinite Answers
A Modularized Framework for Piecewise-Stationary Restless Bandits
Towards Blackwell Optimality: Bellman Optimality Is All You Can Get
Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games
Parameter-Free Dynamic Regret for Unconstrained Linear Bandits
An Information-Geometric Approach to Artificial Curiosity
Learning to Bid in Discriminatory Auctions with Budget Constraints
(ends 11:30 AM)
11:30 a.m.
Paper Award Talks [11:30-12:30]
EventFlow: Forecasting Temporal Point Processes with Flow Matching
We Still Don’t Understand High-Dimensional Bayesian Optimization
(ends 12:30 PM)
12:30 p.m.
Break:
Lunch
(ends 2:00 PM)
2 p.m.
Oral Session 5: Deep Architectures, Transformers & Representation Learning [2:00-3:00]
Orals -
Complexity-Aware Deep Symbolic Regression with Robust Risk-Seeking Policy Gradients
Spotlights -
Representation Learning via Non-Contrastive Mutual Information
Why is prompting hard? Understanding prompts on binary sequence predictors
On the Role of Depth in the Expressivity of RNNs
Certifying Reading Comprehension in Large Language Models
In-Context Learning for Discrete Optimal Transport: Can Transformers Sort?
LAMP: Extracting Local Decision Surfaces from Large Language Models
Beyond Binning: Soft Task Reformulation for Deep Regression
(ends 3:00 PM)
3 p.m.
Poster Session 2 [3:00-6:00]
Posters -
Efficient Uncoupled Learning Dynamics with $\tilde{O}\left(T^{-1/4}\right)$ Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback
Rank Lifting and Random Non-Linear Maps
Data Distribution Valuation Using Generalized Bayesian Inference
Provable Accelerated Bayesian Optimization with Knowledge Transfer
Generalized Correlation Shifting for Lasso
Identification and Estimation of "Probabilities of Causation" in the Presence of Confounding and Selection Bias
Enforcing Fair Predicted Scores on Intervals of Percentiles by Difference-of-Convex Constraints
Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks
CTRLS: Chain-of-Thought Reasoning via Latent State-Transition
Stick-Breaking Embedded Topic Model with Continuous Optimal Transport for Online Analysis of Document Streams
Linear Reasoning Vs. Proof by Cases: Obstacles for Large Language Models in FOL Problem Solving
Ergodic and Subhomogeneous Dynamics in Hyperbolic Neural Networks
Faster Parallel MCMC: Metropolis Adjustment Is Best Served Warm
Minimizing Human Intervention in Online Classification
Structured Temporal Inference in State-Space Models
Incentivizing Truthful Submissions in a Data Marketplace for Mean Estimation
Kernel Treatment Effects with Adaptively Collected Data
Learning under Moral Hazard with Instrumental Regression and Generalized Method of Moments
AlphaFold's Bayesian Roots in Probability Kinematics
Learning Physical Operators using Neural Operators
Gradient Regularized Natural Gradients
i-IF-Learn: Iterative Feature Selection and Unsupervised Learning for High-Dimensional Complex Data
Private Synthetic Graph Generation and Fused Gromov-Wasserstein Distance
Canopy Tree Height Estimation using Quantile Regression: Modeling and Evaluating Uncertainty in Remote Sensing
Momentum SVGD-EM for Accelerated Maximum Marginal Likelihood Estimation
Rate optimal learning of equilibria from data
Hypergraph Neural Networks Accelerate MUS Enumeration
Adversarial Robustness in One-Stage Learning-to-Defer
From Hawkes Processes to Attention: Time-Modulated Mechanisms for Event Sequences
Community-Enhanced Semi-seeded Network Alignment (CESSNA): A Robust Method with Application to Microbiome Networks
Gradient-flow SDEs have unique transient population dynamics
Time Series Forecasting with Hahn Kolmogorov-Arnold Networks
Undersmoothing Black-Box Models for Functional Estimation
Representative, Informative, and De-Amplifying: Requirements for Robust Bayesian Active Learning under Model Misspecification
Bounds and Identification of Joint Probabilities of Potential Outcomes and Observed Variables under Monotonicity Assumptions
Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits
Evaluation of Large Language Models via Coupled Token Generation
Training Latent Diffusion Models with Interacting Particle Algorithms
Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees
On the Misinformation in a Statistical Experiment
LatticeVision: Image to Image Networks for Modeling Non-Stationary Spatial Data
Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning
ECAI: Efficient Convolution Activation Inversion for Constant-Memory Convolutional Neural Networks Training
Exact and Approximate MCMC for Doubly-intractable Probabilistic Graphical Models Leveraging the Underlying Independence Model
Sharp risk bounds for early-stopping in Gaussian linear regression
Adaptive Coverage Policies in Conformal Prediction
A Bayesian Information-Theoretic Approach to Data Attribution
Variational inference via radial transport
GL-LowPopArt: A Nearly Instance-Wise Minimax Estimator for Generalized Low-Rank Trace Regression
ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models
Optimistic Actor-Critic with Parametric Policies for Linear Markov Decision Processes
Counterfactual Explanations via Latent Structure for Time Series Classification
ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory
Thompson Sampling-like Algorithms for Stochastic Rising Bandits
The Riemannian Geometry Associated to Gradient Flows of Linear Convolutional Networks
Active Subspaces in Infinite Dimension
Lag Operator SSMs: A Geometric Framework for Structured State Space Modeling
Learning When Not to Learn: Risk-Sensitive Abstention in Bandits with Unbounded Rewards
Conservative Inference in Switchback Experiments
Fast and Robust Simulation-Based Inference With Optimization Monte Carlo
Deformed Decomposition for Non-negative Tensors
On the optimal regret of collaborative personalized linear bandits
Bayesian Inverse Transition Learning: Learning Dynamics from Near-Optimal Trajectories
Unified Causal Discovery and Missing Data Imputation
The Role of Causal Features in Strategic Classification for Robustness and Alignment
Efficient Logistic Regression with Mixture of Sigmoids
An Evaluation of Cost Functions for Algorithmic Recourse
Demystifying Transition Matching: When and Why It Can Beat Flow Matching
Neuron Block Dynamics for XOR Classification with Zero-Margin
Hyperbolic Part-Whole Image Segmentation
A Goemans-Williamson type algorithm for identifying subcohorts in clinical trials
Provably Efficient Reinforcement Learning for Sparse Dynamical Systems with Non-Gaussian Noise
Conditional Flow Matching for Bayesian Posterior Sampling
DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification
Near-optimal Rank Adaptive Inference of High Dimensional Matrices
On the Convergence and Stability of Distributed Sub-model Training
We Still Don’t Understand High-Dimensional Bayesian Optimization
EventFlow: Forecasting Temporal Point Processes with Flow Matching
Corruption-robust Offline Multi-agent Reinforcement Learning from Human Feedback
Complexity-Aware Deep Symbolic Regression with Robust Risk-Seeking Policy Gradients
Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits
Pure Exploration with Infinite Answers
A Modularized Framework for Piecewise-Stationary Restless Bandits
Representation Learning via Non-Contrastive Mutual Information
Why is prompting hard? Understanding prompts on binary sequence predictors
On the Role of Depth in the Expressivity of RNNs
Towards Blackwell Optimality: Bellman Optimality Is All You Can Get
Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games
Parameter-Free Dynamic Regret for Unconstrained Linear Bandits
Statistical Inference for Explainable Boosting Machines
Certifying Reading Comprehension in Large Language Models
In-Context Learning for Discrete Optimal Transport: Can Transformers Sort?
LAMP: Extracting Local Decision Surfaces from Large Language Models
Beyond Binning: Soft Task Reformulation for Deep Regression
An Information-Geometric Approach to Artificial Curiosity
Learning to Bid in Discriminatory Auctions with Budget Constraints
High-Dimensional Spatial Autoregression with Latent Factors by Diversified Projections
Online Statistical Inference for Stochastic Optimization via Kiefer-Wolfowitz Methods
Root cause discovery via permutations and Cholesky decomposition
Revisiting RIP Guarantees for Sketching Operators on Mixture Models
Towards Sensitivity-Aware Language Models
Deflated HeteroPCA: Overcoming the curse of ill-conditioning in heteroskedastic PCA
Functional Integrative Bayesian Analysis of High-Dimensional Multiplatform Clinicogenomic Data
A new integrative learning framework for integrating multiple secondary outcomes into primary outcome analysis: a case study on liver health
Minimax Optimal Deep Neural Network Classifiers Under Smooth Decision Boundary
Inference for Dispersion and Curvature of Random Objects
Graphical Model Inference with Erosely Measured Data
Evidence Estimation in Gaussian Graphical Models Using a Telescoping Block Decomposition of the Precision Matrix
On the eigenvalue decay rates of a class of neural-network related kernel functions defined on general domains
Settling the sample complexity of model-based offline reinforcement learning
Clustering risk in Non-parametric Hidden Markov and I.I.D. Models
A Divergence-Based Method for Weighting and Averaging Model Predictions
Reinforcement Learning Using Known Invariances
Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation
Scalable community detection in massive networks via predictive assignment
Unmixing Mean Embeddings for Domain Adaptation with Target Label Proportion
LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics Engines
Tight Analysis of Decentralized SGD: a Markov Chain Perspective
Entropic Projection Alignment: Estimating, Explaining, and Improving Model Performance Under Tabular Distribution Shift
Tight Lower Bounds and Optimal Algorithms for Stochastic Nonconvex Optimization with Heavy-Tailed Noise
Neural Doubly Robust Proximal Causal Estimation
Asymptotic optimality theory of confidence intervals of the mean
Injecting Measurement Information Yields a Fast and Noise-Robust Diffusion-Based Inverse Problem Solver
Differentially Private E-Values
Optimal Local Convergence Rates of Stochastic First-Order Methods under Local Alpha-PL
Sequential Off-Policy Learning with Logarithmic Smoothing
Tractable Shapley Values and Interactions via Tensor Networks
Partial VOROS: A Cost-aware Performance Metric for Binary Classifiers with Precision and Capacity Constraints
Learnability with Partial Labels and Adaptive Nearest Neighbors
Statistical-computational gap in multiple Gaussian graph alignment
Uncertainty Quantification for Named Entity Recognition via Conformal Prediction
Efficient and Accurate Tensor Compression via Recursive Sketching
Semi-Random Noisy and One-Bit Matrix Completion With Nonconvex Primal-Dual Framework
Recency Biased Causal Attention for Time-series Forecasting
Incoherence in goal-conditioned autoregressive models
NeST-BO: Fast Local Bayesian Optimization via Newton-Step Targeting of Gradient and Hessian Information
Fact-Augmented Lookahead for LLM Agents: Simple Online Memory, No Finetuning
SiGHT: A Self-Supervised Graph-based Hallucination DeTection Framework for Domain-Specific LLMs
Time-Aware Synthetic Control
Best Policy Learning from Trajectory Preference Feedback
Multilayer Correlation Clustering
Graph Learning is Suboptimal in Causal Bandits
From Transformers to State Spaces: GeoMamba-SE(3) for Fast and Accurate Molecular Learning
Interpretable DNA Sequence Classification via Dynamic Feature Generation in Decision Trees
Structured Matching via Cost-Regularized Unbalanced Optimal Transport
T$_k$CP: Context-Aware Pooling via Top-k% Activation Selection
Online Learning-to-Defer with Varying Experts
Free Random Projection for In-Context Reinforcement Learning
Personalized Incentive Alignment: Correcting Utility-Driven Selection Bias in A/B Tests
Scalable Model-Based Clustering with Sequential Monte Carlo
Loss Gaps Parity for Fairness in Heterogeneous Federated Learning
Rashomon Effect for Visualizing High-Dimensional Data
Adaptive Combinatorial Experimental Design: Pareto Optimality for Decision-Making and Inference
Mask-Conditional Conformal Prediction: Valid Uncertainty For All Missing Data Mechanisms
Local Causal Discovery for Statistically Efficient Causal Inference
Near-Optimal Clustering in Mixture of Markov Chains
Connectome-Guided Optimization for Deep Networks
Efficient Swap Regret Minimization in Combinatorial Bandits
Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validation
Three-operator splitting with stale gradients for faster non-linear optimal transport
In-Context Function Learning in Large Language Models
Hyperbolic Learning with Supervision from any Granularity
Lipschitz Multiscale Deep Equilibrium Models: A Theoretically Guaranteed and Accelerated Approach
Hybrid Meta-Learners for Estimating Heterogeneous Treatment Effects
Formally Exploring Time-Series Anomaly Detection Evaluation Metrics
Bad Values but Good Behavior: Learning Highly Misspecified Bandits with Function Approximation
Robust estimation of heterogeneous treatment effects in randomized trials leveraging external data
Accelerated Distributed Optimization with Compression and Error Feedback
Minimax-Optimal Two-Sample Test with Sliced Wasserstein
FastRank: Fast Tensor Rank Approximation based on Spectral Energy
Information-theoretic error bounds for source localization in neural sensing
Nonparametric Multi Change Point Detection for Markov Chains via Adaptive Clustering
Learning Geometry and Topology via Multi-Chart Flows
Lower Bounds for Public-Private Learning under Distribution Shift
From Token Imbalance to Balanced Routing: An ELBO-Regularized Probabilistic Framework for Contrastive Multimodal Learning
From Cells to Sentences: An End-to-End Framework for Table Understanding
Variational Grey-Box Dynamics Matching
Fundamental Limits of Non-Adaptive Group Testing With Markovian Correlation
FairSHAP: Preprocessing for Fairness Through Attribution-Based Data Augmentation
Explore-then-Commit for Nonstationary Linear Bandits with Latent Dynamics
Local Regression on Path Spaces with Signature Metrics
Fast Quasar-Convex Optimization with Constraints
Learning to Choose or Choosing to Learn: Best-of-N vs. Supervised Fine-Tuning for Bit String Generation
Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space
Moonwalk: Inverse-Forward Differentiation
Towards Characterizing the Complexity of Riemannian Online Convex Optimization
FlowPINNs: A Variational Framework for PDE Parameter Inference and Uncertainty Quantification
Set to Be Fair: Demographic Parity Constraints for Set-Valued Classification
Do we need rebalancing strategies? A theoretical and empirical study around SMOTE and its variants
Process-Tensor Tomography of SGD: Measuring Non-Markovian Memory via Back-Flow of Distinguishability
Power Transform Revisited: Numerically Stable, and Federated
Learning How Deep to Go: Self-Scaling Deep Reinforcement Learning
Stationarity-Aware Causal Discovery in Time Series via Minimal Separating Sets
Computationally Lightweight Classifiers with Frequentist Bounds on Prediction Errors
Where the Score Lives: A Wavelet View of Diffusion
Zeroth-Order Stochastic Compositional Gradient Descent: Towards Black-Box Sparse AUC Maximization
Tensor Gaussian Processes: Efficient Solvers for Nonlinear PDEs
Partial Monotonicity for Submodular Maximization with a Knapsack Constraint
Transportability without Graphs: A Bayesian Approach to Identifying s-Admissible Backdoor Sets
Boosted GFlowNets: Improving Exploration via Sequential Learning
Busemann Functions in the Wasserstein Space: Existence, Closed-Forms, and Applications to Slicing
(ends 6:00 PM)

MON 4 MAY
8:30 a.m.
Registration
(ends 5:00 PM)
9 a.m.
Invited Talk:
Keynote: Taiji Suzuki
Taiji Suzuki
(ends 10:00 AM)
10 a.m.
Break:
Break
(ends 10:30 AM)
10:30 a.m.
Oral Session 6: Generative Modeling (Diffusion / Flow / Temporal / Graph) [10:30-11:30]
Orals -
Beyond Real Data: Synthetic Data through the Lens of Regularization
Spotlights -
Archetypal Graph Generative Models: Explainable and Identifiable Communities via Anchor-Dominant Convex Hulls
Longitudinal Flow Matching for Trajectory Modeling
Denoising Score Matching with Random Features: Insights on Diffusion Models From Precise Learning Curves
Simplex-to-Euclidean Bijections for Categorical Flow Matching
A Continuous Time Markov Chain Framework for Insertion Language Models
Explicit Density Approximation for Neural Implicit Samplers Using a Bernstein-Based Convex Divergence
High-Performance Self-Supervised Representation Learning by Joint Training of Flow Matching and Representation Encoder
(ends 11:30 AM)
11:30 a.m.
Oral Session 7: Causality, Kernels & Statistical Testing [11:30-12:30]
Orals -
Orthogonal Representation Learning for Estimating Causal Quantities
Spotlights -
On the Number of Conditional Independence Tests in Constraint-based Causal Discovery
A Semi-Supervised Kernel Two-Sample Test
DP-SPRT: Differentially Private Sequential Probability Ratio Tests
On the Intrinsic Dimensions of Data in Kernel Learning
RealStats: A Rigorous Real-Only Statistical Framework for Fake Image Detection
The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification
Distribution free M-estimation
(ends 12:30 PM)
12:30 p.m.
Break:
Lunch
(ends 2:00 PM)
2 p.m.
Oral Session 8: Robustness, Calibration, Privacy & Evaluation (Applied) [2:00-3:00]
Orals -
Panprediction: Optimal Predictions for Any Downstream Task and Loss
Spotlights -
OEUVRE: OnlinE Unbiased Variance-Reduced loss Estimation
On the calibration of survival models with competing risks
Patch2Loc: Learning to Localize Patches for Unsupervised Brain Lesion Detection
AMRM-Pure: Semantic-Preserving Adversarial Purification
Scalable Utility-Aware Multiclass Calibration
Near Optimal Dropout-Robust Sortion
SetPINNs: Set-based Physics-informed Neural Networks
(ends 3:00 PM)
3 p.m.
Poster Session 3 [3:00-6:00]
Posters -
Batch-Adaptive Causal Annotations
Quantifying Epistemic Uncertainty in Diffusion Models
PowerSoftmax: Towards Secure LLM Inference Over Encrypted Data
CADENT: Gated Hybrid Distillation for Sample-Efficient Transfer in Reinforcement Learning
Adversary-Free Counterfactual Prediction via Information-Regularized Representations
Accelerating PDE Surrogates via RL-Guided Mesh Optimization
Optimal Transport Guarantees to Nonparametric Regression for Locally Stationary Time Series
On the Hardness of Auditing Model Properties Under Updates: Complexity of Property-Preserving Updates
Active Measurement of Two-Point Correlations
Value Gradient Sampler: Learning Invariant Value Functions for Equivariant Diffusion Sampling
Generalization Bounds for Spectral GNNs via Fourier Domain Analysis
Efficient Model Performance Evaluation Using a Combination of Expert and Crowd-sourced Labels
The Reasoning-Creativity Trade-off: Toward Creativity-Driven Problem Solving
Deep Polynomial Chaos Expansion
On Global Convergence Rates for Federated Softmax Policy Gradient under Heterogeneous Environments
Model Selection for Average Reward RL with Application to Utility Maximization in Repeated Games
RamPINN: Recovering Raman Spectra From Coherent Anti-Stokes Spectra Using Embedded Physics
LLM-as-a-Judge on a Budget
Multiclass Local Calibration with the Jensen-Shannon Distance
Private, Efficient, and Robust Federated Statistical Learning
Learning Linear Regression with Low-Rank Tasks In-Context
Numerical Fragility in Transformers: A Layer-wise Theory for Explaining, Forecasting, and Mitigating Instability
TESLA: Taylor Expansion of Sinusoidal Learnable Activations
Amortized Structural Variational Inference
Aggregation on Learnable Manifolds for Asynchronous Federated Optimisation
Differential Privacy in Kernelized Contextual Bandits via Random Projections
Randomized HyperSteiner: A Stochastic Delaunay Triangulation Heuristic for the Hyperbolic Steiner Minimal Tree
Empirically Calibrated Conditional Independence Tests
MineGrad: Gradient Inversion Attacks on LoRA Fine-Tuning
Discrete State Diffusion Models: A Sample Complexity Perspective
Optimized projection-free algorithms for online learning: construction and worst-case analysis
Frequency-Based Hyperparameter Selection in Games
BOAT: Navigating The Sea of in Silico Predictors for Antibody Design via Multi-Objective Bayesian Optimization
Uncertainty-Aware Meta-Learning with Analytically Tractable Posterior
Conformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise
CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks
GRANITE: A Generalized Regional Framework for Identifying Agreement in Feature-Based Explanations
Adaptive A/B Testing under Nonstationary Dynamics using State-Space Models
Fundamental limits for weighted empirical approximations of exponentially tilted distributions
Network Inversion for Extreme-Case Training-Like Data Reconstruction
Robust Federated Clustering under Heterogeneity and Adversaries
On the Neural Feature Ansatz for Deep Neural Networks
Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization
A New Perspective on Least-Norm Interpolation Under Gaussian Covariates
CoreSPECT: Enhancing Clustering Algorithms via an Interplay of Density and Geometry
Open Multi-agent Multi-armed Bandit with Applications in Permissionless Blockchain
Eliciting Truthful Feedback for Preference-Based Learning via the VCG Mechanism
One-Step Diffusion Samplers via Self-Distillation and Deterministic Flow
Dual Averaging Converges for Nonconvex Smooth Stochastic Optimization
Differentially Private and Federated Structure Learning in Bayesian Networks
Adaptive Diffusion Guidance via Stochastic Optimal Control
Replicable Machine Learning: Theory and Algorithms for Stochastic Convex and Non-Convex Optimization
Efficient Bilevel Optimization with KFAC-Based Hypergradients
A Polynomial-Time Approximation for Pairwise Fair $k$-Median Clustering
UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees
Bandits in Flux: Dynamic Regret under Adversarial Constraints
TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformer
Amortized In-Context Mixed Effect Transformer Models: A Zero-Shot Approach for Pharmacokinetics
Provable Affine Identifiability of Nonlinear CCA under Latent Distributional Priors
Policy Learning with Abstention
Tractable Gaussian Phase Retrieval with Heavy Tails and Adversarial Corruption with Near-Linear Sample Complexity
On the convergence and straightness of flow matching models
Model-independent O(1/k)-convergence rate for TD(0) with linear function approximation, universal learning steps and i.i.d. samples
From Restless to Contextual: A Thresholding Bandit Reformulation for Finite-horizon Improvement
Functional Properties of the Focal-Entropy
DRAUN: An Optimization-Agnostic Data Reconstruction Attack on Federated Unlearning
Spectral Thresholds in Correlated Spiked Models and Fundamental Limits of Partial Least Squares
HGT-FD: Hypergraph transformer for Fraud Detection
Leveraging Machine-Learned Advice in Strategic Interactions with No-Regret Learners
Gradient Descent with Provably Tuned Learning-rate Schedules
On the bias of variational resampling
Q-ShiftDP: A Differentially Private Parameter-Shift Rule for Quantum Machine Learning
Spectral Text Fusion: A Frequency-Aware Approach to Multimodal Time-Series Forecasting
On the Identifiability of Tensor Ranks via Prior Predictive Matching
Learning Equivariant Functions via Quadratic Forms
TexTSC: Class-Texture Preserving Data Condensation for Time Series Classification
Multi-Armed Sampling Problem and the End of Exploration
Fast Private Adaptive Query Answering for Large Data Domains
Generalization Bounds under Heavy-Tailed Losses
Is Supervised Learning Really That Different from Unsupervised?
The Cross-Context Threshold Test: Detecting Discrimination Under Environmental Shifts
Scalable Policy Maximization Under Network Interference
Adaptive Candidate Point Thompson Sampling for High-Dimensional Bayesian Optimization
Disentangling Federated Learning Heterogeneity: A Dual-Perspective Analysis of Quantifying Skew versus Scarcity
Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective
Active Measuring in Reinforcement Learning With Delayed Negative Effects
Atlas-based Manifold Representations for Interpretable Riemannian Machine Learning
Robust Learning of A Group DRO Neuron
Provable FDR Control for Deep Feature Selection: Deep MLPs and Beyond
Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation
Inverse-Free Sparse Variational Gaussian Processes
Orthogonal Representation Learning for Estimating Causal Quantities
Panprediction: Optimal Predictions for Any Downstream Task and Loss
OEUVRE: OnlinE Unbiased Variance-Reduced loss Estimation
On the Number of Conditional Independence Tests in Constraint-based Causal Discovery
On the calibration of survival models with competing risks
Archetypal Graph Generative Models: Explainable and Identifiable Communities via Anchor-Dominant Convex Hulls
Patch2Loc: Learning to Localize Patches for Unsupervised Brain Lesion Detection
A Semi-Supervised Kernel Two-Sample Test
KQ-SVD: Compressing the KV Cache with Provable Guarantees on Attention Fidelity
Empirical PAC-Bayes Bounds for Markov Chains
Longitudinal Flow Matching for Trajectory Modeling
AMRM-Pure: Semantic-Preserving Adversarial Purification
DP-SPRT: Differentially Private Sequential Probability Ratio Tests
Scalable Utility-Aware Multiclass Calibration
Near Optimal Dropout-Robust Sortion
Beyond Real Data: Synthetic Data through the Lens of Regularization
Denoising Score Matching with Random Features: Insights on Diffusion Models From Precise Learning Curves
Simplex-to-Euclidean Bijections for Categorical Flow Matching
On the Intrinsic Dimensions of Data in Kernel Learning
From Decision to Acquisition: Loss-Driven Bayesian Active Learning
Clustering-Based Edge Augmentation for Minimizing the Kirchhoff Index
SetPINNs: Set-based Physics-informed Neural Networks
A Continuous Time Markov Chain Framework for Insertion Language Models
RealStats: A Rigorous Real-Only Statistical Framework for Fake Image Detection
The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification
Distribution free M-estimation
High-Performance Self-Supervised Representation Learning by Joint Training of Flow Matching and Representation Encoder
Auditing Pay-Per-Token in Large Language Models
Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level
Regularizing attention scores with the bootstrapping
Direct Preference Optimization With Unobserved Preference Heterogeneity
Learning to Explore with Lagrangians for Bandits under Unknown Constraints
SenTSR-Bench: Thinking with Injected Knowledge for Time-Series Reasoning
Visual Prompting Reimagined: The Power of Activation Prompts
Optimistic Reinforcement Learning with Quantile Objectives
The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches
Uncovering Hidden Training Dynamics in Neural Networks via Inter-Sample Influence Graphs
ConDiSim: Conditional Diffusion Models for Simulation-Based Inference
Deep Feedback Models
WSBD: Freezing-Based Optimizer for Quantum Neural Networks
Guided by the Experts: Provable Feature Learning Dynamic of Soft-Routed Mixture-of-Experts
A Unifying Framework for Unsupervised Concept Extraction
Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs
Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria
Robustness and Generalization in Uncertainty-Aware Message Passing Neural Networks
Refining Covariance Matrix Estimation in Stochastic Gradient Descent through Bias Reduction
A Gaussian Process View on Observation Noise and Initialization in Wide Neural Networks
VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference
High-Probability Bounds for Heterogeneous Local Differential Privacy
Accelerated Learning on Large Scale Screens using Generative Library Models
Recovery Guarantees for Continual Learning of Dependent Tasks: Memory, Data-Dependent Regularization, and Data-Dependent Weights
TENDE: Transfer Entropy Neural Diffusion Estimation
Calibrated Principal Component Regression
Modeling Multi-Objective Tradeoffs with Monotonic Utility Functions
Explicit Density Approximation for Neural Implicit Samplers Using a Bernstein-Based Convex Divergence
On the Normalization of Confusion Matrices: Methods and Geometric Interpretations
How to approximate inference with subtractive mixture models
Differentially Private Linear Regression and Synthetic Data Generation with Statistical Guarantees
$\epsilon$-Identifiability of Causal Quantities
SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features
Shift is Good: Mismatched Data Mixing Improves Test Performance
Confidence-Guided Self-Training for Gradual Domain Adaptation
ACE-KT: Cascaded Cognitive Modeling for Stage-wise Knowledge Tracing
Improving Adaptive Moment Optimization via Preconditioner Diagonalization
BASTION: A Bayesian Framework for Trend and Seasonality Decomposition
Beyond Spectral Clustering: Probabilistic Cuts for Differentiable Graph Partitioning
Deliberate-When-Needed: Flow-Reasoner for Neuro-Symbolic Continuous Thought
Finite-Time Analysis of Gradient Descent for Shallow Transformers
Predictive Deep Sets
Impact of Positional Encoding: Clean and Adversarial Rademacher Complexity for Transformers under In-Context Regression
ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers
Understanding the Benefits of SimCLR Pre-Training in Two-Layer Convolutional Neural Networks
Auto-Regressive Masked Diffusion Models
Optimal Learning in Two-Player Zero-Sum Games under Delayed Feedback
Contextual ranking and matching. Optimal regret under LST
Beyond the Ideal: Analyzing the Inexact Muon Update
Slithering through Gaps: Capturing Discrete Isolated Modes via Logistic Bridging
Multiple Invertible and Partial-Equivariant Function for Latent Vector Transformation to Enhance Disentanglement in VAEs
PolarQuant: Vector Quantization with Polar Transformation
Latent-IMH: Efficient Bayesian Inference for Inverse Problems with Approximate Operators
Two mathematical models of knowledge distillation
Q-Learning with Shift-Aware Upper Confidence Bound in Non-Stationary Reinforcement Learning
Counterfactually Fair Conformal Prediction
Learning Markov Processes as Sum-of-Square Forms for Analytical Belief Propagation
Regularized $f-$Divergence Kernel Tests
Proof of The TAP Free Energy for High-Dimensional Linear Regression with Spherical Priors at All Temperatures
Understanding SAM's Robustness to Noisy Labels through Gradient Down-weighting
Adversarial Debiasing for Parameter Recovery
Securing Model Weights Against Eavesdropping Adversaries in Federated Learning Using Quantization
Nearly Optimal Best Arm Identification for Semiparametric Bandits
Regression Descent: A Statistical Framework for Neural Network Optimization
Meta-probabilistic Modeling
Multi-Agent Lipschitz Bandits
On the Finite-Sample Bias of Minimizing Expected Wasserstein Loss Between Empirical Distributions
ZipMoE: A Theoretically-Grounded Mixture of Experts Approach forParameter-Efficient Deep Learning
It’s All In The (Exponential) Family: An Equivalence Between Maximum Likelihood Estimation and Control Variates For Sketching Algorithms
On propagation of chaos for the Fisher-Rao gradient flow in entropic mean-field optimization
Three-Step Nav: A Hierarchical Global–Local Planner for Zero-Shot Vision-and-Language Navigation
Efficient Flow Matching using Latent Variables
Closed-Form Coordinate Ascent Variational Inference for Student-t Process Regression with Student-t Likelihood
From Counts to Preferences: Preference-Driven Models for Spatio-Temporal Event Data
A correlation analysis approach to finding interpretable latent representations via conditional generative models
An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representation
Exact Tensor Completion Beyond Isotropy and Invertibility
Learning Right Monotone Permutation Matrices for Neural Subsequence Search
Non-Stationary Functional Bilevel Optimization
Provably Efficient and Agile Randomized Q-Learning
Monotone and Conservative Policy Iteration Beyond the Tabular Case
Retrieval Augmented Time Series Forecasting
The Information Geometry of Local Generalization Dynamics
Black-Box Optimization from Small Offline Datasets via Meta Learning with Synthetic Tasks
Breaking Data Symmetry is Needed For Generalization in Feature Learning Kernels
Bayesian Fourier Features for Reduced Rank Gaussian Processes
(ends 6:00 PM)

TUE 5 MAY
8:30 a.m.
Registration
(ends 2:00 PM)
9 a.m.
Workshop:
OPTIMAL: (O)ptimisation and (P)os(T)-Bayesian (I)nference in (MA)chine (L)earning
(ends 6:00 PM)
Workshop:
Causality in the Age of AI Scaling
(ends 6:00 PM)
Workshop:
Towards Trustworthy Predictions: Theory and Applications of Calibration for Modern AI
(ends 6:00 PM)