Skip to yearly menu bar Skip to main content


Show Detail
Schedule Tue Wed Thu
Timezone: CET
 
Filter Rooms:  

 

TUE 25 APR
7 a.m.
Registration + Assistance
(ends 5:00 PM)
8:45 a.m.
Opening Remarks:
Opening Remarks
(ends 9:00 AM)
9 a.m.
Invited Talk:
Causal Effect Estimation with Context and Confounders
Arthur Gretton
(ends 10:00 AM)
10 a.m.
Coffee Break
10:30 a.m.
Optimal Transport, Information Theory [10:30-11:30]
Orals 10:30-11:30
[10:30] The Schrödinger Bridge between Gaussian Measures has a Closed Form
[10:45] Rethinking Initialization of the Sinkhorn Algorithm
[11:00] Using Sliced Mutual Information to Study Memorization and Generalization in Deep Neural Networks
[11:15] Mode-Seeking Divergences: Theory and Applications to GANs
(ends 11:30 AM)
11:30 a.m.
Affinity Panel:
Carving out a niche as a researcher
(ends 12:30 PM)
12:30 p.m.
Lunch Break
2 p.m.
Trustworthy ML and Statistics [2:00-3:00]
Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy
Origins of Low-Dimensional Adversarial Perturbations
Data Banzhaf: A Robust Data Valuation Framework for Machine Learning
(ends 3:00 PM)
3 p.m.
Coffee Break
3:30 p.m.
Representations of Graphs [3:30-4:30]
Orals 3:30-4:30
[3:30] The Power of Recursion in Graph Neural Networks for Counting Substructures
[3:45] Implicit Graphon Neural Representation
[4:00] Implications of sparsity and high triangle density for graph representation learning
[4:15] Fitting low-rank models on egocentrically sampled partial networks
(ends 4:30 PM)
4:30 p.m.
Poster Session 1 [4:30-7:00]
Posters 4:30-7:00
CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision
BlitzMask: Real-Time Instance Segmentation Approach for Mobile Devices
Finding Regularized Competitive Equilibria of Heterogeneous Agent Macroeconomic Models via Reinforcement Learning
Continuous-Time Decision Transformer for Healthcare Applications
Who Should Predict? Exact Algorithms For Learning to Defer to Humans
Learning from Multiple Sources for Data-to-Text and Text-to-Data
Graph Spectral Embedding using the Geodesic Betweenness Centrality
Implications of sparsity and high triangle density for graph representation learning
Fitting low-rank models on egocentrically sampled partial networks
Reinforcement Learning for Adaptive Mesh Refinement
Autoencoded sparse Bayesian in-IRT factorization, calibration, and amortized inference for the Work Disability Functional Assessment Battery
Loss-Curvature Matching for Dataset Selection and Condensation
Covariate-informed Representation Learning to Prevent Posterior Collapse of iVAE
Deep Joint Source-Channel Coding with Iterative Source Error Correction
Conjugate Gradient Method for Generative Adversarial Networks
The ELBO of Variational Autoencoders Converges to a Sum of Entropies
Barlow Graph Auto-Encoder for Unsupervised Network Embedding
Probing Graph Representations
EGG-GAE: scalable graph neural networks for tabular data imputation
The Power of Recursion in Graph Neural Networks for Counting Substructures
Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data
Linear Convergence of Gradient Descent For Overparametrized Finite Width Two-Layer Linear Networks With General Initialization
Mind the (optimality) Gap: A Gap-Aware Learning Rate Scheduler for Adversarial Nets
A Mini-Block Fisher Method for Deep Neural Networks
Rethinking Initialization of the Sinkhorn Algorithm
Adversarial De-confounding in Individualised Treatment Effects Estimation
Using Sliced Mutual Information to Study Memorization and Generalization in Deep Neural Networks
Analysis of Catastrophic Forgetting for Random Orthogonal Transformation Tasks in the Overparameterized Regime
Singular Value Representation: A New Graph Perspective On Neural Networks
Deep equilibrium models as estimators for continuous latent variables
Reconstructing Training Data from Model Gradient, Provably
Active Cost-aware Labeling of Streaming Data
Nonparametric Indirect Active Learning
Improved Robust Algorithms for Learning with Discriminative Feature Feedback
Smoothly Giving up: Robustness for Simple Models
Fast Computation of Branching Process Transition Probabilities via ADMM
Spread Flows for Manifold Modelling
Ultra-marginal Feature Importance: Learning from Data with Causal Guarantees
Model-X Sequential Testing for Conditional Independence via Testing by Betting
Complex-to-Real Sketches for Tensor Products with Applications to the Polynomial Kernel
MMD-B-Fair: Learning Fair Representations with Statistical Testing
Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneity
Catalyst Acceleration of Error Compensated Methods Leads to Better Communication Complexity
Scalable Unbalanced Sobolev Transport for Measures on a Graph
Positional Encoder Graph Neural Networks for Geographic Data
Implicit Graphon Neural Representation
Symmetric (Optimistic) Natural Policy Gradient for Multi-Agent Learning with Parameter Convergence
Simulator-Based Inference with WALDO: Confidence Regions by Leveraging Prediction Algorithms and Posterior Estimators for Inverse Problems
Revisiting Weighted Strategy for Non-stationary Parametric Bandits
Overcoming Prior Misspecification in Online Learning to Rank
Optimal robustness-consistency tradeoffs for learning-augmented metrical task systems
Iterative Teaching by Data Hallucination
Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning
Near-Optimal Differentially Private Reinforcement Learning
Mode-constrained Model-based Reinforcement Learning via Gaussian Processes
Provably Efficient Reinforcement Learning via Surprise Bound
A Tighter Problem-Dependent Regret Bound for Risk-Sensitive Reinforcement Learning
Model-Based Uncertainty in Value Functions
Neural Laplace Control for Continuous-time Delayed Systems
Entropic Risk Optimization in Discounted MDPs
A Statistical Analysis of Polyak-Ruppert-Averaged Q-Learning
On the Complexity of Representation Learning in Contextual Linear Bandits
Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learning
TS-UCB: Improving on Thompson Sampling With Little to No Additional Computation
Consistent Complementary-Label Learning via Order-Preserving Losses
Regression as Classification: Influence of Task Formulation on Neural Network Features
Mediated Uncoupled Learning and Validation with Bregman Divergences: Loss Family with Maximal Generality
Theory and Algorithm for Batch Distribution Drift Problems
NTS-NOTEARS: Learning Nonparametric DBNs With Prior Knowledge
Coherent Probabilistic Forecasting of Temporal Hierarchies
A Novel Stochastic Gradient Descent Algorithm for Learning Principal Subspaces
Clustering above Exponential Families with Tempered Exponential Measures
Clustering High-dimensional Data with Ordered Weighted L1 Regularization
Large deviations rates for stochastic gradient descent with strongly convex functions
Root Cause Identification for Collective Anomalies in Time Series given an Acyclic Summary Causal Graph with Loops
Combining Graphical and Algebraic Approaches for Parameter Identification in Latent Variable Structural Equation Models
Learning Treatment Effects from Observational and Experimental Data
Context-Specific Causal Discovery for Categorical Data Using Staged Trees
Understanding the Impact of Competing Events on Heterogeneous Treatment Effect Estimation from Time-to-Event Data
PAC Learning of Halfspaces with Malicious Noise in Nearly Linear Time
Breaking a Classical Barrier for Classifying Arbitrary Test Examples in the Quantum Model
Exploration in Reward Machines with Low Regret
Randomized Greedy Learning for Non-monotone Stochastic Submodular Maximization Under Full-bandit Feedback
Learning While Scheduling in Multi-Server Systems With Unknown Statistics: MaxWeight with Discounted UCB
Vector Optimization with Stochastic Bandit Feedback
Risk-aware linear bandits with convex loss
Nonstationary Bandit Learning via Predictive Sampling
Adaptation to Misspecified Kernel Regularity in Kernelised Bandits
Optimal Algorithms for Latent Bandits with Cluster Structure
Further Adaptive Best-of-Both-Worlds Algorithm for Combinatorial Semi-Bandits
Learning to Optimize for Stochastic Dominance Constraints
Incentive-aware Contextual Pricing with Non-parametric Market Noise
On the Limitations of the Elo, Real-World Games are Transitive, not Additive
Matching Map Recovery with an Unknown Number of Outliers
Online Linearized LASSO
Average Adjusted Association: Efficient Estimation with High Dimensional Confounders
Dropout-Resilient Secure Multi-Party Collaborative Learning with Linear Communication Complexity
Mode-Seeking Divergences: Theory and Applications to GANs
Adaptive Tuning for Metropolis Adjusted Langevin Trajectories
Regularization for Shuffled Data Problems via Exponential Family Priors on the Permutation Group
Improved Bound on Generalization Error of Compressed KNN Estimator
The Schrödinger Bridge between Gaussian Measures has a Closed Form
Pointwise sampling uncertainties on the Precision-Recall curve
Is interpolation benign for random forest regression?
Statistical Analysis of Karcher Means for Random Restricted PSD Matrices
Instance-dependent Sample Complexity Bounds for Zero-sum Matrix Games
A Case of Exponential Convergence Rates for SVM
Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws
Wasserstein Distributional Learning via Majorization-Minimization
Fast Feature Selection with Fairness Constraints
Select and Optimize Learning to Solve Large-Scale Traveling Salesman Problem
An Online and Unified Algorithm for Projection Matrix Vector Multiplication with Application to Empirical Risk Minimization
A principled framework for the design and analysis of token algorithms
A Variance-Reduced and Stabilized Proximal Stochastic Gradient Method with Support Identification Guarantees for Structured Optimization
Can 5th Generation Local Training Methods Support Client Sampling? Yes!
Reducing Discretization Error in the Frank-Wolfe Method
Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Data
Distributed Offline Policy Optimization Over Batch Data
Sequential Gradient Descent and Quasi-Newton's Method for Change-Point Analysis
HeteRSGD: Tackling Heterogeneous Sampling Costs via Optimal Reweighted Stochastic Gradient Descent
High Probability Bounds for Stochastic Continuous Submodular Maximization
Riemannian Accelerated Gradient Methods via Extrapolation
Bures-Wasserstein Barycenters and Low-Rank Matrix Recovery
A Targeted Accuracy Diagnostic for Variational Approximations
Incorporating functional summary information in Bayesian neural networks using a Dirichlet process likelihood approach
Preferential Subsampling for Stochastic Gradient Langevin Dynamics
Variational Inference for Neyman-Scott Processes
Bounding Evidence and Estimating Log-Likelihood in VAE
qEUBO: A Decision-Theoretic Acquisition Function for Preferential Bayesian Optimization
Stochastic Tree Ensembles for Estimating Heterogeneous Effects
Bayesian Structure Scores for Probabilistic Circuits
Scalable Bayesian Optimization Using Vecchia Approximations of Gaussian Processes
Sparse Bayesian optimization
Causal Entropy Optimization
Hierarchical-Hyperplane Kernels for Actively Learning Gaussian Process Models of Nonstationary Systems
Unsupervised representation learning with recognition-parametrised probabilistic models
Mixtures of All Trees
Energy-Based Models for Functional Data using Path Measure Tilting
No time to waste: practical statistical contact tracing with few low-bit messages
Estimating Total Correlation with Mutual Information Estimators
Randomized geometric tools for anomaly detection in stock markets
Efficient Informed Proposals for Discrete Distributions via Newton’s Series Approximation
Probabilistic Querying of Continuous-Time Event Sequences
Minority Oversampling for Imbalanced Data via Class-Preserving Regularized Auto-Encoders
Deep Grey-Box Models With Adaptive Data-Driven Models Toward Trustworthy Estimation of Theory-Driven Models
Unifying local and global model explanations by functional decomposition of low dimensional structures
Feasible Recourse Plan via Diverse Interpolation
Computing Abductive Explanations for Boosted Trees
Data Banzhaf: A Robust Data Valuation Framework for Machine Learning
Mean Parity Fair Regression in RKHS
Revisiting Fair-PAC Learning and the Axioms of Cardinal Welfare
Efficient fair PCA for fair representation learning
Membership Inference Attacks against Synthetic Data through Overfitting Detection
Noise-Aware Statistical Inference with Differentially Private Synthetic Data
Does Label Differential Privacy Prevent Label Inference Attacks?
Protecting Global Properties of Datasets with Distribution Privacy Mechanisms
Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy
Byzantine-Robust Federated Learning with Optimal Statistical Rates
Gradient-Informed Neural Network Statistical Robustness Estimation
Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles
Distributionally Robust Policy Gradient for Offline Contextual Bandits
Robust Variational Autoencoding with Wasserstein Penalty for Novelty Detection
Global-Local Regularization Via Distributional Robustness
Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games
Origins of Low-Dimensional Adversarial Perturbations
Retrospective Uncertainties for Deep Models using Vine Copulas
Hedging against Complexity: Distributionally Robust Optimization with Parametric Approximation
(ends 7:00 PM)
6 p.m.
Affinity Event:
LatinX in AI Social
(ends 8:00 PM)
WED 26 APR
7 a.m.
Registration + Assistance
(ends 5:00 PM)
9 a.m.
Invited Talk:
Elevating our Evaluations: Technical and Sociotechnical Standards of Assessment in Machine Learning
Shakir Mohamed
(ends 10:00 AM)
10 a.m.
Coffee Break
10:30 a.m.
Probabilistic Methods 1 [10:30-11:30]
Orals 10:30-11:30
[10:30] Do Bayesian Neural Networks Need To Be Fully Stochastic?
[10:45] Indeterminacy in Generative Models: Characterization and Strong Identifiability
[11:00] Distance-to-Set Priors and Constrained Bayesian Inference
[11:15] Particle algorithms for maximum likelihood training of latent variable models
(ends 11:30 AM)
11:30 a.m.
Probabilistic Methods 2 [11:30-12:30]
Orals 11:30-12:30
[11:30] BaCaDI: Bayesian Causal Discovery with Unknown Interventions
[11:45] Multilevel Bayesian Quadrature
[12:00] Discovering Many Diverse Solutions with Bayesian Optimization
[12:15] Inducing Point Allocation for Sparse Gaussian Processes in High-Throughput Bayesian Optimisation
(ends 12:30 PM)
12:30 p.m.
Lunch Break
2 p.m.
Test Of Time Award:
Deep Gaussian Processes
(ends 3:00 PM)
3 p.m.
Coffee Break
3:30 p.m.
Statistical Methods 1 [3:30-4:30]
Orals 3:30-4:30
[3:30] Huber-robust confidence sequences
[3:45] Error Estimation for Random Fourier Features
[4:00] A Tale of Sampling and Estimation in Discounted Reinforcement Learning
[4:15] Safe Sequential Testing and Effect Estimation in Stratified Count Data
(ends 4:30 PM)
4:30 p.m.
Poster Session 2 [4:30-7:00]
Posters 4:30-7:00
Bayesian Hierarchical Models for Counterfactual Estimation
USIM Gate: Novel Attention-based UpSampling Interpolation Method for Segmenting Precise Boundaries of Target Objects
Balanced Off-Policy Evaluation for Personalized Pricing
Knowledge Acquisition for Human-In-The-Loop Image Captioning
Classification of Adolescents' Risky Behavior in Instant Messaging Conversations
Surveillance Evasion Through Bayesian Reinforcement Learning
Learning Physics-Informed Neural Networks without Stacked Back-propagation
Weather2K: A Multivariate Spatio-Temporal Benchmark Dataset for Meteorological Forecasting Based on Real-Time Observation Data from Ground Weather Stations
Learning with Partial Forgetting in Modern Hopfield Networks
Improved Representation Learning Through Tensorized Autoencoders
Diffusion Generative Models in Infinite Dimensions
Precision Recall Cover: A Method For Assessing Generative Models
Generative Oversampling for Imbalanced Data via Majority-Guided VAE
Temporal Graph Neural Networks for Irregular Data
Weisfeiler and Leman go Hyperbolic: Learning Distance Preserving Node Representations
Learning Robust Graph Neural Networks with Limited Supervision
Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation
Deep Neural Networks with Efficient Guaranteed Invariances
Performative Prediction with Neural Networks
Faithful Heteroscedastic Regression with Neural Networks
Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneck
On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data
Overparameterized Random Feature Regression with Nearly Orthogonal Data
Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion
Global Convergence of Over-parameterized Deep Equilibrium Models
FAIR: Fair Collaborative Active Learning with Individual Rationality for Scientific Discovery
Prediction-Oriented Bayesian Active Learning
Active Learning for Single Neuron Models with Lipschitz Non-Linearities
Boosted Off-Policy Learning
Average case analysis of Lasso under ultra sparse conditions
The Role of Codeword-to-Class Assignments in Error Correcting Codes: An Empirical Study
A Unified Perspective on Regularization and Perturbation in Differentiable Subset Selection
DIET: Conditional independence testing with marginal dependence measures of residual information
Learning in RKHM: a C*-algebraic twist for kernel machines
Tensor-based Kernel Machines with Structured Inducing Points for Large and High-Dimensional Data
Error Estimation for Random Fourier Features
Federated Learning for Data Streams
Private Non-Convex Federated Learning Without a Trusted Server
Characterizing Polarization in Social Networks using the Signed Relational Latent Distance Model
Collision Probability Matching Loss for Disentangling Epistemic Uncertainty from Aleatoric Uncertainty
Learning Sparse Graphon Mean Field Games
No-Regret Learning in Two-Echelon Supply Chain with Unknown Demand Distribution
Second Order Path Variationals in Non-Stationary Online Learning
Online Learning for Traffic Routing under Unknown Preferences
Robust Linear Regression for General Feature Distribution
Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervision
Coarse-Grained Smoothness for Reinforcement Learning in Metric Spaces
Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables
Algorithm for Constrained Markov Decision Process with Linear Convergence
Byzantine-Robust Online and Offline Distributed Reinforcement Learning
Krylov--Bellman boosting: Super-linear policy evaluation in general state spaces
Provable Safe Reinforcement Learning with Binary Feedback
Representation Learning in Deep RL via Discrete Information Bottleneck
Universal Agent Mixtures and the Geometry of Intelligence
A Finite Sample Complexity Bound for Distributionally Robust Q-learning
One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learning
Uniformly Conservative Exploration in Reinforcement Learning
Nearly Optimal Latent State Decoding in Block MDPs
A Tale of Sampling and Estimation in Discounted Reinforcement Learning
Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification
Density Ratio Estimation and Neyman Pearson Classification with Missing Data
Data Augmentation for Imbalanced Regression
Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining
Dimensionality Collapse: Optimal Measurement Selection for Low-Error Infinite-Horizon Forecasting
Scalable marked point processes for exchangeable and non-exchangeable event sequences
SwAMP: Swapped Assignment of Multi-Modal Pairs for Cross-Modal Retrieval
Fast Distributed k-Means with a Small Number of Rounds
Structure of Nonlinear Node Embeddings in Stochastic Block Models
To Impute or not to Impute? Missing Data in Treatment Effect Estimation
Estimating Conditional Average Treatment Effects with Missing Treatment Information
Nothing but Regrets --- Privacy-Preserving Federated Causal Discovery
Probabilities of Causation: Role of Observational Data
Falsification of Internal and External Validity in Observational Studies via Conditional Moment Restrictions
Subset verification and search algorithms for causal DAGs
BaCaDI: Bayesian Causal Discovery with Unknown Interventions
Agnostic PAC Learning of k-Juntas Using L2-Polynomial Regression
Flexible and Efficient Contextual Bandits with Heterogeneous Treatment Effect Oracles
ANACONDA: An Improved Dynamic Regret Algorithm for Adaptive Non-Stationary Dueling Bandits
Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference
Squeeze All: Novel Estimator and Self-Normalized Bound for Linear Contextual Bandits
On-Demand Communication for Asynchronous Multi-Agent Bandits
Tight Regret and Complexity Bounds for Thompson Sampling via Langevin Monte Carlo
An Optimization-based Algorithm for Non-stationary Kernel Bandits without Prior Knowledge
Delayed Feedback in Generalised Linear Bandits Revisited
Mixed-Effect Thompson Sampling
Optimal Contextual Bandits with Knapsacks under Realizability via Regression Oracles
Provable Hierarchy-Based Meta-Reinforcement Learning
Minimax Nonparametric Two-Sample Test under Adversarial Losses
Last-Iterate Convergence with Full and Noisy Feedback in Two-Player Zero-Sum Games
Bayesian Strategy-Proof Facility Location via Robust Estimation
Mixed Linear Regression via Approximate Message Passing
Asymptotic Bayes risk of semi-supervised multitask learning on Gaussian mixture
Federated Asymptotics: a model to compare federated learning algorithms
How Does Pseudo-Labeling Affect the Generalization Error of the Semi-Supervised Gibbs Algorithm?
Frequentist Uncertainty Quantification in Semi-Structured Neural Networks
Fair learning with Wasserstein barycenters for non-decomposable performance measures
Unified Perspective on Probability Divergence via the Density-Ratio Likelihood: Bridging KL-Divergence and Integral Probability Metrics
Huber-robust confidence sequences
A Contrastive Approach to Online Change Point Detection
A Statistical Learning Take on the Concordance Index for Survival Analysis
Sample Efficiency of Data Augmentation Consistency Regularization
Risk Bounds on Aleatoric Uncertainty Recovery
On the bias of K-fold cross validation with stable learners
Theoretically Grounded Loss Functions and Algorithms for Adversarial Robustness
Learning Constrained Structured Spaces with Application to Multi-Graph Matching
Approximating a RUM from Distributions on $k$-Slates
On Generalization of Decentralized Learning with Separable Data
Stochastic Optimization for Spectral Risk Measures
An Homogeneous Unbalanced Regularized Optimal Transport Model with Applications to Optimal Transport with Boundary
Faster Projection-Free Augmented Lagrangian Methods via Weak Proximal Oracle
Deep Value Function Networks for Large-Scale Multistage Stochastic Programming Problems
Online Algorithms with Costly Predictions
Nystrom Method for Accurate and Scalable Implicit Differentiation
Improved Rate of First Order Algorithms for Entropic Optimal Transport
Exact Gradient Computation for Spiking Neural Networks via Forward Propagation
A Bregman Divergence View on the Difference-of-Convex Algorithm
Resolving the Approximability of Offline and Online Non-monotone DR-Submodular Maximization over General Convex Sets
AdaGDA: Faster Adaptive Gradient Descent Ascent Methods for Minimax Optimization
\{PF\}$^2$ES: Parallel Feasible Pareto Frontier Entropy Search for Multi-Objective Bayesian Optimization
Bayesian Variable Selection in a Million Dimensions
Transport Elliptical Slice Sampling
The Lie-Group Bayesian Learning Rule
Langevin Diffusion Variational Inference
Particle algorithms for maximum likelihood training of latent variable models
Meta-Uncertainty in Bayesian Model Comparison
Bayesian Optimization Over Iterative Learners with Structured Responses: A Budget-aware Planning Approach
Do Bayesian Neural Networks Need To Be Fully Stochastic?
Distance-to-Set Priors and Constrained Bayesian Inference
EEGNN: Edge Enhanced Graph Neural Network with a Bayesian Nonparametric Graph Model
Compositional Probabilistic and Causal Inference using Tractable Circuit Models
Isotropic Gaussian Processes on Finite Spaces of Graphs
Factorial SDE for Multi-Output Gaussian Process Regression
A Multi-Task Gaussian Process Model for Inferring Time-Varying Treatment Effects in Panel Data
Nonparametric Gaussian Process Covariances via Multidimensional Convolutions
Multilevel Bayesian Quadrature
Discovering Many Diverse Solutions with Bayesian Optimization
Inducing Point Allocation for Sparse Gaussian Processes in High-Throughput Bayesian Optimisation
Bayesian Convolutional Deep Sets with Task-Dependent Stationary Prior
ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images
Connectivity-contrastive learning: Combining causal discovery and representation learning for multimodal data
Indeterminacy in Generative Models: Characterization and Strong Identifiability
The Lauritzen-Chen Likelihood For Graphical Models
Probabilistic Conformal Prediction Using Conditional Random Samples
Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition
Transport Reversible Jump Proposals
Testing of Horn Samplers
Optimal and Private Learning from Human Response Data
Safe Sequential Testing and Effect Estimation in Stratified Count Data
A Sea of Words: An In-Depth Analysis of Anchors for Text Data
But Are You Sure? An Uncertainty-Aware Perspective on Explainable AI
Efficient SAGE Estimation via Causal Structure Learning
From Shapley Values to Generalized Additive Models and back
Reinforcement Learning with Stepwise Fairness Constraints
Stochastic Methods for AUC Optimization subject to AUC-based Fairness Constraints
Toward Fairness in Text Generation via Mutual Information Minimization based on Importance Sampling
The communication cost of security and privacy in federated frequency estimation
A Blessing of Dimensionality in Membership Inference through Regularization
Active Membership Inference Attack under Local Differential Privacy in Federated Learning
Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond
Wasserstein Distributionally Robust Linear-Quadratic Estimation under Martingale Constraints
Improving Adaptive Conformal Prediction Using Self-Supervised Learning
Convex Bounds on the Softmax Function with Applications to Robustness Verification
Domain Adaptation under Missingness Shift
Adapting to Latent Subgroup Shifts via Concepts and Proxies
Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise
Conformalized Unconditional Quantile Regression
Minimax-Bayes Reinforcement Learning
Discrete Langevin Samplers via Wasserstein Gradient Flow
(ends 7:00 PM)
THU 27 APR
7 a.m.
Registration + Assistance
(ends 12:00 PM)
8 a.m.
Mentorship:
Mentoring: Tips for Scientific Writing
(ends 9:00 AM)
9 a.m.
Invited Talk:
An Automatic Finite-Sample Robustness Check: Can Dropping a Little Data Change Conclusions?
Tamara Broderick
(ends 10:00 AM)
10 a.m.
Coffee Break
10:30 a.m.
Supervised Learning [10:30-11:30]
Orals 10:30-11:30
[10:30] Don't be fooled: label leakage in explanation methods and the importance of their quantitative evaluation
[10:45] Fix-A-Step: Semi-supervised Learning From Uncurated Unlabeled Data
[11:00] Blessing of Class Diversity in Pre-training
[11:15] Federated Learning under Distributed Concept Drift
(ends 11:30 AM)
11:30 a.m.
Statistical Methods 2 [11:30-12:30]
Orals 11:30-12:30
[11:30] Scalable Bicriteria Algorithms for Non-Monotone Submodular Cover
[11:45] Noisy Low-rank Matrix Optimization: Geometry of Local Minima and Convergence Rate
[12:00] An Efficient and Continuous Voronoi Density Estimator
[12:15] Hedging against Complexity: Distributionally Robust Optimization with Parametric Approximation
(ends 12:30 PM)
12:30 p.m.
Lunch Break
2 p.m.
Poster Session 3 [2:00-4:30]
Posters 2:00-4:30
Uncertainty-aware Unsupervised Video Hashing
Uni6Dv2: Noise Elimination for 6D Pose Estimation
Towards Balanced Representation Learning for Credit Policy Evaluation
TabLLM: Few-shot Classification of Tabular Data with Large Language Models
Two-Sample Tests for Inhomogeneous Random Graphs in $L_r$ norm: Optimality and Asymptotics
Active Exploration via Experiment Design in Markov Chains
SoundSynp: Sound Source Detection from Raw Waveforms with Multi-Scale Synperiodic Filterbanks
Direct Inference of Effect of Treatment (DIET) for a Cookieless World
INO: Invariant Neural Operators for Learning Complex Physical Systems with Momentum Conservation
Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions
SurvivalGAN: Generating Time-to-Event Data for Survival Analysis
Vector Quantized Time Series Generation with a Bidirectional Prior Model
Adversarial robustness of VAEs through the lens of local geometry
An Unpooling Layer for Graph Generation
Geometric Random Walk Graph Neural Networks via Implicit Layers
Spectral Augmentations for Graph Contrastive Learning
Multi-task Representation Learning with Stochastic Linear Bandits
Meta-learning for Robust Anomaly Detection
Learning to Generalize Provably in Learning to Optimize
LOFT: Finding Lottery Tickets through Filter-wise Training
Neural Discovery of Permutation Subgroups
Inducing Neural Collapse in Deep Long-tailed Learning
Strong Lottery Ticket Hypothesis with $\varepsilon$--perturbation
Benign overfitting of non-smooth neural networks beyond lazy training
On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks
Equivariant Representation Learning via Class-Pose Decomposition
Nonmyopic Multiclass Active Search with Diminishing Returns for Diverse Discovery
Bayesian Optimization with Conformal Prediction Sets
A stopping criterion for Bayesian optimization by the gap of expected minimum simple regrets
Optimal Sketching Bounds for Sparse Linear Regression
Noisy Low-rank Matrix Optimization: Geometry of Local Minima and Convergence Rate
Federated Learning under Distributed Concept Drift
Privacy-preserving Sparse Generalized Eigenvalue Problem
ForestPrune: Compact Depth-Pruned Tree Ensembles
Fast Block Coordinate Descent for Non-Convex Group Regularizations
Semantic Strengthening of Neuro-Symbolic Learning
Compress Then Test: Powerful Kernel Testing in Near-linear Time
Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropout
On the Convergence of Distributed Stochastic Bilevel Optimization Algorithms over a Network
Graph Alignment Kernels using Weisfeiler and Leman Hierarchies
Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection
Convolutional Persistence as a Remedy to Neural Model Analysis
Multi-Agent congestion cost minimization with linear function approximations
Interactive Learning with Pricing for Optimal and Stable Allocations in Markets
Multi-armed Bandit Experimental Design: Online Decision-making and Adaptive Inference
Competing against Adaptive Strategies in Online Learning via Hints
Meta-Learning with Adjoint Methods
MARS: Masked Automatic Ranks Selection in Tensor Decompositions
Coordinate Ascent for Off-Policy RL with Global Convergence Guarantees
Dueling RL: Reinforcement Learning with Trajectory Preferences
Sample Complexity of Kernel-Based Q-Learning
Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation
Identification of Blackwell Optimal Policies for Deterministic MDPs
Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path
Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embedding
Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments
Multiple-policy High-confidence Policy Evaluation
On The Convergence Of Policy Iteration-Based Reinforcement Learning With Monte Carlo Policy Evaluation
Conformal Off-Policy Prediction
Provably Efficient Model-Free Algorithms for Non-stationary CMDPs
Fix-A-Step: Semi-supervised Learning From Uncurated Unlabeled Data
Nonstochastic Contextual Combinatorial Bandits
AUC-based Selective Classification
On the Capacity Limits of Privileged ERM
Score-based Quickest Change Detection for Unnormalized Models
Differentiable Change-point Detection With Temporal Point Processes
The Ordered Matrix Dirichlet for State-Space Models
T-Phenotype: Discovering Phenotypes of Predictive Temporal Patterns in Disease Progression
Improved Approximation for Fair Correlation Clustering
Random Features Model with General Convex Regularization: A Fine Grained Analysis with Precise Asymptotic Learning Curves
Robust and Agnostic Learning of Conditional Distributional Treatment Effects
Kernel Conditional Moment Constraints for Confounding Robust Inference
Rank-Based Causal Discovery for Post-Nonlinear Models
Sample Complexity of Distinguishing Cause from Effect
A New Causal Decomposition Paradigm towards Health Equity
Improved Generalization Bound and Learning of Sparsity Patterns for Data-Driven Low-Rank Approximation
Semi-Verified PAC Learning from the Crowd
One Arrow, Two Kills: A Unified Framework for Achieving Optimal Regret Guarantees for Sleeping Bandits
Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach
Posterior Tracking Algorithm for Classification Bandits
Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles
Thresholded linear bandits
Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework
Piecewise Stationary Bandits under Risk Criteria
Optimism and Delays in Episodic Reinforcement Learning
Beyond Performative Prediction: Open-environment Learning with Presence of Corruptions
Doubly Fair Dynamic Pricing
Ideal Abstractions for Decision-Focused Learning
“Plus/minus the learning rate”: Easy and Scalable Statistical Inference with SGD
Pricing against a Budget and ROI Constrained Buyer
On the Strategyproofness of the Geometric Median
On double-descent in uncertainty quantification in overparametrized models
Sampling From a Schrödinger Bridge
Minimum-Entropy Coupling Approximation Guarantees Beyond the Majorization Barrier
On Universal Portfolios with Continuous Side Information
Recurrent Neural Networks and Universal Approximation of Bayesian Filters
A Tale of Two Efficient Value Iteration Algorithms for Solving Linear MDPs with Large Action Space
Influence Diagnostics under Self-concordance
Principled Approaches for Private Adaptation from a Public Source
On the Consistency Rate of Decision Tree Learning Algorithms
Optimal Sample Complexity Bounds for Non-convex Optimization under Kurdyka-Lojasiewicz Condition
Tighter PAC-Bayes Generalisation Bounds by Leveraging Example Difficulty
Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition
Flexible risk design using bi-directional dispersion
Blessing of Class Diversity in Pre-training
Neural Simulated Annealing
A Constant-Factor Approximation Algorithm for Reconciliation $k$-Median
Scalable Bicriteria Algorithms for Non-Monotone Submodular Cover
Randomized Primal-Dual Methods with Adaptive Step Sizes
Coordinate Descent for SLOPE
Stochastic Mirror Descent for Large-Scale Sparse Recovery
Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods
Acceleration of Frank-Wolfe Algorithms with Open-Loop Step-Sizes
A Conditional Gradient-based Method for Simple Bilevel Optimization with Convex Lower-level Problem
PAC-Bayesian Learning of Optimization Algorithms
ASkewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks
Alternating Projected SGD for Equality-constrained Bilevel Optimization
Explicit Regularization in Overparametrized Models via Noise Injection
Online Learning for Non-monotone DR-Submodular Maximization: From Full Information to Bandit Feedback
Incremental Aggregated Riemannian Gradient Method for Distributed PCA
On the Accelerated Noise-Tolerant Power Method
Federated Averaging Langevin Dynamics: Toward a unified theory and new algorithms
Variational Boosted Soft Trees
Fast Variational Estimation of Mutual Information for Implicit and Explicit Likelihood Models
On Model Selection Consistency of Lasso for High-Dimensional Ising Models
Multi-Fidelity Bayesian Optimization with Unreliable Information Sources
Sparse Spectral Bayesian Permanental.Process with Generalized Kernel
Adversarial Random Forests for Density Estimation and Generative Modeling
An Efficient and Continuous Voronoi Density Estimator
Adaptive Cholesky Gaussian Processes
No-regret Sample-efficient Bayesian Optimization for Finding Nash Equilibria with Unknown Utilities
Actually Sparse Variational Gaussian Processes
Bayesian Optimization over High-Dimensional Combinatorial Spaces via Dictionary-based Embeddings
Gaussian Processes on Distributions based on Regularized Optimal Transport
Encoding Domain Knowledge in Multi-view Latent Variable Models: A Bayesian Approach with Structured Sparsity
Likelihood-Based Generative Radiance Field with Latent Space Energy-Based Model for 3D-Aware Disentangled Image Representation
NODAGS-Flow: Nonlinear Cyclic Causal Structure Learning
A New Modeling Framework for Continuous, Sequential Domains
SMCP3: Sequential Monte Carlo with Probabilistic Program Proposals
Oblivious near-optimal sampling for multidimensional signals with Fourier constraints
Precision/Recall on Imbalanced Test Data
A Faster Sampler for Discrete Determinantal Point Processes
On the Privacy Risks of Algorithmic Recourse
Distill n' Explain: explaining graph neural networks using simple surrogates
Heavy Sets with Applications to Interpretable Machine Learning Diagnostics
Manifold Restricted Interventional Shapley Values
Don't be fooled: label leakage in explanation methods and the importance of their quantitative evaluation
Fair Representation Learning with Unreliable Labels
Scalable Spectral Clustering with Group Fairness Constraints
Discrete Distribution Estimation under User-level Local Differential Privacy
High-Dimensional Private Empirical Risk Minimization by Greedy Coordinate Descent
Differentially Private Matrix Completion through Low-rank Matrix Factorization
Differentially Private Synthetic Control
Cooperative Inverse Decision Theory for Uncertain Preferences
Approximate Regions of Attraction in Learning with Decision-Dependent Distributions
Calibration of Probabilistic Classifier Sets
Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classes
Adversarial Noises Are Linearly Separable for （Nearly） Random Neural Networks
Online Defense Strategies for Reinforcement Learning Against Adaptive Reward Poisoning
Characterizing Internal Evasion Attacks in Federated Learning
Learning k-qubit Quantum Operators via Pauli Decomposition
(ends 4:30 PM)