Skip to yearly menu bar Skip to main content


Show Detail
Schedule Thu Fri Sat
Timezone:
America/Los_Angeles
 
Filter Rooms:  

WED 1 MAY
10:30 p.m.
Registration
(ends 8:00 AM)
11:45 p.m.
Remarks:
GC
(ends 12:00 AM)

THU 2 MAY
midnight
Invited Talk:
Invited Talk - Matt Hoffman
Matthew D. Hoffman
(ends 1:00 AM)
1 a.m.
Morning Coffee Break
1:30 a.m.
Oral: RL & Optimization [1:30-2:30]
Orals -
Conformal Contextual Robust Optimization
Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games
Model-based Policy Optimization under Approximate Bayesian Inference
Online Learning of Decision Trees with Thompson Sampling
(ends 2:30 AM)
2:30 a.m.
D&I Panel:
Establishing your own research path in the age of big compute
(ends 3:30 AM)
3:30 a.m.
Lunch - retail
5 a.m.
Oral: Optimization [5:00-6:15]
Orals -
The sample complexity of ERMs in stochastic convex optimization
Stochastic Methods in Variational Inequalities: Ergodicity, Bias and Refinements
Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses
Learning-Based Algorithms for Graph Searching Problems
Graph Partitioning with a Move Budget
(ends 6:15 AM)
6:15 a.m.
Afternoon Coffee Break
6:45 a.m.
Oral: Probabilistic Methods [6:45-8:00]
Orals -
Neural McKean-Vlasov Processes: Distributional Dependence in Diffusion Processes
Reparameterized Variational Rejection Sampling
Intrinsic Gaussian Vector Fields on Manifolds
Generative Flow Networks as Entropy-Regularized RL
Robust Approximate Sampling via Stochastic Gradient Barker Dynamics
(ends 8:00 AM)
8 a.m.
Poster Session 1 [8:00-8:30]
Posters 8:00-
Self-Supervised Quantization-Aware Knowledge Distillation
Directed Hypergraph Representation Learning for Link Prediction
DHMConv: Directed Hypergraph Momentum Convolution Framework
Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint
The Risks of Recourse in Binary Classification
Online Distribution Learning with Local Privacy Constraints
Backward Filtering Forward Deciding in Linear Non-Gaussian State Space Models
Enhancing In-context Learning via Linear Probe Calibration
Sketch In, Sketch Out: Accelerating both Learning and Inference for Structured Prediction with Kernels
Surrogate Bayesian Networks for Approximating Evolutionary Games
Structural perspective on constraint-based learning of Markov networks
Estimation of partially known Gaussian graphical models with score-based structural priors
Distributionally Robust Model-based Reinforcement Learning with Large State Spaces
BOBA: Byzantine-Robust Federated Learning with Label Skewness
Subsampling Error in Stochastic Gradient Langevin Diffusions
Adaptive Batch Sizes for Active Learning: A Probabilistic Numerics Approach
Optimal Sparse Survival Trees
Autoregressive Bandits
Error bounds for any regression model using Gaussian processes with gradient information
Diagonalisation SGD: Fast \& Convergent SGD for Non-Differentiable Models via Reparameterisation and Smoothing
Orthogonal Gradient Boosting for Simpler Additive Rule Ensembles
Robust Data Clustering with Outliers via Transformed Tensor Low-Rank Representation
Towards Achieving Sub-linear Regret and Hard Constraint Violation in Model-free RL
On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation
Fast and Adversarial Robust Kernelized SDU Learning
Analysis of Kernel Mirror Prox for Measure Optimization
Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters
Manifold-Aligned Counterfactual Explanations for Neural Networks
Emergent specialization from participation dynamics and multi-learner retraining
Neural McKean Vlasov Processes: Distributional Dependence in Diffusion Models
A Unifying Variational Framework for Gaussian Process Motion Planning
Regret Bounds for Risk-sensitive Reinforcement Learning with Lipschitz Dynamic Risk Measures
Learning to Rank for Optimal Treatment Allocation Under Resource Constraints
Learning Sparse Codes with Entropy-Based ELBOs
Simple and scalable algorithms for cluster-aware precision medicine
Scalable Learning of Item Response Theory Models
Federated Learning For Heterogeneous Electronic Health Records Utilising Augmented Temporal Graph Attention Networks
Fair Soft Clustering
Clustering Items From Adaptively Collected Inconsistent Feedback
Beyond Bayesian Model Averaging over Paths in Probabilistic Programs with Stochastic Support
Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability
Queuing dynamics of asynchronous Federated Learning
Reparameterized Variational Rejection Sampling
Quantifying Uncertainty in Natural Language Explanations of Large Language Models
Categorical Generative Model Evaluation via Synthetic Distribution Coarsening
Adaptivity of Diffusion Models to Manifold Structures
Density Uncertainty Layers for Reliable Uncertainty Estimation
Uncertainty-aware Continuous Implicit Neural Representations for Remote Sensing Object Counting
Joint control variate for faster black-box variational inference
Classifier Calibration with ROC-Regularized Isotonic Regression
Shape Arithmetic Expressions: Advancing Scientific Discovery Beyond Closed-Form Equations
Feasible $Q$-Learning for Average Reward Reinforcement Learning
Efficient Model-Based Concave Utility Reinforcement Learning through Greedy Mirror Descent
Agnostic Multi-Robust Learning using ERM
MINTY: Rule-based models that minimize the need for imputing features with missing values
Tuning-Free Maximum Likelihood Training of Latent Variable Models via Coin Betting
Intrinsic Gaussian Vector Fields on Manifolds
MIM-Reasoner: Learning with Theoretical Guarantees for Multiplex Influence Maximization
FedFisher: Leveraging Fisher Information for One-Shot Federated Learning
Efficient Graph Laplacian Estimation by Proximal Newton
The Effective Number of Shared Dimensions Between Paired Datasets
On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem
Dynamic Inter-treatment Information Sharing for Individualized Treatment Effects Estimation
Information Theoretically Optimal Sample Complexity of Learning Dynamical Directed Acyclic Graphs
Best Arm Identification with Resource Constraints
ALAS: Active Learning for Autoconversion Rates Prediction from Satellite Data
RL in Markov Games with Independent Function Approximation: Improved Sample Complexity Bound under the Local Access Model
Prior-dependent analysis of posterior sampling reinforcement learning with function approximation
Deep anytime-valid hypothesis testing
Smoothness-Adaptive Dynamic Pricing with Nonparametric Demand Learning
GRAWA: Gradient-based Weighted Averaging for Distributed Training of Deep Learning Models
Tackling the XAI Disagreement Problem with Regional Explanations
Learning Populations of Preferences via Pairwise Comparison Queries
Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations
Equivariant bootstrapping for uncertainty quantification in imaging inverse problems
Contextual Bandits with Budgeted Information Reveal
Conformal Contextual Robust Optimization
Bayesian Online Learning for Consensus Prediction
Variational Gaussian Process Diffusion Processes
Analysis of Privacy Leakage in Federated Large Language Models
Training Implicit Generative Models via an Invariant Statistical Loss
Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Mean
Auditing Fairness under Unobserved Confounding
Better Batch for Deep Probabilistic Time Series Forecasting
Fast Dynamic Sampling for Determinantal Point Processes
Corruption-Robust Offline Two-Player Zero-Sum Markov Games
Adaptive Experiment Design with Synthetic Controls
Looping in the Human: Collaborative and Explainable Bayesian Optimization
Operationalizing Counterfactual Metrics: Incentives, Ranking, and Information Asymmetry
GmGM: a fast multi-axis Gaussian graphical model
From Data Imputation to Data Cleaning --- Automated Cleaning of Tabular Data Improves Downstream Predictive Performance
Certified private data release for sparse Lipschitz functions
Linear Convergence of Black-Box Variational Inference: Should We Stick the Landing?
Riemannian Laplace Approximation with the Fisher Metric
Making Better Use of Unlabelled Data in Bayesian Active Learning
Safe and Interpretable Estimation of Optimal Treatment Regimes
Deep Learning-Based Alternative Route Computation
MMD-based Variable Importance for Distributional Random Forest
A Doubly Robust Approach to Sparse Reinforcement Learning
Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection
Data-Adaptive Probabilistic Likelihood Approximation for Ordinary Differential Equations
Cross-model Mutual Learning for Exemplar-based Medical Image Segmentation
Fair k-center Clustering with Outliers
Learning Granger Causality from Instance-wise Self-attentive Hawkes Processes
Ethics in Action: Training Reinforcement Learning Agents for Moral Decision-making In Text-based Adventure Games
Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data
Attention-based Multi-instance Mixed Models
Is this model reliable for everyone? Testing for strong calibration
Achieving Fairness through Separability: A Unified Framework for Fair Representation Learning
When No-Rejection Learning is Consistent for Regression with Rejection
Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions
Graph Machine Learning through the Lens of Bilevel Optimization
Interpretability Guarantees with Merlin-Arthur Classifiers
Uncertainty Matters: Stable Conclusions under Unstable Assessment of Fairness Results
Sample Complexity Characterization for Linear Contextual MDPs
Asynchronous SGD on Graphs: a Unified Framework for Asynchronous Decentralized and Federated Optimization
A General Algorithm for Solving Rank-one Matrix Sensing
Simulation-Free Schrödinger Bridges via Score and Flow Matching
Estimating treatment effects from single-arm trials via latent-variable modeling
On the Privacy of Selection Mechanisms with Gaussian Noise
Fusing Individualized Treatment Rules Using Secondary Outcomes
Time to Cite: Modeling Citation Networks using the Dynamic Impact Single-Event Embedding Model
Provable local learning rule by expert aggregation for a Hawkes network
Bayesian Semi-structured Subspace Inference
Sample Efficient Learning of Factored Embeddings of Tensor Fields
CAD-DA: Controllable Anomaly Detection after Domain Adaptation by Statistical Inference
TenGAN: Pure Transformer Encoders Make an Efficient Discrete GAN for De Novo Molecular Generation
Explanation-based Training with Differentiable Insertion/Deletion Metric-aware Regularizers
Recovery Guarantees for Distributed-OMP
Imposing Fairness Constraints in Synthetic Data Generation
Optimal Zero-Shot Detector for Multi-Armed Attacks
Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classification
Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients
Learning Safety Constraints from Demonstrations with Unknown Rewards
Stochastic Approximation with Biased MCMC for Expectation Maximization
Offline Policy Evaluation and Optimization Under Confounding
BlockBoost: Scalable and Efficient Blocking through Boosting
DAGnosis: Localized Identification of Data Inconsistencies using Structures
Theory-guided Message Passing Neural Network for Probabilistic Inference
Thompson Sampling Itself is Differentially Private
Robust Approximate Sampling via Stochastic Gradient Barker Dynamics
Mixed variational flows for discrete variables
A White-Box False Positive Adversarial Attack Method on Contrastive Loss Based Offline Handwritten Signature Verification Models
Minimizing Convex Functionals over Space of Probability Measures via KL Divergence Gradient Flow
Fair Supervised Learning with A Simple Random Sampler of Sensitive Attributes
Towards Generalizable and Interpretable Motion Prediction: A Deep Variational Bayes Approach
A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning
Data-Driven Online Model Selection With Regret Guarantees
Online Calibrated and Conformal Prediction Improves Bayesian Optimization
Scalable Algorithms for Individual Preference Stable Clustering
An Improved Algorithm for Learning Drifting Discrete Distributions
Sparse and Faithful Explanations Without Sparse Models
Large-Scale Gaussian Processes via Alternating Projection
Online non-parametric likelihood-ratio estimation by Pearson-divergence functional minimization
An Online Bootstrap for Time Series
LEDetection: A Simple Framework for Semi-Supervised Few-Shot Object Detection
Robust Offline Reinforcement Learning with Heavy-Tailed Rewards
Confident Feature Ranking
Online Learning in Contextual Second-Price Pay-Per-Click Auctions
Multitask Online Learning: Listen to the Neighborhood Buzz
Quantized Fourier and Polynomial Features for more Expressive Tensor Network Models
Towards a Complete Benchmark on Video Moment Localization
Enhancing Distributional Stability among Sub-populations
SADI: Similarity-Aware Diffusion Model-Based Imputation for Incomplete Temporal EHR Data
HintMiner: Automatic Question Hints Mining From Q\&A Web Posts with Language Model via Self-Supervised Learning
DNNLasso: Scalable Graph Learning for Matrix-Variate Data
Solving Attention Kernel Regression Problem via Pre-conditioner
Scalable Higher-Order Tensor Product Spline Models
Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias
Scalable Meta-Learning with Gaussian Processes
Local Causal Discovery with Linear non-Gaussian Cyclic Models
VEC-SBM: Optimal Community Detection with Vectorial Edges Covariates
Gaussian process regression with Sliced Wasserstein Weisfeiler-Lehman graph kernels
Probabilistic Integral Circuits
Efficiently Computable Safety Bounds for Gaussian Processes in Active Learning
On-Demand Federated Learning for Arbitrary Target Class Distributions
Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective
Multiclass Learning from Noisy Labels for Non-decomposable Performance Measures
A Neural Architecture Predictor based on GNN-Enhanced Transformer
Extended Deep Adaptive Input Normalization for Preprocessing Time Series Data for Neural Networks
Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learning
Taming False Positives in Out-of-Distribution Detection with Human Feedback
Monitoring machine learning-based risk prediction algorithms in the presence of performativity
(ends 8:30 AM)
9 a.m.
Affinity Event:
LatinX Social
(ends 11:00 AM)
10 p.m.
Registration
(ends 8:00 AM)
11 p.m.
Mentoring Event (D&I):
tbd
(ends 12:00 AM)

FRI 3 MAY
midnight
Invited Talk:
Conformal online model aggregation
Aaditya Ramdas
(ends 1:00 AM)
1 a.m.
Morning Coffee Break
1:30 a.m.
Oral: Bandit & Causality [1:30-2:30]
Orals -
Positivity-free Policy Learning with Observational Data
Best-of-Both-Worlds Algorithms for Linear Contextual Bandits
Policy Learning for Localized Interventions from Observational Data
Exploration via linearly perturbed loss minimisation
(ends 2:30 AM)
2:30 a.m.
Oral: Causality [2:30-3:30]
Orals -
Membership Testing in Markov Equivalence Classes via Independence Queries
Causal Modeling with Stationary Diffusions
On the Misspecification of Linear Assumptions in Synthetic Controls
General Identifiability and Achievability for Causal Representation Learning
(ends 3:30 AM)
3:30 a.m.
Lunch - retail
Mentoring Event (D&I):
Mentoring Event (D&I)
(ends 5:00 AM)
5 a.m.
Test Of Time:
ToT Award
(ends 6:00 AM)
6 a.m.
Oral: Applications [6:00-6:30]
Equivariant bootstrapping for uncertainty quantification in imaging inverse problems
Mixed Models with Multiple Instance Learning
(ends 6:30 AM)
6:15 a.m.
Afternoon Coffee Break
7 a.m.
Oral: General Machine Learning [7:00-8:00]
Orals -
End-to-end Feature Selection Approach for Learning Skinny Trees
Probabilistic Modeling for Sequences of Sets in Continuous-Time
Learning to Defer to a Population: A Meta-Learning Approach
An Impossibility Theorem for Node Embedding
(ends 8:00 AM)
8 a.m.
Poster Session 2 [8:00-8:30]
Posters 8:00-
Efficient Data Valuation for Weighted Nearest Neighbor Algorithms
Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization
On the Expected Size of Conformal Prediction Sets
User-level Differentially Private Stochastic Convex Optimization: Efficient Algorithms with Optimal Rates
Proximal Causal Inference for Synthetic Control with Surrogates
Integrating Uncertainty Awareness into Conformalized Quantile Regression
Federated Linear Contextual Bandits with Heterogeneous Clients
Fairness in Submodular Maximization over a Matroid Constraint
Training a Tucker Model With Shared Factors: a Riemannian Optimization Approach
Minimax optimal density estimation using a shallow generative model with a one-dimensional latent variable
Adaptive Discretization for Event PredicTion (ADEPT)
Graph Pruning for Enumeration of Minimal Unsatisfiable Subsets
Hidden yet quantifiable: A lower bound for confounding strength using randomized trials
Generalization Bounds of Nonconvex-(Strongly)-Concave Stochastic Minimax Optimization
Sharp error bounds for imbalanced classification: how many examples in the minority class?
Mind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors
Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approach
On Convergence in Wasserstein Distance and f-divergence Minimization Problems
Analysis of Using Sigmoid Loss for Contrastive Learning
Fixed-kinetic Neural Hamiltonian Flows for enhanced interpretability and reduced complexity
Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling
Consistent Optimal Transport with Empirical Conditional Measures
Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers
Maximum entropy GFlowNets with soft Q-learning
Information-theoretic Analysis of Bayesian Test Data Sensitivity
Learning Sampling Policy to Achieve Fewer Queries for Zeroth-Order Optimization
Independent Learning in Constrained Markov Potential Games
End-to-end Feature Selection Approach for Learning Skinny Trees
Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees
Causal Modeling with Stationary Diffusions
Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components
Testing Generated Distributions in GANs to Penalize Mode Collapse
Non-Neighbors Also Matter to Kriging: A New Contrastive-Prototypical Learning
Model-Based Best Arm Identification for Decreasing Bandits
Efficient Low-Dimensional Compression of Overparameterized Models
Robust Non-linear Normalization of Heterogeneous Feature Distributions with Adaptive Tanh-Estimators
An Efficient Stochastic Algorithm for Decentralized Nonconvex-Strongly-Concave Minimax Optimization
Probabilistic Modeling for Sequences of Sets in Continuous-Time
Breaking isometric ties and introducing priors in Gromov-Wasserstein distances
Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization
Distributionally Robust Quickest Change Detection using Wasserstein Uncertainty Sets
Extragradient Type Methods for Riemannian Variational Inequality Problems
Fitting ARMA Time Series Models without Identification: A Proximal Approach
Transductive conformal inference with adaptive scores
AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms
Directional Optimism for Safe Linear Bandits
How Good is a Single Basin?
Length independent PAC-Bayes bounds for Simple RNNs
Efficient Reinforcement Learning for Routing Jobs in Heterogeneous Queueing Systems
Faster Convergence with MultiWay Preferences
Privacy-Preserving Decentralized Actor-Critic for Cooperative Multi-Agent Reinforcement Learning
Simulating weighted automata over sequences and trees with transformers
Exploring the Power of Graph Neural Networks in Solving Linear Optimization Problems
Consistent Hierarchical Classification with A Generalized Metric
Monotone Operator Theory-Inspired Message Passing for Learning Long-Range Interaction on Graphs
Unsupervised Novelty Detection in Pretrained Representation Space with Locally Adapted Likelihood Ratio
Meta Learning in Bandits within shared affine Subspaces
Fixed-Budget Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit
Restricted Isometry Property of Rank-One Measurements with Random Unit-Modulus Vectors
Efficient Quantum Agnostic Improper Learning of Decision Trees
Robust SVD Made Easy: A fast and reliable algorithm for large-scale data analysis
On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers
Equation Discovery with Bayesian Spike-and-Slab Priors and Efficient Kernels
Asymptotic Characterisation of the Performance of Robust Linear Regression in the Presence of Outliers
Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems
Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems
A Scalable Algorithm for Individually Fair k-Means Clustering
Multi-Level Symbolic Regression: Function Structure Learning for Multi-Level Data
Lower-level Duality Based Reformulation and Majorization Minimization Algorithm for Hyperparameter Optimization
Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression
Robust Sparse Voting
A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning
Consistency of Dictionary-Based Manifold Learning
Double InfoGAN for Contrastive Analysis
Bures-Wasserstein Means of Graphs
Compression with Exact Error Distribution for Federated Learning
Adaptive and non-adaptive minimax rates for weighted Laplacian-Eigenmap based nonparametric regression
Nonparametric Automatic Differentiation Variational Inference with Spline Approximation
Unsupervised Change Point Detection in Multivariate Time Series
Fast 1-Wasserstein distance approximations using greedy strategies
Implicit Regularization in Deep Tucker Factorization: Low-Rankness via Structured Sparsity
Dissimilarity Bandits
Improved Sample Complexity Analysis of Natural Policy Gradient Algorithm with General Parameterization for Infinite Horizon Discounted Reward Markov Decision Processes
Continual Domain Adversarial Adaptation via Double-Head Discriminators
Delegating Data Collection in Decentralized Machine Learning
Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses
Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates
On the Generalization Ability of Unsupervised Pretraining
Lexicographic Optimization: Algorithms and Stability
TransFusion: Covariate-Shift Robust Transfer Learning for High-Dimensional Regression
Multi-Resolution Active Learning of Fourier Neural Operators
P-tensors: a General Framework for Higher Order Message Passing in Subgraph Neural Networks
DiffRed: Dimensionality reduction guided by stable rank
Sequence Length Independent Norm-Based Generalization Bounds for Transformers
Mechanics of Next Token Prediction with Self-Attention
Surrogate Active Subspaces for Jump-Discontinuous Functions
A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitrary Opponent
Constant or Logarithmic Regret in Asynchronous Multiplayer Bandits with Limited Communication
Importance Matching Lemma for Lossy Compression with Side Information
Optimising Distributions with Natural Gradient Surrogates
Learning Fair Division from Bandit Feedback
Resilient Constrained Reinforcement Learning
Conformalized Deep Splines for Optimal and Efficient Prediction Sets
Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games
From Coupled Oscillators to Graph Neural Networks: Reducing Over-smoothing via a Kuramoto Model-based Approach
A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization
On The Temporal Domain of Differential Equation Inspired Graph Neural Networks
Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation
Provable Policy Gradient Methods for Average-Reward Markov Potential Games
Positivity-free Policy Learning with Observational Data
Learning Extensive-Form Perfect Equilibria in Two-Player Zero-Sum Sequential Games
Comparing Comparators in Generalization Bounds
Unified Transfer Learning in High-Dimensional Linear Regression
Identifying Copeland Winners in Dueling Bandits with Indifferences
Learning Latent Partial Matchings with Gumbel-IPF Networks
Don't Be Pessimistic Too Early: Look K Steps Ahead!
On the estimation of persistence intensity functions and linear representations of persistence diagrams
Learning Cartesian Product Graphs with Laplacian Constraints
Learning to Defer to a Population: A Meta-Learning Approach
Learning-Based Algorithms for Graph Searching Problems
Online multiple testing with e-values
Learning Dynamics in Linear VAE: Posterior Collapse Threshold, Superfluous Latent Space Pitfalls, and Speedup with KL Annealing
Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation
A 4-Approximation Algorithm for Min Max Correlation Clustering
Risk Seeking Bayesian Optimization under Uncertainty for Obtaining Extremum
Efficient Neural Architecture Design via Capturing Architecture-Performance Joint Distribution
Timing as an Action: Learning When to Observe and Act
Personalized Federated X-armed Bandit
Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity
Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplex
Oracle-Efficient Pessimism: Offline Policy Optimization In Contextual Bandits
Identifiable Feature Learning for Spatial Data with Nonlinear ICA
Model-based Policy Optimization under Approximate Bayesian Inference
DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data
Multi-Domain Causal Representation Learning via Weak Distributional Invariances
A/B testing under Interference with Partial Network Information
Functional Graphical Models: Structure Enables Offline Data-Driven Optimization
A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity
Best-of-Both-Worlds Algorithms for Linear Contextual Bandits
Complexity of Single Loop Algorithms for Nonlinear Programming with Stochastic Objective and Constraints
Optimal Exploration is no harder than Thompson Sampling
Multi-Dimensional Hyena for Spatial Inductive Bias
Mixture-of-Linear-Experts for Long-term Time Series Forecasting
On the Model-Misspecification in Reinforcement Learning
The Solution Path of SLOPE
Causal Discovery under Off-Target Interventions
Adaptive Quasi-Newton and Anderson Acceleration Framework with Explicit Global (Accelerated) Convergence Rates
An Impossibility Theorem for Node Embedding
Optimal Transport for Measures with Noisy Tree Metric
Decentralized Multi-Level Compositional Optimization Algorithms with Level-Independent Convergence Rate
Graph fission and cross-validation
On Ranking-based Tests of Independence
Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games
Multi-resolution Time-Series Transformer for Long-term Forecasting
On the Nystr\"om Approximation for Preconditioning in Kernel Machines
Learning multivariate temporal point processes via the time-change theorem
Free-form Flows: Make Any Architecture a Normalizing Flow
Learning Adaptive Kernels for Statistical Independence Tests
Generalization Bounds for Label Noise Stochastic Gradient Descent
Pure Exploration in Bandits with Linear Constraints
Probabilistic Calibration by Design for Neural Network Regression
Filter, Rank, and Prune: Learning Linear Cyclic Gaussian Graphical Models
Structured Transforms Across Spaces with Cost-Regularized Optimal Transport
Vector Quantile Regression on Manifolds
Supervised Feature Selection via Ensemble Gradient Information from Sparse Neural Networks
Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods
Adaptive Compression in Federated Learning via Side Information
Exploration via linearly perturbed loss minimisation
Robust variance-regularized risk minimization with concomitant scaling
Near Optimal Adversarial Attacks on Stochastic Bandits and Defenses with Smoothed Responses
On learning history-based policies for controlling Markov decision processes
Near-Optimal Convex Simple Bilevel Optimization with a Bisection Method
E(3)-Equivariant Mesh Neural Networks
Low-rank MDPs with Continuous Action Spaces
Online Learning of Decision Trees with Thompson Sampling
Submodular Minimax Optimization: Finding Effective Sets
Multi-armed bandits with guaranteed revenue per arm
Offline Primal-Dual Reinforcement Learning for Linear MDPs
A Specialized Semismooth Newton Method for Kernel-Based Optimal Transport
Ordinal Potential-based Player Rating
Understanding Progressive Training Through the Framework of Randomized Coordinate Descent
Graph Partitioning with a Move Budget
A Unified Framework for Discovering Discrete Symmetries
A General Theoretical Paradigm to Understand Learning from Human Preferences
Central Limit Theorem for Two-Timescale Stochastic Approximation with Markovian Noise: Theory and Applications
(ends 8:30 AM)
10 p.m.
Registration
(ends 8:00 AM)
11 p.m.
Mentoring Event (D&I):
tbd
(ends 12:00 AM)

SAT 4 MAY
midnight
Invited Talk:
Learning with symmetries: eigenvectors, graph representations and sample complexity
Stefanie Jegelka
(ends 1:00 AM)
1 a.m.
Morning Coffee Break
1:30 a.m.
Oral: Deep Learning [1:30-2:30]
Orals -
Mind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors
Functional Flow Matching
Deep Classifier Mimicry without Data Access
Multi-Resolution Active Learning of Fourier Neural Operators
(ends 2:30 AM)
2:30 a.m.
Oral: Statistics [2:30-3:30]
Orals -
Transductive conformal inference with adaptive scores
Approximate Leave-one-out Cross Validation for Regression with $\ell_1$ Regularizers
Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent
Testing exchangeability by pairwise betting
(ends 3:30 AM)
3:30 a.m.
Lunch - retail
Mentoring Event (D&I):
Mentoring
(ends 5:00 AM)
5 a.m.
Oral: Trustworthy ML [5:00-6:00]
Orals -
Efficient Data Shapley for Weighted Nearest Neighbor Algorithms
On Counterfactual Metrics for Social Welfare: Incentives, Ranking, and Information Asymmetry
Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data
Is this model reliable for everyone? Testing for strong calibration
(ends 6:00 AM)
6 a.m.
Poster Session 3 [6:00-8:30]
Posters -
Pessimistic Off-Policy Multi-Objective Optimization
Understanding Inverse Scaling and Emergence in Multitask Representation Learning
BLIS-Net: Classifying and Analyzing Signals on Graphs
Score Operator Newton transport
The Galerkin method beats Graph-Based Approaches for Spectral Algorithms
Benefits of Non-Linear Scale Parameterizations in Black Box Variational Inference through Smoothness Results and Gradient Variance Bounds
Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks
Sample-efficient neural likelihood-free Bayesian inference of implicit HMMs
How does GPT-2 Predict Acronyms? Extracting and Understanding a Circuit via Mechanistic Interpretability
Identification and Estimation of ``Causes of Effects'' using Covariate-Mediator Information
Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources
Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate
Approximate Bayesian Class-Conditional Models under Continuous Representation Shift
Membership Testing in Markov Equivalence Classes via Independence Queries
Asynchronous Randomized Trace Estimation
NoisyMix: Boosting Model Robustness to Common Corruptions
Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective
Conformalized Semi-supervised Random Forest for Classification and Abnormality Detection
Towards Practical Non-Adversarial Distribution Matching
Posterior Uncertainty Quantification in Neural Networks using Data Augmentation
Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methods
Inconsistency of Cross-Validation for Structure Learning in Gaussian Graphical Models
Data Driven Threshold and Potential Initialization for Spiking Neural Networks
Boundary-Aware Uncertainty for Feature Attribution Explainers
Random Oscillators Network for Time Series Processing
Cylindrical Thompson Sampling for High-Dimensional Bayesian Optimization
No-Regret Algorithms for Safe Bayesian Optimization with Monotonicity Constraints
Non-vacuous Generalization Bounds for Adversarial Risk in Stochastic Neural Networks
On Parameter Estimation in Deviated Gaussian Mixture of Experts
Discriminator Guidance for Autoregressive Diffusion Models
Learning Unknown Intervention Targets in Structural Causal Models from Heterogeneous Data
Functional Flow Matching
The Relative Gaussian Mechanism and its Application to Private Gradient Descent
Private Learning with Public Features
Computing epidemic metrics with edge differential privacy
Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
Towards Costless Model Selection in Contextual Bandits: A Bias-Variance Perspective
Federated Experiment Design under Distributed Differential Privacy
Sequential learning of the Pareto front for multi-objective bandits
Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias
Causally Inspired Regularization Enables Domain General Representations
Learning Under Random Distributional Shifts
Sharpened Lazy Incremental Quasi-Newton Method
Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformers
Variational Resampling
Fast Minimization of Expected Logarithmic Loss via Stochastic Dual Averaging
Non-Convex Joint Community Detection and Group Synchronization via Generalized Power Method
Stochastic Frank-Wolfe: Unified Analysis and Zoo of Special Cases
Stochastic Multi-Armed Bandits with Strongly Reward-Dependent Delays
Proving Linear Mode Connectivity of Neural Networks via Optimal Transport
Think Global, Adapt Local: Learning Locally Adaptive K-Nearest Neighbor Kernel Density Estimators
A Greedy Approximation for k-Determinantal Point Processes
Equivalence Testing: The Power of Bounded Adaptivity
XB-MAML: Learning Expandable Basis Parameters for Effective Meta-Learning with Wide Task Coverage
Invariant Aggregator for Defending against Federated Backdoor Attacks
THE SAMPLE COMPLEXITY OF ERM IN EUCLIDEAN STOCHASTIC CONVEX OPTIMIZATION
On Feynman–Kac training of partial Bayesian neural networks
Learning to Solve the Constrained Most Probable Explanation Task in Probabilistic Graphical Models
SDEs for Minimax Optimization
SDMTR: A Brain-inspired Transformer for Relation Inference
Deep Classifier Mimicry without Data Access
Stochastic Extragradient with Random Reshuffling: Improved Convergence for Variational Inequalities
Data-Driven Confidence Intervals with Optimal Rates for the Mean of Heavy-Tailed Distributions
Why is parameter averaging beneficial in SGD? An objective smoothing perspective
Parameter-Agnostic Optimization under Relaxed Smoothness
Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts
Stochastic Methods in Variational Inequalities: Ergodicity, Bias and Refinements
Fast Fourier Bayesian Quadrature
Gibbs-Based Information Criteria and the Over-Parameterized Regime
FairRR: Pre-Processing for Group Fairness through Randomized Response
Interpretable Causal Inference for Analyzing Wearable, Sensor, and Distributional Data
Acceleration and Implicit Regularization in Gaussian Phase Retrieval
Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training
Learning the Pareto Set Under Incomplete Preferences: Pure Exploration in Vector Bandits
On the Impact of Overparameterization on the Training of a Shallow Neural Network in High Dimensions
Communication-Efficient Federated Learning With Data and Client Heterogeneity
Approximate Leave-one-out Cross Validation for Regression with l1 Regularizers
Faithful graphical representations of local independence
EM for Mixture of Linear Regression with Clustered Data
Bandit Pareto Set Identification: the Fixed Budget Setting
Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process
On the Effect of Key Factors in Spurious Correlation: A theoretical Perspective
Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation
Efficient Conformal Prediction under Data Heterogeneity
Minimax Excess Risk of First-Order Methods for Statistical Learning with Data-Dependent Oracles
Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures
Stochastic Smoothed Gradient Descent Ascent for Federated Minimax Optimization
Strategic Usage in a Multi-Learner Setting
On the Misspecification of Linear Assumptions in Synthetic Controls
SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits
Informative Path Planning with Limited Adaptivity
Efficient Variational Sequential Information Control
Trigonometric Quadrature Fourier Features for Scalable Gaussian Process Regression
Tight Verification of Probabilistic Robustness in Bayesian Neural Networks
Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence
Electronic Medical Records Assisted Digital Clinical Trial Design
Generative Flow Networks as Entropy-Regularized RL
Adaptive Federated Minimax Optimization with Lower Complexities
DE-HNN: An effective neural model for Circuit Netlist representation
Differentially Private Reward Estimation with Preference Feedback
Hodge-Compositional Edge Gaussian Processes
Causal Q-Aggregation for CATE Model Selection
Optimal Budgeted Rejection Sampling for Generative Models
SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization
Provable Mutual Benefits from Federated Learning in Privacy-Sensitive Domains
General Tail Bounds for Non-Smooth Stochastic Mirror Descent
autoMALA: Locally adaptive Metropolis-adjusted Langevin algorithm
Soft-constrained Schr\"odinger Bridge: a Stochastic Control Approach
Pathwise Explanation of ReLU Neural Networks
Reward-Relevance-Filtered Linear Offline Reinforcement Learning
Revisiting the Noise Model of Stochastic Gradient Descent
Differentially Private Conditional Independence Testing
Warped Diffusion for Latent Differentiation Inference
Mitigating Underfitting in Learning to Defer with Consistent Losses
Achieving Group Distributional Robustness and Minimax Group Fairness with Interpolating Classifiers
Preventing Arbitrarily High Confidence on Far-Away Data in Point-Estimated Discriminative Neural Networks
Policy Evaluation for Reinforcement Learning from Human Feedback: A Sample Complexity Analysis
Bounding Box-based Multi-objective Bayesian Optimization of Risk Measures under Input Uncertainty
Coreset Markov chain Monte Carlo
Online learning in bandits with predicted context
Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo
Identifiability of Product of Experts Models
Spectrum Extraction and Clipping for Implicitly Linear Layers
An Analytic Solution to Covariance Propagation in Neural Networks
Understanding the Generalization Benefits of Late Learning Rate Decay
Any-dimensional equivariant neural networks
FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning
On cyclical MCMC sampling
Adaptive importance sampling for heavy-tailed distributions via $\alpha$-divergence minimization
Learning Policies for Localized Interventions from Observational Data
On the Vulnerability of Fairness Constrained Learning to Malicious Noise
The effect of Leaky ReLUs on the training and generalization of overparameterized networks
Approximate Control for Continuous-Time POMDPs
Quantifying intrinsic causal contributions via structure preserving interventions
Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion
Conditions on Preference Relations that Guarantee the Existence of Optimal Policies
Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent in High-Dimensional Least Squares
Formal Verification of Unknown Stochastic Systems via Non-parametric Estimation
LP-based Construction of DC Decompositions for Efficient Inference of Markov Random Fields
First Passage Percolation with Queried Hints
Optimal estimation of Gaussian (poly)trees
Conditional Adjustment in a Markov Equivalence Class
Anytime-Constrained Reinforcement Learning
On the price of exact truthfulness in incentive-compatible online learning with bandit feedback: a regret lower bound for WSU-UX
Multi-Agent Learning in Contextual Games under Unknown Constraints
Causal Bandits with General Causal Models and Interventions
To Pool or Not To Pool: Analyzing the Regularizing Effects of Group-Fair Training on Shared Models
Identifying Confounding from Causal Mechanism Shifts
Contextual Directed Acyclic Graphs
Near-Optimal Pure Exploration in Matrix Games: A Generalization of Stochastic Bandits \& Dueling Bandits
Consistent and Asymptotically Unbiased Estimation of Proper Calibration Errors
Multi-Agent Bandit Learning through Heterogeneous Action Erasure Channels
Differentiable Rendering with Reparameterized Volume Sampling
The AL$\ell_0$CORE Tensor Decomposition for Sparse Count Data
Sinkhorn Flow as Mirror Flow: A Continuous-Time Framework for Generalizing the Sinkhorn Algorithm
Multivariate Time Series Forecasting By Graph Attention Networks With Theoretical Guarantees
Tensor-view Topological Graph Neural Network
Benchmarking Observational Studies with Experimental Data under Right-Censoring
General Identifiability and Achievability for Causal Representation Learning
Faster Recalibration of an Online Predictor via Approachability
Proxy Methods for Domain Adaptation
Simulation-Based Stacking
Sum-max Submodular Bandits
Fast and Accurate Estimation of Low-Rank Matrices from Noisy Measurements via Preconditioned Non-Convex Gradient Descent
Weight-Sharing Regularization
Multi-objective Optimization via Wasserstein-Fisher-Rao Gradient Flow
On the connection between Noise-Contrastive Estimation and Contrastive Divergence
Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification
Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention
Testing exchangeability by pairwise betting
SVARM-IQ: Efficient Approximation of Any-order Shapley Interactions through Stratification
Fair Machine Unlearning: Data Removal while Mitigating Disparities
Density-Regression: Efficient and Distance-aware Deep Regressor for Uncertainty Estimation under Distribution Shifts
Can Probabilistic Feedback Drive User Impacts in Online Platforms?
Pr{I}sing: Privacy-Preserving Peer Effect Estimation via {I}sing Model
Self-Compatibility: Evaluating Causal Discovery without Ground Truth
Symmetric Equilibrium Learning of VAEs
Near-optimal Per-Action Regret Bounds for Sleeping Bandits
Sequential Monte Carlo for Inclusive KL Minimization in Amortized Variational Inference
(ends 8:30 AM)