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]
(ends 11:30 AM)
11:30 a.m.
Oral Session 2: Learning Theory & High-Dimensional Statistics [11:30-12:30]
(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]
(ends 3:00 PM)
3 p.m.
Poster Session 1 [3:00-6:00]
Posters -
$k$-PCA for (non-squared) Euclidean Distances: Deterministic Polynomial Time Approximation
A Scalable Lift-and-Project Differentiable Approach For the Maximum Cut Problem
Linearly Separable Features in Shallow Nonlinear Networks: Width Scales Polynomially with Intrinsic Data Dimension
LLMs Judging LLMs: A Simplex Perspective
Lloyd's $K$-Means Clustering Algorithm is Frank-Wolfe in Disguise
Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models
Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks
Low-Complexity and Consistent Graphon Estimation from Multiple Networks
Low-rank bias, weight decay, and model merging in neural networks
Lyapunov-Guided Self-Alignment: Test-Time Adaptation for Offline Safe Reinforcement Learning
MDPs with a State Sensing Cost
Meet Me at the Arm: The Cooperative Multi Armed Bandits Problem with Shareable Arms
Accelerating Byzantine-Robust Distributed Learning with Compressed Communication via Double Momentum and Variance Reduction
Meta Sparse Principal Component Analysis
Minimax generalized cross-entropy
Mixture Proportion Estimation and Weakly-supervised Kernel Test for Conditional Independence
MLorc: Momentum Low-rank Compression for Large Language Model Adaptation
Multi-Component VAE with Gaussian Markov Random Field
Narrowing Action Choices with AI Improves Human Sequential Decisions
Near-Optimal Sample Complexities of Divergence-based S-rectangular Distributionally Robust Reinforcement Learning
Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity
Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration
Noise-Free Dynamic Rank-Adaptation via Riemannian Methods in Federated Fine-Tuning
Active learning for stochastic contextual linear bandits
Non-Asymptotic Generalization and Optimization Bounds for Stochastic Gauss-Newton in Deep Neural Networks
Off-policy Distributional Q($\lambda$): Distributional RL without Importance Sampling
On Barycenter Computation: Analyzing Semi-Unbalanced Optimal Transport-based Method on Bures-Wasserstein manifold.
On Computational Limits of FlowAR Models: Expressivity and Efficiency
On Different Notions of Redundancy in Conditional-Independence-Based Discovery of Graphical Models
On Kernel based Variational Autoencoders
On Relation-Aware Slicing in Cross-Domain Alignment
On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial Approach
On the hardness of Reinforcement Learning with Transition Lookahead
On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors
Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning
On the Latent Information Geometry of the Grassmann Manifold
On the Weight Density of L2-Regularized Linear Classification and Regression
Optimal Arm Elimination Algorithms for Combinatorial Bandits
Optimal Posterior Sampling for Policy Identification in Tabular Markov Decision Processes
Optimal rates for density and mode estimation with expand-and-sparsify representations
Optimal Variance and Covariance Estimation under Differential Privacy in the Add-Remove Model and Beyond
Orientability of Causal Relations in Time Series using Summary Causal Graphs and Faithful Distributions
PAC-Bayesian Bounds on Constrained $f$-Entropic Risk Measures
Partially Lazy Gradient Descent for Smoothed Online Learning
PENGUIN: Enhancing Transformer with Periodic-Nested Group Attention for Long-term Time Series Forecasting
ADOPT: Additive Optimal Transport Regression
Policy Testing in Markov Decision Processes
Policy-Oriented Binary Classification: Improving (KD-)CART Final Splits for Subpopulation Targeting
Practical Attribution Guidance for Rashomon Sets
Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory
Preconditioned Attention: Enhancing Efficiency in Transformer Blocks
Preference-based Conditional Treatment Effects and Policy Learning
Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time Methods
Prior shift estimation for positive unlabeled data through the lens of kernel embedding
Probabilistic multi-dimensional classification with incomplete data at the prediction time
Prognostic Scores and Representation Learning for Causal Effect Estimation with Weak Overlap
Almost Sure Convergence of Differential Temporal Difference Learning for Average Reward Markov Decision Processes
Projection-free Algorithms for Online Convex Optimization with Adversarial Constraints
Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective
Provable Guarantees for Estimating Covariances between Latent Variables with Application to Precision Matrix Estimation
Provable Target Sample Complexity Improvements as Pre‑Trained Models Scale
Random Features for Operator-Valued Kernels: Bridging Kernel Methods and Neural Operators
Rate-optimal Design for Anytime Best Arm Identification
Regret Guarantees for Linear Contextual Stochastic Shortest Path
Regularized Operator Extrapolation Method For Stochastic Bilevel Variational Inequality Problems
Regularizing Extrapolation in Causal Inference
Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction between Feature Alignment and Target Fitting
Amortized Safe Active Learning for Real-Time Data Acquisition: Pretrained Neural Policies from Simulated Nonparametric Functions
Rethinking Intrinsic Dimension Estimation in Neural Representations
Rethinking Probabilistic Circuit Parameter Learning
Revisiting Social Welfare in Bandits: UCB is (Nearly) All You Need
RL-finetuning LLMs from on- and off-policy data with a single algorithm
Robust Estimation of a Sparse Linear Model: Provable Guarantees with Non-convexity
Robust Generalization with Adaptive Optimal Transport Priors for Decision-Focused Learning
Root cause analysis of outliers in unknown cyclic graphs
RoseCDL: Robust and Scalable Convolutional Dictionary Learning for rare-event and anomaly detection
Sample Average Approximation for Alpha-Divergence Minimization with Exponential Convergence Guarantees
Scalable Learning of Multivariate Distributions via Coresets
An Indicator of Membership Inference Security in Post-Training Quantized Models
Scalable Spatiotemporal Inference with Biased Scan Attention Transformer Neural Processes
Secretary problem with predictions and ordering
Semi-Implicit Variational Inference via Kernelized Path Gradient Descent
Sequential 1-bit Mean Estimation with Near-Optimal Sample Complexity
SFBD Flow: A Continuous-Optimization Framework for Training Diffusion Models with Noisy Samples
Sparse Linear Bandits with Blocking Constraints
Sparse Linear Bandits with Fixed Sparsity Support: Adversarial and Stochastic Regimes
Sparse Offline Reinforcement Learning with Corruption Robustness
Spectral Clustering for Directed Graphs via Likelihood Estimation on Stochastic Block Models
SPIRE: Conditional Personalization for Federated Diffusion Generative Models
An Information-Theoretic Approach to Understanding Transformers' In-Context Learning of Variable-Order Markov Chains
Split-Flows: Measure Transport and Information Loss Across Molecular Resolutions
Standard Acquisition is Sufficient for Asynchronous Bayesian Optimization
Stochastic Bandits on Mixture Distributions: Metrics & Regret Bounds
Structural Alignment Improves Graph Test-Time Adaptation
Structured Difference-of-Q via Orthogonal Learning
Structured Matrix Scaling for Multi-Class Calibration
Support Basis: Fast Attention Beyond Bounded Entries
TAS-EGNN: Task-Aware Spectral Ego-Graphs for Efficient GNNs-Based Classification
The Majority Vote Paradigm Shift: When Popular Meets Optimal
The Minimax Lower Bound of Kernel Stein Discrepancy Estimation
Balanced and Robust Multi-Treatment Experimental Designs via Randomized Differencing
The Riemannian Geometry associated to Gradient Flows of Linear Convolutional Networks
Topological Alignment of Shared Vision-Language Embedding Space
Towards Motion-aware Referring Image Segmentation
Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity
Tyler’s M-estimator Through the Lens Of Convex-Concave Programming
Uncertainty-Aware Meta-Learning with Analytically Tractable Posterior
Understanding Generalization in Node and Link Prediction
Unsupervised Ensemble Learning Through Deep Energy-based Models
Variance Constrained Distribution Alignment in Few-shot Models
Variance Reduction Methods Do Not Need to Compute Full Gradients: Improved Efficiency through Shuffling
A Consequentialist Critique of Binary Classification Evaluation Practices: Theory, Practice, and Tools
Bandit-based Maximum Inner Product Search with Data-Dependent Confidence Intervals
Weighted quantization using MMD: From mean field to mean shift using gradient flows
Welfare-Centric Clustering
When Can Federated Learning Match Centralized Learning? A PAC-Bayesian Generalization Gap Analysis
Where You Place the Norm Matters: From Prejudiced to Neutral Initializations
Bayesian Model Selection via a Data-Emphasized Variational Objective
Beyond Binary Out of Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories
Beyond Black-Box Predictions: Identifying Marginal Feature Effects in Tabular Transformer Networks
Beyond Johnson-Lindenstrauss: Uniform Bounds for Sketched Bilinear Forms
Beyond Pooling: Matching for Robust Generalization under Data Heterogeneity
Boltzmann Exploration for Heavy-Tailed Bandits
Brenier Isotonic Regression
Catoni-Style Change Point Detection for Regret Minimization in Piecewise-Stationary Heavy-Tailed Bandits
Causal Additive Models with Unobserved Causal Paths and Backdoor Paths
A Covering Framework for Offline POMDPs Learning using Belief Space Metric
Causal Partial Identification via Conditional Optimal Transport
Causal-DRF: Conditional Kernel Treatment Effect Estimation using Distributional Random Forest
Closed-Form Coordinate Ascent Variational Inference for Student-t Process Regression with Student-t Likelihood
Composable Coresets for Constrained Determinant Maximization and Beyond
Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Text-Guided Generative AI Models
Conformal Prediction in Hierarchical Classification with Constrained Representation Complexity
Conformal Robust Control of Linear Systems
Consistent PCA and Spectral Clustering
Contraction rates for generalized posteriors based on $f$-divergences: a diffusion process approach
Convergence of projected stochastic natural gradient variational inference: Balancing speed, computational effort, and accuracy
A Finite Time Analysis of Thompson Sampling for Bayesian Optimization with Preferential Feedback
Convexified Message-Passing Graph Neural Networks
Corruption Robust Thompson Sampling for Gaussian Bandits
Counterfactual Credit Guided Bayesian Optimization
Dashed Line Defense: Plug-And-Play Defense Against Adaptive Score-Based Query Attacks
DeepRV: Accelerating spatiotemporal inference with pre-trained neural priors
Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency without Model Sweeps
Design-Based Finite-Sample Analysis for Regression Adjustment
Differential Privacy in Kernelized Contextual Bandits via Random Projections
Differentially Private Algorithms for the Stochastic Compositional Optimization Problem
Differentially Private Clustering in Data Streams
A projection-based framework for gradient-free and parallel learning
Differentially Private Minimum Spanning Tree in Euclidean Graphs
DISPO: Enhancing Training Efficiency and Stability in Reinforcement Learning for Large Language Model Mathematical Reasoning
Doctor Rashomon and the UNIVERSE of Madness: Variable Importance with Unobserved Confounding and the Rashomon Effect
Dualformer: Time-Frequency Dual Domain Learning for Long-term Time Series Forecasting
Duality-based Residual Estimation for Fully Offline Value-based Reinforcement Learning
Dyno-Net: A Dynamic Feature Extraction Model for Gastrointestinal Polyp Detection
E-Scores for (In)Correctness Assessment of Generative Model Outputs
Efficient Learning of Stationary Diffusions with Stein-type Discrepancies
Efficient Subgroup Analysis via Optimal Trees with Global Parameter Fusion
Empirical PAC-Bayes bounds for Markov chains
A Proof of Learning Rate Transfer under $\mu$P
Enhancing LLM Safety through a Theoretical Minimax Game Lens
Examining the Bias of In-Batch Sampling in Similarity Learning with Two-Tower Models
Explanation Design in Strategic Learning: Sufficient Explanations that Induce Non-harmful Responses
Fair Clustering via Hierarchical Fair-Dirichlet Prior
Feature Importance via Sets of Locally Performant Linear Models
FedCCA: Federated Canonical Correlation Analysis
FedDuA: Doubly Adaptive Federated Learning
FIELDING: Clustered Federated Learning with Data Drift
Filter, Augment, Forecast: Online Data Selection for Robust Time Series Forecasting
FocusViT: Faithful Explanations for Vision Transformers via Gradient-Guided Layer-Skipping
A pure hypothesis test for inhomogeneous random graph models based on a kernelised Stein discrepancy
From Guess2Graph: When and How Can Unreliable Experts Safely Boost Causal Discovery in Finite Samples?
Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent
Gaussian Equivalence for Self-Attention: Asymptotic Spectral Analysis of Attention Matrix
General Weighted Averaging in Stochastic Gradient Descent: CLT and Adaptive Optimality
Generalized and Optimal Straight-Through Estimators
Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids
GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification
GiVA: Gradient-Informed Bases for Vector-Based Adaptation
Graphon Mixtures
Happiness as a Measure of Fairness
A Recovery Theory for Diffusion Priors: Deterministic Analysis of the Implicit Prior Algorithm
Harnessing the Power of Reinforcement Learning for Adaptive MCMC
Hellinger Multimodal Variational Autoencoders
High Effort, Low Gain: Fundamental Limits of Active Learning for Linear Dynamical Systems
High-Dimensional Analysis of Bootstrap Ensemble Classifiers
High-dimensional Learning with Noisy Labels
High-dimensional Level Set Estimation with Trust Regions and Double Acquisition Functions
Identifiability of potentially degenerate Gaussian Mixture Models with piecewise affine mixing
Implicit Updates for Average-Reward Temporal Difference Learning
Improved Algorithms for Clustering with Noisy Distance Oracles
Improving Coverage in Combined Prediction Sets with Weighted p-values
A Regularized Actor-Critic Algorithm for Bi-Level Reinforcement Learning
Improving Semantic Uncertainty Quantification in Language Models via Token-Level Temperature Scaling
Incorporating Expert Knowledge into Bayesian Causal Discovery of Mixtures of Directed Acyclic Graphs
Influence Attributions can be Systematically Altered by Model Manipulation
Information Hidden in Gradients of Regression with Target Noise
Integrating Feature Correlation in Differential Privacy with Applications in DP-ERM
Laplace approximation for Bayesian variable selection via Le Cam's one-step procedure
Learning in Continuous State-Space MDPs for Network Inventory Management
Learning with Incomplete Context: Linear Contextual Bandits with Pretrained Imputation
Likelihood-Free Inference via Structured Score Matching
Linear Convergence of the Frank-Wolfe Algorithm over Product Polytopes
(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]
(ends 11:30 AM)
11:30 a.m.
Paper Award Talks [11:30-12:30]
(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]
(ends 3:00 PM)
3 p.m.
Poster Session 2 [3:00-6:00]
Posters -
A Bayesian Information-Theoretic Approach to Data Attribution
Adaptive Coverage Policies in Conformal Prediction
Linear Reasoning vs. Proof by Cases: Obstacles for Large Language Models in FOL Problem Solving
Lipschitz Multiscale Deep Equilibrium Models: A Theoretically Guaranteed and Accelerated Approach
LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics Engines
Local Causal Discovery for Statistically Efficient Causal Inference
Local Regression on Path Spaces with Signature Metrics
Loss Gaps Parity for Fairness in Heterogeneous Federated Learning
Lower Bounds for Public-Private Learning under Distribution Shift
Mask-Conditional Conformal Prediction: Valid Uncertainty For All Missing Data Mechanisms
Minimax-Optimal Two-Sample Test with Sliced Wasserstein
Minimizing Human Intervention in Online Classification
Adversarial Robustness in One-Stage Learning-to-Defer
Momentum SVGD-EM for Accelerated Maximum Marginal Likelihood Estimation
Moonwalk: Inverse-Forward Differentiation
Multi-Metric Adaptive Experimental Design under a Fixed Budget with Validation
Multilayer Correlation Clustering
Near-optimal Rank Adaptive Inference of High Dimensional Matrices
Near-Optimal Swap Regret in Combinatorial Bandits
NeST-BO: Fast Local Bayesian Optimization via Newton-Step Targeting of Gradient and Hessian Information
Neural Doubly Robust Proximal Causal Estimation
Neuron Block Dynamics for XOR Classification with Zero-Margin
Nonparametric Multi Change Point Detection for Markov Chains via Adaptive Clustering
AlphaFold's Bayesian Roots in Probability Kinematics
On the Convergence and Stability of Distributed Sub-model Training
On the Misinformation in a Statistical Experiment
On the optimal regret of collaborative personalized linear bandits
On the Role of Depth in the Expressivity of RNNs
Online Learning-to-Defer with Varying Experts
Optimal Local Convergence Rates of Stochastic First-Order Methods under Local $\alpha$-PL
Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees
Optimistic Actor-Critic with Parametric Policies: Unifying Sample Efficiency and Practicality
Parameter-Free Dynamic Regret for Unconstrained Linear Bandits
Partial Monotonicity for Submodular Maximization with a Knapsack Constraint
An Evaluation of Cost Functions for Algorithmic Recourse
Partial VOROS: A Cost-aware Performance Metric for Binary Classifiers with Precision and Capacity Constraints
Personalized Incentive Alignment: Correcting Utility-Driven Selection Bias in A/B Tests
Power Transform Revisited: Numerically Stable, and Federated
Private Synthetic Graph Generation and Fused Gromov-Wasserstein Distance
Process-Tensor Tomography of SGD: Measuring Non-Markovian Memory via Back-Flow of Distinguishability
Provable Accelerated Bayesian Optimization with Knowledge Transfer
Provably Efficient and Agile Randomized Q-Learning
Provably Efficient Reinforcement Learning for Sparse Dynamical Systems with Non-Gaussian Noise
Pure Exploration with Infinite Answers
Rank Lifting and Random Non-Linear Maps
An Information-Geometric Approach to Artificial Curiosity
Rashomon Effect for Visualizing High-Dimensional Data
Rate optimal learning of equilibria from data
Recency Biased Causal Attention for Time-series Forecasting
Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning
Reinforcement Learning Using Known Invariances
Representation Learning via Non-Contrastive Mutual Information
Representative, Informative, and De-Amplifying: Requirements for Robust Bayesian Active Learning under Model Misspecification
ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory
Robust estimation of heterogeneous treatment effects in randomized trials leveraging external data
Scalable Model-Based Clustering with Sequential Monte Carlo
Asymptotic optimality theory of confidence intervals of the mean
Semi-Random Noisy and One-Bit Matrix Completion With Nonconvex Primal-Dual Framework
Sequential Off-Policy Learning with Logarithmic Smoothing
Set to Be Fair: Demographic Parity Constraints for Set-Valued Classification
Sharp risk bounds for early-stopping in Gaussian linear regression
SiGHT: A Self-Supervised Graph-based Hallucination DeTection Framework for Domain-Specific LLMs
Stationarity-Aware Causal Discovery in Time Series via Minimal Separating Sets
Statistical Inference for Explainable Boosting Machines
Statistical-computational gap in multiple Gaussian graph alignment
Stick-Breaking Embedded Topic Model with Continuous Optimal Transport for Online Analysis of Document Streams
Structured Matching via Cost-Regularized Unbalanced Optimal Transport
Bad Values but Good Behavior: Learning Highly Misspecified Bandits with Function Approximation
Structured Temporal Inference in State-Space Models
T$_k$CP: Context-Aware Pooling via Top-k% Activation Selection
Tensor Gaussian Processes: Efficient Solvers for Nonlinear PDEs
The Role of Causal Features in Strategic Classification for Robustness and Alignment
Thompson Sampling-like Algorithms for Stochastic Rising Bandits
Three-operator splitting with stale gradients for faster non-linear optimal transport
Tight Analysis of Decentralized SGD: a Markov Chain Perspective
Tight Lower Bounds and Optimal Algorithms for Stochastic Nonconvex Optimization with Heavy-Tailed Noise
Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games
Time Series Forecasting with Hahn Kolmogorov-Arnold Networks
Bayesian Inverse Transition Learning: Learning Dynamics from Near-Optimal Trajectories
Time-Aware Synthetic Control
Towards Blackwell Optimality: Bellman Optimality Is All You Can Get
Towards Characterizing the Complexity of Riemannian Online Convex Optimization
Towards Sensitivity-Aware Language Models
Tractable Shapley Values and Interactions via Tensor Networks
Training Latent Diffusion Models with Interacting Particle Algorithms
Transportability without Graphs: A Bayesian Approach to Identifying s-Admissible Backdoor Sets
Uncertainty Quantification for Named Entity Recognition via Conformal Prediction
Undersmoothing Black-Box Models for Functional Estimation
Understanding and Steering Large Generative Models Using Constitutions for Atomic Concept Edits
Best Policy Learning from Trajectory Preference Feedback
Unified Causal Discovery and Missing Data Imputation
Unmixing Mean Embeddings for Domain Adaptation with Target Label Proportion
Variational Grey-Box Dynamics Matching
Variational inference via radial transport
We Still Don’t Understand High-Dimensional Bayesian Optimization
Where the Score Lives: A Wavelet View of Diffusion
Why is prompting hard? Understanding prompts on binary sequence predictors
Zeroth-Order Stochastic Compositional Gradient Descent: Towards Black-Box Sparse AUC Maximization
Beyond Binning: Soft Task Reformulation for Deep Regression
A Divergence-Based Method for Weighting and Averaging Model Predictions
Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks
Boosted GFlowNets: Improving Exploration via Sequential Learning
Bounds and Identification of Joint Probabilities of Potential Outcomes and Observed Variables under Monotonicity Assumptions
Busemann Functions in the Wasserstein Space: Existence, Closed-Forms, and Applications to Slicing
Canopy Tree Height Estimation using Quantile Regression: Modeling and Evaluating Uncertainty in Remote Sensing
Certifying Reading Comprehension in Large Language Models
Clustering in Mixtures of Ergodic Markov Chains: Fundamental Limit and Two-Stage Algorithm
Community-Enhanced Semi-seeded Network Alignment (CESSNA): A Robust Method with Application to Microbiome Networks
Complexity-Aware Deep Symbolic Regression with Robust Risk-Seeking Policy Gradients
Computationally Lightweight Classifiers with Frequentist Bounds on Prediction Errors
A Geometric Approach to Optimal Experimental Design
Conditional Flow Matching for Bayesian Posterior Sampling
ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models
Connectome-Guided Optimization for Deep Networks
Conservative Inference in Switchback Experiments
Corruption-robust Offline Multi-agent Reinforcement Learning from Human Feedback
Counterfactual Explanations via Latent Structure for Time Series Classification
Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits
CTRLS: Chain-of-Thought Reasoning via Latent State-Transition
Data Distribution Valuation Using Generalized Bayesian Inference
Deformed Decomposition for Non-negative Tensors
A Goemans-Williamson type algorithm for identifying subcohorts in clinical trials
Demystifying Transition Matching: When and Why It Can Beat Flow Matching
Differentially Private E-Values
DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification
Do we need rebalancing strategies? A theoretical and empirical study around SMOTE and its variants
ECAI: Efficient Convolution Activation Inversion for Constant-Memory Convolutional Neural Networks Training
Efficient and Accurate Tensor Compression via Recursive Sketching
Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space
Efficient Logistic Regression with Mixture of Sigmoids
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
Enforcing Fair Predicted Scores on Intervals of Percentiles by Difference-of-Convex Constraints
A Modularized Framework for Piecewise-Stationary Restless Bandits
Entropic Projection Alignment: Estimating, Explaining, and Improving Model Performance Under Tabular Distribution Shift
Ergodic and Subhomogeneous Dynamics in Hyperbolic Neural Networks
Evaluation of Large Language Models via Coupled Token Generation
EventFlow: Forecasting Temporal Point Processes with Flow Matching
Exact and Approximate MCMC for Doubly-intractable Probabilistic Graphical Models Leveraging the Underlying Independence Model
Explore-then-Commit for Nonstationary Linear Bandits with Latent Dynamics
Fact-Augmented Lookahead for LLM Agents: Simple Online Memory, No Finetuning
FairSHAP: Preprocessing for Fairness Through Attribution-Based Data Augmentation
Fast and Robust Simulation-Based Inference With Optimization Monte Carlo
Fast Quasar-Convex Optimization with Constraints
Accelerated Distributed Optimization with Compression and Error Feedback
Faster parallel MCMC: Metropolis adjustment is best served warm
FastRank: Fast Tensor Rank Approximation based on Spectral Energy
FlowPINNs: A Variational Framework for PDE Parameter Inference and Uncertainty Quantification
Formally Exploring Time-Series Anomaly Detection Evaluation Metrics
Free Random Projection for In-Context Reinforcement Learning
From Cells to Sentences: An End-to-End Framework for Table Understanding
From Hawkes Processes to Attention: Time-Modulated Mechanisms for Event Sequences
From Token Imbalance to Balanced Routing: An ELBO-Regularized Probabilistic Framework for Contrastive Multimodal Learning
From Transformers to State Spaces: GeoMamba-SE(3) for Fast and Accurate Molecular Learning
Fundamental Limits of Non-Adaptive Group Testing With Markovian Correlation
Accelerating PDE Surrogates via RL-Guided Mesh Optimization
Generalized Correlation Shifting for Lasso
GL-LowPopArt: A Nearly Instance-Wise Minimax Estimator for Generalized Low-Rank Trace Regression
Gradient Regularized Natural Gradients
Gradient-flow SDEs have unique transient population dynamics
Graph Learning is Suboptimal in Causal Bandits
Hybrid Meta-Learners for Estimating Heterogeneous Treatment Effects
Hyperbolic Learning with Supervision from any Granularity
Hyperbolic Part-Whole Image Segmentation
Hypergraph Neural Networks Accelerate MUS Enumeration
i-IF-Learn: Iterative Feature Selection and Unsupervised Learning for High-Dimensional Complex Data
Active Subspaces in Infinite Dimension
Identification and Estimation of "Probabilities of Causation" in the Presence of Confounding and Selection Bias
In-Context Function Learning in Large Language Models
In-Context Learning for Discrete Optimal Transport: Can Transformers Sort?
Incentivizing Truthful Submissions in a Data Marketplace for Mean Estimation
Incoherence in goal-conditioned autoregressive models
Information-theoretic error bounds for source localization in neural sensing
Injecting Measurement Information Yields a Fast and Noise-Robust Diffusion-Based Inverse Problem Solver
Interpretable DNA Sequence Classification via Dynamic Feature Generation in Decision Trees
Kernel Treatment Effects with Adaptively Collected Data
Lag Operator SSMs: A Geometric Framework for Structured State Space Modeling
Adaptive Combinatorial Experimental Design: Pareto Optimality for Decision-Making and Inference
LAMP: Extracting Local Decision Surfaces from Large Language Models
LatticeVision: Image to Image Networks for Modeling Non-Stationary Spatial Data
Learnability with partial labels and adaptive nearest neighbors
Learning Geometry and Topology via Multi-Chart Flows
Learning How Deep to Go: Self-Scaling Deep Reinforcement Learning
Learning Physical Operators using Neural Operators
Learning to Bid in Discriminatory Auctions with Budget Constraints
Learning to Choose or Choosing to Learn: Best-of-N vs. Supervised Fine-Tuning for Bit String Generation
Learning under Moral Hazard with Instrumental Regression and Generalized Method of Moments
Learning When Not to Learn: Risk-Sensitive Abstention in Bandits with Unbounded Rewards
(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]
(ends 11:30 AM)
11:30 a.m.
Oral Session 7: Causality, Kernels & Statistical Testing [11:30-12:30]
(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]
(ends 3:00 PM)
3 p.m.
Poster Session 3 [3:00-6:00]
Posters -
$\epsilon$-Identifiability of Causal Quantities
ACE-KT: Cascaded Cognitive Modeling for Stage-wise Knowledge Tracing
Learning to Explore with Lagrangians for Bandits under Unknown Constraints
Leveraging Machine-Learned Advice in Strategic Interactions with No-Regret Learners
LLM-as-a-Judge on a Budget
Longitudinal Flow Matching for Trajectory Modeling
Meta-probabilistic Modeling
MineGrad: Gradient Inversion Attacks on LoRA Fine-Tuning
Model Selection for Average Reward RL with Application to Utility Maximization in Repeated Games
Model-independent O(1/k)-convergence rate for TD(0) with linear function approximation, universal learning steps and i.i.d. samples
Modeling Multi-Objective Tradeoffs with Monotonic Utility Functions
Monotone and Conservative Policy Iteration Beyond the Tabular Case
Active Measurement of Two-Point Correlations
Multi-Agent Lipschitz Bandits
Multi-Armed Sampling Problem and the End of Exploration
Multiclass Local Calibration with the Jensen-Shannon Distance
Multiple Invertible and Partial-Equivariant Function for Latent Vector Transformation to Enhance Disentanglement in VAEs
Near Optimal Dropout-Robust Sortion
Nearly Optimal Best Arm Identification for Semiparametric Bandits
Network Inversion for Extreme-Case Training-Like Data Reconstruction
Non-Stationary Functional Bilevel Optimization
Numerical Fragility in Transformers: A Layer-wise Theory for Explaining, Forecasting, and Mitigating Instability
OEUVRE: OnlinE Unbiased Variance-Reduced loss Estimation
Active Measuring in Reinforcement Learning With Delayed Negative Effects
On Global Convergence Rates for Federated Softmax Policy Gradient under Heterogeneous Environments
On propagation of chaos for the Fisher-Rao gradient flow in entropic mean-field optimization
On the bias of variational resampling
On the calibration of survival models with competing risks
On the convergence and straightness of flow matching models
On the Finite-Sample Bias of Minimizing Expected Wasserstein Loss Between Empirical Distributions
On the Hardness of Auditing Model Properties Under Updates: Complexity of Property-Preserving Updates
On the Identifiability of Tensor Ranks via Prior Predictive Matching
On the Intrinsic Dimensions of Data in Kernel Learning
On the Neural Feature Ansatz for Deep Neural Networks
Adaptive A/B Testing under Nonstationary Dynamics using State-Space Models
On the Normalization of Confusion Matrices: Methods and Geometric Interpretations
On the Number of Conditional Independence Tests in Constraint-based Causal Discovery
One-Step Diffusion Samplers via Self-Distillation and Deterministic Flow
Open Multi-agent Multi-armed Bandit with Applications in Permissionless Blockchain
Optimal Learning in Two-Player Zero-Sum Games under Delayed Feedback
Optimal Transport Guarantees to Nonparametric Regression for Locally Stationary Time Series
Optimistic Reinforcement Learning with Quantile Objectives
Optimized projection-free algorithms for online learning: construction and worst-case analysis
Orthogonal Representation Learning for Estimating Causal Quantities
Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective
Adaptive Candidate Point Thompson Sampling for High-Dimensional Bayesian Optimization
Panprediction: Optimal Predictions for Any Downstream Task and Loss
Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation
Patch2Loc: Learning to Localize Patches for Unsupervised Brain Lesion Detection
PolarQuant: Vector Quantization with Polar Transformation
Policy Learning with Abstention
PowerSoftmax: Towards Secure LLM Inference Over Encrypted Data
Predictive Deep Sets
Private, Efficient, and Robust Federated Statistical Learning
Proof of The TAP Free Energy for High-Dimensional Linear Regression with Spherical Priors at All Temperatures
Provable Affine Identifiability of Nonlinear CCA under Latent Distributional Priors
Adaptive Diffusion Guidance via Stochastic Optimal Control
Provable FDR Control for Deep Feature Selection: Arbitrarily Deep MLPs and Transformers
ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers
Q-Learning with Shift-Aware Upper Confidence Bound in Non-Stationary Reinforcement Learning
Q-ShiftDP: A Differentially Private Parameter-Shift Rule for Quantum Machine Learning
Quantifying Epistemic Uncertainty in Diffusion Models
RamPINN: Recovering Raman Spectra From Coherent Anti-Stokes Spectra Using Embedded Physics
Randomized HyperSteiner: A Stochastic Delaunay Triangulation Heuristic for the Hyperbolic Steiner Minimal Tree
RealStats: A Rigorous Real-Only Statistical Framework for Fake Image Detection
Recovery Guarantees for Continual Learning of Dependent Tasks: Memory, Data-Dependent Regularization, and Data-Dependent Weights
Refining Covariance Matrix Estimation in Stochastic Gradient Descent through Bias Reduction
Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization
Regression Descent: A Statistical Framework for Neural Network Optimization
Regularized $f-$Divergence Kernel Tests
Regularizing attention scores with the bootstrapping
Replicable Machine Learning: Theory and Algorithms for Stochastic Convex and Non-Convex Optimization
Retrieval Augmented Time Series Forecasting
Robust Federated Clustering under Heterogeneity and Adversaries
Robust Learning of A Group DRO Neuron
Robustness and Generalization in Uncertainty-Aware Message Passing Neural Networks
Scalable Policy Maximization Under Network Interference
Scalable Utility-Aware Multiclass Calibration
Adversarial Debiasing for Parameter Recovery
Securing Model Weights against Eavesdropping Adversaries in Federated Learning using Quantization
SetPINNs: Set-based Physics-informed Neural Networks
Shift is Good: Mismatched Data Mixing Improves Test Performance
Simplex-to-Euclidean Bijections for Categorical Flow Matching
Slithering through Gaps: Capturing Discrete Isolated Modes via Logistic Bridging
Spectral Text Fusion: A Frequency-Aware Approach to Multimodal Time-Series Forecasting
Spectral Thresholds in Correlated Spiked Models and Fundamental Limits of Partial Least Squares
SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features
TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformer
TENDE: Transfer Entropy Neural Diffusion Estimation
Adversary-Free Counterfactual Prediction via Information-Regularized Representations
TESLA: Taylor Expansion of Sinusoidal Learnable Activations
TexTSC: Class-Texture Preserving Data Condensation for Time Series Classification
The Cross-Context Threshold Test: Detecting Discrimination Under Environmental Shifts
The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification
The Information Geometry of Local Generalization Dynamics
The Reasoning-Creativity Trade-off: Toward Creativity-Driven Problem Solving
The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches
Three-Step Nav: A Hierarchical Global–Local Planner for Zero-Shot Vision-and-Language Navigation
Time-series Diagnostic Reasoning with Knowledge Injection
Tractable Gaussian Phase Retrieval with Heavy Tails and Adversarial Corruption with Near-Linear Sample Complexity
Aggregation on Learnable Manifolds for Asynchronous Federated Optimisation
Two mathematical models of knowledge distillation
Uncovering Hidden Training Dynamics in Neural Networks via Inter-Sample Influence Graphs
Understanding SAM's Robustness to Noisy Labels through Gradient Down-weighting
Understanding the Benefits of SimCLR Pre-Training in Two-Layer Convolutional Neural Networks
UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees
Value Gradient Sampler: Learning Invariant Value Functions for Equivariant Diffusion Sampling
VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference
Visual Prompting Reimagined: The Power of Activation Prompts
WSBD: Freezing-Based Optimizer for Quantum Neural Networks
ZipMoE: A Theoretically-Grounded Mixture of Experts Approach forParameter-Efficient Deep Learning
A Continuous Time Markov Chain Framework for Insertion Language Models
Amortized In-Context Mixed Effect Transformer Models: A Zero-Shot Approach for Pharmacokinetics
Amortized Structural Variational Inference
AMRM-Pure: Semantic-Preserving Adversarial Purification
An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representation
Archetypal Graph Generative Models: Explainable and Identifiable Communities via Anchor-Dominant Convex Hulls
Atlas-based Manifold Representations for Interpretable Riemannian Machine Learning
Auditing Pay-Per-Token in Large Language Models
Auto-Regressive Masked Diffusion Models
Bandits in Flux: Dynamic Regret under Adversarial Constraints
BASTION: A Bayesian Framework for Trend and Seasonality Decomposition
A correlation analysis approach to finding interpretable latent representations via conditional generative models
Batch-Adaptive Causal Annotations
Bayesian Fourier Features for Reduced Rank Gaussian Processes
Beyond Real Data: Synthetic Data through the Lens of Regularization
Beyond Spectral Clustering: Probabilistic Cuts for Differentiable Graph Partitioning
Beyond the Ideal: Analyzing the Inexact Muon Update
Black-Box Optimization from Small Offline Datasets via Meta Learning with Synthetic Tasks
BOAT: Navigating The Sea of in Silico Predictors for Antibody Design via Multi-Objective Bayesian Optimization
Breaking Data Symmetry is Needed For Generalization in Feature Learning Kernels
CADENT: Gated Hybrid Distillation for Sample-Efficient Transfer in Reinforcement Learning
Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs
A Gaussian Process View on Observation Noise and Initialization in Wide Neural Networks
Calibrated Principal Component Regression
CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks
Clustering-Based Edge Augmentation for Minimizing the Kirchhoff Index
ConDiSim: Conditional Diffusion Models for Simulation-Based Inference
Confidence-Guided Self-Training for Domain Adaptation
Conformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise
Contextual ranking and matching. Optimal regret under LST
Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria
CoreSPECT: Enhancing Clustering Algorithms via an Interplay of Density and Geometry
Counterfactually Fair Conformal Prediction
A New Perspective on Least-Norm Interpolation Under Gaussian Covariates
Deep Feedback Models
Deep Polynomial Chaos Expansion
Deliberate-When-Needed: Flow-Reasoner for Neuro-Symbolic Continuous Thought
Denoising Score Matching with Random Features: Insights on Diffusion Models from Precise Learning Curves
Differentially Private and Federated Structure Learning in Bayesian Networks
Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level
Differentially Private Linear Regression and Synthetic Data Generation with Statistical Guarantees
Direct Preference Optimization With Unobserved Preference Heterogeneity
Discrete State Diffusion Models: A Sample Complexity Perspective
Disentangling Federated Learning Heterogeneity: A Dual-Perspective Analysis of Quantifying Skew versus Scarcity
A Polynomial-Time Approximation for Pairwise Fair $k$-Median Clustering
Distribution free M-estimation
DP-SPRT: Differentially Private Sequential Probability Ratio Tests
DRAUN: An Optimization-Agnostic Data Reconstruction Attack on Federated Unlearning
Dual Averaging Converges for Nonconvex Smooth Stochastic Optimization
Efficient Bilevel Optimization with KFAC-Based Hypergradients
Efficient Flow Matching using Latent Variables
Efficient model performance evaluation using a combination of expert and crowd-sourced labels
Eliciting Truthful Feedback for Preference-Based Learning via the VCG Mechanism
Empirically Calibrated Conditional Independence Tests
Exact Tensor Completion Powered by Slim Transforms
A Semi-Supervised Kernel Two-Sample Test
Explicit Density Approximation for Neural Implicit Samplers Using a Bernstein-Based Convex Divergence
Fast Private Adaptive Query Answering for Large Data Domains
Finite-Time Analysis of Gradient Descent for Shallow Transformers
Frequency-Based Hyperparameter Selection in Games
From Counts to Preferences: Preference-Driven Models for Spatio-Temporal Event Data
From Decision to Acquisition: Loss-Driven Bayesian Active Learning
From Restless to Contextual: A Thresholding Bandit Reformulation for Finite-horizon Improvement
Functional Properties of the Focal-Entropy
Fundamental limits for weighted empirical approximations of exponentially tilted distributions
Generalization Bounds for Heavy-Tailed Losses
A Unifying Framework for Unsupervised Concept Extraction
Generalization Bounds for Spectral GNNs via Fourier Domain Analysis
Gradient Descent with Provably Tuned Learning-rate Schedules
GRANITE: A Generalized Regional Framework for Identifying Agreement in Feature-Based Explanations
Guided by the Experts: Provable Feature Learning Dynamic of Soft-Routed Mixture-of-Experts
HGT-FD: Hypergraph transformer for Fraud Detection
High-Performance Self-Supervised Representation Learning by Joint Training of Flow Matching and Representation Encoder
High-Probability Bounds for Heterogeneous Local Differential Privacy
How to approximate inference with subtractive mixture models
Impact of Positional Encoding: Clean and Adversarial Rademacher Complexity for Transformers under In-Context Regression
Improving Adaptive Moment Optimization via Preconditioner Diagonalization
Accelerated Learning on Large Scale Screens using Generative Library Models
In-memory Training on Analog Devices with Limited Conductance States via Multi-tile Residual Learning
Inverse-Free Sparse Variational Gaussian Processes
Is Supervised Learning Really That Different from Unsupervised?
It’s All In The (Exponential) Family: An Equivalence Between Maximum Likelihood Estimation and Control Variates For Sketching Algorithms
KQ-SVD: Compressing the KV Cache with Provable Guarantees on Attention Fidelity
Latent-IMH: Efficient Bayesian Inference for Inverse Problems with Approximate Operators
Learning Equivariant Functions via Quadratic Forms
Learning Linear Regression with Low-Rank Tasks in-Context
Learning Markov Processes as Sum-of-Square Forms for Analytical Belief Propagation
Learning Right Monotone Permutation Matrices for Neural Subsequence Search
(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)