Skip to yearly menu bar Skip to main content


Show Detail
Schedule Tue Wed Thu
Timezone:
America/Los_Angeles
 
Filter Rooms:  

 

TUE 13 APR
8:45 a.m.
Remarks:
Opening Remarks
(ends 9:00 AM)
9 a.m.
Invited Talk:
Reliable Predictions? Counterfactual Predictions? Equitable Treatment? Some Recent Progress in Predictive Inference
Emmanuel Candes
(ends 10:15 AM)
10:30 a.m.
Theory of Statistical and Deep Learning Methods [10:30-11:30]
Oral s 10:30-11:30
[10:30] Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent
[10:45] Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture Models
[11:00] Towards a Theoretical Understanding of the Robustness of Variational Autoencoders
[11:15] Stable ResNet
(ends 11:30 AM)
11:30 a.m.
Sampling Methods [11:30-12:30]
Oral s 11:30-12:30
[11:30] Couplings for Multinomial Hamiltonian Monte Carlo
[11:45] An Adaptive-MCMC Scheme for Setting Trajectory Lengths in Hamiltonian Monte Carlo
[12:00] Maximal Couplings of the Metropolis-Hastings Algorithm
[12:15] GANs with Conditional Independence Graphs: On Subadditivity of Probability Divergences
(ends 12:30 PM)
12:30 p.m.
Mentorship:
Mentorship Session 1
(ends 2:00 PM)
Affinity Event:
WiML and Caucus for Women in Statistics
(ends 2:00 PM)
2 p.m.
Poster Session 1 [2:00-4:00]
Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data
Does Invariant Risk Minimization Capture Invariance?
Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation
Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series
A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks
Inductive Mutual Information Estimation: A Convex Maximum-Entropy Copula Approach
Bayesian Active Learning by Soft Mean Objective Cost of Uncertainty
Matérn Gaussian Processes on Graphs
A Hybrid Approximation to the Marginal Likelihood
Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions
Hogwild! over Distributed Local Data Sets with Linearly Increasing Mini-Batch Sizes
Detection and Defense of Topological Adversarial Attacks on Graphs
Efficient Interpolation of Density Estimators
On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient Flow
Deep Spectral Ranking
Designing Transportable Experiments Under S-admissability
Semi-Supervised Learning with Meta-Gradient
Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations.
Sample Complexity Bounds for Two Timescale Value-based Reinforcement Learning Algorithms
Reinforcement Learning for Mean Field Games with Strategic Complementarities
Maximizing Agreements for Ranking, Clustering and Hierarchical Clustering via MAX-CUT
Training a Single Bandit Arm
Sketch based Memory for Neural Networks
Provably Efficient Actor-Critic for Risk-Sensitive and Robust Adversarial RL: A Linear-Quadratic Case
List Learning with Attribute Noise
No-Regret Algorithms for Private Gaussian Process Bandit Optimization
The Minecraft Kernel: Modelling correlated Gaussian Processes in the Fourier domain
Non-Stationary Off-Policy Optimization
Learning the Truth From Only One Side of the Story
Generalization of Quasi-Newton Methods: Application to Robust Symmetric Multisecant Updates
Counterfactual Representation Learning with Balancing Weights
An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling
Regression Discontinuity Design under Self-selection
Multitask Bandit Learning Through Heterogeneous Feedback Aggregation
Problem-Complexity Adaptive Model Selection for Stochastic Linear Bandits
Cluster Trellis: Data Structures & Algorithms for Exact Inference in Hierarchical Clustering
Dynamic Cutset Networks
A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix
Learning-to-Rank with Partitioned Preference: Fast Estimation for the Plackett-Luce Model
Nonparametric Variable Screening with Optimal Decision Stumps
Principal Subspace Estimation Under Information Diffusion
Learning with Gradient Descent and Weakly Convex Losses
Active Online Learning with Hidden Shifting Domains
Differentially Private Online Submodular Maximization
Fast Statistical Leverage Score Approximation in Kernel Ridge Regression
Distributionally Robust Optimization for Deep Kernel Multiple Instance Learning
Finding First-Order Nash Equilibria of Zero-Sum Games with the Regularized Nikaido-Isoda Function
Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization
On the Linear Convergence of Policy Gradient Methods for Finite MDPs
Influence Decompositions For Neural Network Attribution
Learning GPLVM with arbitrary kernels using the unscented transformation
On the Privacy Properties of GAN-generated Samples
Differentially Private Weighted Sampling
Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning
Misspecification in Prediction Problems and Robustness via Improper Learning
Sharp Analysis of a Simple Model for Random Forests
On Learning Continuous Pairwise Markov Random Fields
Non-asymptotic Performance Guarantees for Neural Estimation of f-Divergences
Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMC
Alternating Direction Method of Multipliers for Quantization
Convergence of Gaussian-smoothed optimal transport distance with sub-gamma distributions and dependent samples
Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning
Online Model Selection for Reinforcement Learning with Function Approximation
Animal pose estimation from video data with a hierarchical von Mises-Fisher-Gaussian model
Density of States Estimation for Out of Distribution Detection
A constrained risk inequality for general losses
Accumulations of Projections—A Unified Framework for Random Sketches in Kernel Ridge Regression
Active Learning under Label Shift
Competing AI: How does competition feedback affect machine learning?
Random Coordinate Underdamped Langevin Monte Carlo
Differentiable Greedy Algorithm for Monotone Submodular Maximization: Guarantees, Gradient Estimators, and Applications
Differentiable Causal Discovery Under Unmeasured Confounding
Algorithms for Fairness in Sequential Decision Making
Minimax Optimal Regression over Sobolev Spaces via Laplacian Regularization on Neighborhood Graphs
The Base Measure Problem and its Solution
Sample Elicitation
Bayesian Coresets: Revisiting the Nonconvex Optimization Perspective
The Sample Complexity of Meta Sparse Regression
Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks
Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration
SONIA: A Symmetric Blockwise Truncated Optimization Algorithm
Online Robust Control of Nonlinear Systems with Large Uncertainty
Shapley Flow: A Graph-based Approach to Interpreting Model Predictions
Improving Classifier Confidence using Lossy Label-Invariant Transformations
Associative Convolutional Layers
An Optimal Reduction of TV-Denoising to Adaptive Online Learning
TenIPS: Inverse Propensity Sampling for Tensor Completion
Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning
Accelerating Metropolis-Hastings with Lightweight Inference Compilation
Fast Adaptation with Linearized Neural Networks
(ends 4:00 PM)
4:15 p.m.
Bandits, Reinforcement Learning / Optimization [4:15-5:15]
Oral s 4:15-5:15
[4:15] Federated Multi-armed Bandits with Personalization
[4:30] Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning
[4:45] Provably Efficient Safe Exploration via Primal-Dual Policy Optimization
[5:00] Bayesian Coresets: Revisiting the Nonconvex Optimization Perspective
(ends 5:15 PM)
5:15 p.m.
Theory and Practice of Machine Learning [5:15-6:15]
Oral s 5:15-6:15
[5:15] Entropy Partial Transport with Tree Metrics: Theory and Practice
[5:30] Independent Innovation Analysis for Nonlinear Vector Autoregressive Process
[5:45] Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?
[6:00] A Variational Information Bottleneck Approach to Multi-Omics Data Integration
(ends 6:15 PM)
6:30 p.m.
Poster Session 2 [6:30-8:30]
Understanding the wiring evolution in differentiable neural architecture search
Linear Regression Games: Convergence Guarantees to Approximate Out-of-Distribution Solutions
Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization
Fenchel-Young Losses with Skewed Entropies for Class-posterior Probability Estimation
γ-ABC: Outlier-Robust Approximate Bayesian Computation Based on a Robust Divergence Estimator
Taming heavy-tailed features by shrinkage
Learning Individually Fair Classifier with Path-Specific Causal-Effect Constraint
Learning Shared Subgraphs in Ising Model Pairs
Identification of Matrix Joint Block Diagonalization
Tight Regret Bounds for Infinite-armed Linear Contextual Bandits
Generalization Bounds for Stochastic Saddle Point Problems
Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers
Predictive Power of Nearest Neighbors Algorithm under Random Perturbation
The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry
Provably Efficient Safe Exploration via Primal-Dual Policy Optimization
Mirror Descent View for Neural Network Quantization
Adversarially Robust Estimate and Risk Analysis in Linear Regression
Bayesian Model Averaging for Causality Estimation and its Approximation based on Gaussian Scale Mixture Distributions
Contrastive learning of strong-mixing continuous-time stochastic processes
Regularized Policies are Reward Robust
A comparative study on sampling with replacement vs Poisson sampling in optimal subsampling
Ridge Regression with Over-parametrized Two-Layer Networks Converge to Ridgelet Spectrum
Minimal enumeration of all possible total effects in a Markov equivalence class
DAG-Structured Clustering by Nearest Neighbors
Tensor Networks for Probabilistic Sequence Modeling
Minimax Model Learning
Q-learning with Logarithmic Regret
Federated Multi-armed Bandits with Personalization
Shadow Manifold Hamiltonian Monte Carlo
Online Forgetting Process for Linear Regression Models
Differentially Private Monotone Submodular Maximization Under Matroid and Knapsack Constraints
Meta Learning in the Continuous Time Limit
Hierarchical Inducing Point Gaussian Process for Inter-domian Observations
Independent Innovation Analysis for Nonlinear Vector Autoregressive Process
Gradient Descent in RKHS with Importance Labeling
GANs with Conditional Independence Graphs: On Subadditivity of Probability Divergences
Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning
Linear Models are Robust Optimal Under Strategic Behavior
Minimax Estimation of Laplacian Constrained Precision Matrices
Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?
A Parameter-Free Algorithm for Misspecified Linear Contextual Bandits
Consistent k-Median: Simpler, Better and Robust
Optimal query complexity for private sequential learning against eavesdropping
On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification
Learning Temporal Point Processes with Intermittent Observations
On the Faster Alternating Least-Squares for CCA
PClean: Bayesian Data Cleaning at Scale with Domain-Specific Probabilistic Programming
Robust Imitation Learning from Noisy Demonstrations
Entropy Partial Transport with Tree Metrics: Theory and Practice
Learning with risk-averse feedback under potentially heavy tails
Prediction with Finitely many Errors Almost Surely
Mean-Variance Analysis in Bayesian Optimization under Uncertainty
Sample efficient learning of image-based diagnostic classifiers via probabilistic labels
Beyond Perturbation Stability: LP Recovery Guarantees for MAP Inference on Noisy Stable Instances
Experimental Design for Regret Minimization in Linear Bandits
Stability and Risk Bounds of Iterative Hard Thresholding
Parametric Programming Approach for More Powerful and General Lasso Selective Inference
One-pass Stochastic Gradient Descent in overparametrized two-layer neural networks
On the Absence of Spurious Local Minima in Nonlinear Low-Rank Matrix Recovery Problems
Flow-based Alignment Approaches for Probability Measures in Different Spaces
Exponential Convergence Rates of Classification Errors on Learning with SGD and Random Features
RankDistil: Knowledge Distillation for Ranking
Multi-Fidelity High-Order Gaussian Processes for Physical Simulation
One-Round Communication Efficient Distributed M-Estimation
Communication Efficient Primal-Dual Algorithm for Nonconvex Nonsmooth Distributed Optimization
No-Regret Reinforcement Learning with Heavy-Tailed Rewards
Regret Minimization for Causal Inference on Large Treatment Space
Statistical Guarantees for Transformation Based Models with applications to Implicit Variational Inference
On the Generalization Properties of Adversarial Training
On the High Accuracy Limitation of Adaptive Property Estimation
Unifying Clustered and Non-stationary Bandits
vqSGD: Vector Quantized Stochastic Gradient Descent
Diagnostic Uncertainty Calibration: Towards Reliable Machine Predictions in Medical Domain
Tractable contextual bandits beyond realizability
On the Suboptimality of Negative Momentum for Minimax Optimization
Semi-Supervised Aggregation of Dependent Weak Supervision Sources With Performance Guarantees
Corralling Stochastic Bandit Algorithms
CADA: Communication-Adaptive Distributed Adam
Robustness and scalability under heavy tails, without strong convexity
Causal Modeling with Stochastic Confounders
Dual Principal Component Pursuit for Learning a Union of Hyperplanes: Theory and Algorithms
Good Classifiers are Abundant in the Interpolating Regime
Dominate or Delete: Decentralized Competing Bandits in Serial Dictatorship
Graph Gamma Process Linear Dynamical Systems
Bandit algorithms: Letting go of logarithmic regret for statistical robustness
Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent
Tracking Regret Bounds for Online Submodular Optimization
Causal Inference with Selectively Deconfounded Data
Understanding Gradient Clipping In Incremental Gradient Methods
Non-Volume Preserving Hamiltonian Monte Carlo and No-U-TurnSamplers
Maximal Couplings of the Metropolis-Hastings Algorithm
(ends 8:30 PM)
8:30 p.m.
Mentorship:
Mentorship Session 2
(ends 10:00 PM)
WED 14 APR
4 a.m.
Affinity Event:
Black in AI
(ends 6:00 AM)
Mentorship:
Mentorship Session 3
(ends 6:00 AM)
6 a.m.
Poster Session 3 [6:00-8:00]
Top-m identification for linear bandits
Quantum Tensor Networks, Stochastic Processes, and Weighted Automata
Multi-Armed Bandits with Cost Subsidy
Logical Team Q-learning: An approach towards factored policies in cooperative MARL
Online k-means Clustering
Aggregating Incomplete and Noisy Rankings
Online probabilistic label trees
Graphical Normalizing Flows
Scalable Gaussian Process Variational Autoencoders
Kernel Distributionally Robust Optimization: Generalized Duality Theorem and Stochastic Approximation
Improved Complexity Bounds in Wasserstein Barycenter Problem
On the convergence of the Metropolis algorithm with fixed-order updates for multivariate binary probability distributions
Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
Anderson acceleration of coordinate descent
Neural Enhanced Belief Propagation on Factor Graphs
Deep Generative Missingness Pattern-Set Mixture Models
Collaborative Classification from Noisy Labels
Sequential Random Sampling Revisited: Hidden Shuffle Method
Local Competition and Stochasticity for Adversarial Robustness in Deep Learning
On the proliferation of support vectors in high dimensions
Adaptive wavelet pooling for convolutional neural networks
Fully Gap-Dependent Bounds for Multinomial Logit Bandit
Inference in Stochastic Epidemic Models via Multinomial Approximations
Hyperparameter Transfer Learning with Adaptive Complexity
On Multilevel Monte Carlo Unbiased Gradient Estimation for Deep Latent Variable Models
Linearly Constrained Gaussian Processes with Boundary Conditions
Equitable and Optimal Transport with Multiple Agents
Learning Complexity of Simulated Annealing
Dirichlet Pruning for Convolutional Neural Networks
A Variational Inference Approach to Learning Multivariate Wold Processes
Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization
Wasserstein Random Forests and Applications in Heterogeneous Treatment Effects
Deep Neural Networks Are Congestion Games: From Loss Landscape to Wardrop Equilibrium and Beyond
Improving predictions of Bayesian neural nets via local linearization
All of the Fairness for Edge Prediction with Optimal Transport
Deep Fourier Kernel for Self-Attentive Point Processes
Optimal Quantisation of Probability Measures Using Maximum Mean Discrepancy
High-Dimensional Multi-Task Averaging and Application to Kernel Mean Embedding
Predictive Complexity Priors
A Bayesian nonparametric approach to count-min sketch under power-law data streams
Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learning
On Riemannian Stochastic Approximation Schemes with Fixed Step-Size
Free-rider Attacks on Model Aggregation in Federated Learning
Unconstrained MAP Inference, Exponentiated Determinantal Point Processes, and Exponential Inapproximability
On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
Fast Learning in Reproducing Kernel Krein Spaces via Signed Measures
Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network
On the number of linear functions composing deep neural network: Towards a refined definition of neural networks complexity
Direct-Search for a Class of Stochastic Min-Max Problems
A Theoretical Characterization of Semi-supervised Learning with Self-training for Gaussian Mixture Models
Causal Autoregressive Flows
Differentiating the Value Function by using Convex Duality
Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization
Adaptive Sampling for Fast Constrained Maximization of Submodular Functions
Sparse Gaussian Processes Revisited: Bayesian Approaches to Inducing-Variable Approximations
SDF-Bayes: Cautious Optimism in Safe Dose-Finding Clinical Trials with Drug Combinations and Heterogeneous Patient Groups
Foundations of Bayesian Learning from Synthetic Data
Learning Bijective Feature Maps for Linear ICA
A unified view of likelihood ratio and reparameterization gradients
Gaming Helps! Learning from Strategic Interactions in Natural Dynamics
On the Effect of Auxiliary Tasks on Representation Dynamics
CONTRA: Contrarian statistics for controlled variable selection
Nearest Neighbour Based Estimates of Gradients: Sharp Nonasymptotic Bounds and Applications
Self-Supervised Steering Angle Prediction for Vehicle Control Using Visual Odometry
Robust and Private Learning of Halfspaces
Logistic Q-Learning
An Analysis of the Adaptation Speed of Causal Models
Fisher Auto-Encoders
Thresholded Adaptive Validation: Tuning the Graphical Lasso for Graph Recovery
Learning Fair Scoring Functions: Bipartite Ranking under ROC-based Fairness Constraints
SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation
Nonlinear Functional Output Regression: A Dictionary Approach
Nested Barycentric Coordinate System as an Explicit Feature Map
Latent Derivative Bayesian Last Layer Networks
The Sample Complexity of Level Set Approximation
Improved Exploration in Factored Average-Reward MDPs
Kernel regression in high dimensions: Refined analysis beyond double descent
An Analysis of LIME for Text Data
Couplings for Multinomial Hamiltonian Monte Carlo
Amortized Bayesian Prototype Meta-learning: A New Probabilistic Meta-learning Approach to Few-shot Image Classification
Wyner-Ziv Estimators: Efficient Distributed Mean Estimation with Side-Information
Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithms
Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence
Interpretable Random Forests via Rule Extraction
Calibrated Adaptive Probabilistic ODE Solvers
Regularized ERM on random subspaces
Budgeted and Non-Budgeted Causal Bandits
DP-MERF: Differentially Private Mean Embeddings with RandomFeatures for Practical Privacy-preserving Data Generation
Differentiable Divergences Between Time Series
On the Memory Mechanism of Tensor-Power Recurrent Models
A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free!
Offline detection of change-points in the mean for stationary graph signals.
ATOL: Measure Vectorization for Automatic Topologically-Oriented Learning
Efficient Statistics for Sparse Graphical Models from Truncated Samples
Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes
(ends 8:00 AM)
8:15 a.m.
Theory and Methods of Learning [8:15-9:15]
Oral s 8:15-9:15
[8:15] Neural Enhanced Belief Propagation on Factor Graphs
[8:30] An Analysis of LIME for Text Data
[8:45] Bandit algorithms: Letting go of logarithmic regret for statistical robustness
[9:00] The Sample Complexity of Level Set Approximation
(ends 9:15 AM)
9:15 a.m.
Bandits, Reinforcement Learning / Learning Theory / Sparse Methods [9:15-10:15]
Oral s 9:15-10:15
[9:15] Logistic Q-Learning
[9:30] Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits
[9:45] Robust and Private Learning of Halfspaces
[10:00] Hadamard Wirtinger Flow for Sparse Phase Retrieval
(ends 10:15 AM)
10:30 a.m.
Optimization / Learning Theory / Generalization [10:30-11:30]
Oral s 10:30-11:30
[10:30] Projection-Free Optimization on Uniformly Convex Sets
[10:45] Measure Transport with Kernel Stein Discrepancy
[11:00] Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization
[11:15] Improving Adversarial Robustness via Unlabeled Out-of-Domain Data
(ends 11:30 AM)
11:30 a.m.
Graphs and Networks [11:30-12:30]
Oral s 11:30-12:30
[11:30] Graph Community Detection from Coarse Measurements: Recovery Conditions for the Coarsened Weighted Stochastic Block Model
[11:45] Matérn Gaussian Processes on Graphs
[12:00] Differentially Private Analysis on Graph Streams
[12:15] On Learning Continuous Pairwise Markov Random Fields
(ends 12:30 PM)
12:45 p.m.
Poster Session 4 [12:45-2:45]
Decision Making Problems with Funnel Structure: A Multi-Task Learning Approach with Application to Email Marketing Campaigns
Fair for All: Best-effort Fairness Guarantees for Classification
Combinatorial Gaussian Process Bandits with Probabilistically Triggered Arms
Shuffled Model of Differential Privacy in Federated Learning
A Statistical Perspective on Coreset Density Estimation
Exploiting Equality Constraints in Causal Inference
Feedback Coding for Active Learning
Efficient Balanced Treatment Assignments for Experimentation
Probabilistic Sequential Matrix Factorization
Curriculum Learning by Optimizing Learning Dynamics
Product Manifold Learning
A Deterministic Streaming Sketch for Ridge Regression
Abstract Value Iteration for Hierarchical Reinforcement Learning
Uniform Consistency of Cross-Validation Estimators for High-Dimensional Ridge Regression
Robust Mean Estimation on Highly Incomplete Data with Arbitrary Outliers
Localizing Changes in High-Dimensional Regression Models
A Theory of Multiple-Source Adaptation with Limited Target Labeled Data
Improving KernelSHAP: Practical Shapley Value Estimation Using Linear Regression
Provable Hierarchical Imitation Learning via EM
Location Trace Privacy Under Conditional Priors
Power of Hints for Online Learning with Movement Costs
On the Minimax Optimality of the EM Algorithm for Learning Two-Component Mixed Linear Regression
Private optimization without constraint violations
On Data Efficiency of Meta-learning
Implicit Regularization via Neural Feature Alignment
Selective Classification via One-Sided Prediction
Rate-improved inexact augmented Lagrangian method for constrained nonconvex optimization
Contextual Blocking Bandits
Goodness-of-Fit Test for Mismatched Self-Exciting Processes
Significance of Gradient Information in Bayesian Optimization
Regret-Optimal Filtering
Stability and Differential Privacy of Stochastic Gradient Descent for Pairwise Learning with Non-Smooth Loss
Approximation Algorithms for Orthogonal Non-negative Matrix Factorization
Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders
Completing the Picture: Randomized Smoothing Suffers from the Curse of Dimensionality for a Large Family of Distributions
Kernel Interpolation for Scalable Online Gaussian Processes
CLAR: Contrastive Learning of Auditory Representations
A Study of Condition Numbers for First-Order Optimization
Hyperbolic graph embedding with enhanced semi-implicit variational inference.
A Variational Information Bottleneck Approach to Multi-Omics Data Integration
Hidden Cost of Randomized Smoothing
Learning Smooth and Fair Representations
Automatic Differentiation Variational Inference with Mixtures
Finite-Sample Regret Bound for Distributionally Robust Offline Tabular Reinforcement Learning
Fast and Smooth Interpolation on Wasserstein Space
Low-Rank Generalized Linear Bandit Problems
Efficient Designs Of SLOPE Penalty Sequences In Finite Dimension
Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation
Geometrically Enriched Latent Spaces
A Change of Variables Method For Rectangular Matrix-Vector Products
Principal Component Regression with Semirandom Observations via Matrix Completion
Towards Flexible Device Participation in Federated Learning
Hierarchical Clustering in General Metric Spaces using Approximate Nearest Neighbors
Towards Understanding the Behaviors of Optimal Deep Active Learning Algorithms
Scalable Constrained Bayesian Optimization
DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural Networks
Direct Loss Minimization for Sparse Gaussian Processes
Evaluating Model Robustness and Stability to Dataset Shift
When MAML Can Adapt Fast and How to Assist When It Cannot
Stochastic Bandits with Linear Constraints
Follow Your Star: New Frameworks for Online Stochastic Matching with Known and Unknown Patience
Evading the Curse of Dimensionality in Unconstrained Private GLMs
Robust hypothesis testing and distribution estimation in Hellinger distance
Local Stochastic Gradient Descent Ascent: Convergence Analysis and Communication Efficiency
Federated Learning with Compression: Unified Analysis and Sharp Guarantees
One-Sketch-for-All: Non-linear Random Features from Compressed Linear Measurements
Novel Change of Measure Inequalities with Applications to PAC-Bayesian Bounds and Monte Carlo Estimation
On the Consistency of Metric and Non-Metric K-Medoids
Large Scale K-Median Clustering for Stable Clustering Instances
A Fast and Robust Method for Global Topological Functional Optimization
Rate-Regularization and Generalization in Variational Autoencoders
The Multiple Instance Learning Gaussian Process Probit Model
Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference
Differentially Private Analysis on Graph Streams
Learning to Defend by Learning to Attack
Reaping the Benefits of Bundling under High Production Costs
Deep Probabilistic Accelerated Evaluation: A Robust Certifiable Rare-Event Simulation Methodology for Black-Box Safety-Critical Systems
Rao-Blackwellised parallel MCMC
Meta-Learning Divergences for Variational Inference
Toward a General Theory of Online Selective Sampling: Trading Off Mistakes and Queries
A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets
False Discovery Rates in Biological Networks
Provably Safe PAC-MDP Exploration Using Analogies
Learning Prediction Intervals for Regression: Generalization and Calibration
Understanding Robustness in Teacher-Student Setting: A New Perspective
Quick Streaming Algorithms for Maximization of Monotone Submodular Functions in Linear Time
Faster & More Reliable Tuning of Neural Networks: Bayesian Optimization with Importance Sampling
Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors
(ends 2:45 PM)
3 p.m.
Mentorship:
Mentorship Session 4
(ends 4:00 PM)
4 p.m.
Invited Talk:
Veridical Data Science: The Practice of Responsible Data Analysis and Decision-Making
Bin Yu
(ends 5:15 PM)
5:15 p.m.
Affinity Event:
Caucus for Women in Statistics
(ends 6:15 PM)
5:30 p.m.
Mentorship:
Mentorship Session 5
(ends 7:00 PM)
THU 15 APR
4 a.m.
Mentorship:
Mentorship Session 6
(ends 6:00 AM)
6 a.m.
Invited Talk:
Recent Progress in Simulation-Based Inference
Kyle Cranmer
(ends 7:15 AM)
7:30 a.m.
Poster Session 5 [7:30-9:30]
The Teaching Dimension of Kernel Perceptron
Learning with Hyperspherical Uniformity
Approximate Data Deletion from Machine Learning Models
Learning Contact Dynamics using Physically Structured Neural Networks
A Spectral Analysis of Dot-product Kernels
Efficient Computation and Analysis of Distributional Shapley Values
Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT
Graph Community Detection from Coarse Measurements: Recovery Conditions for the Coarsened Weighted Stochastic Block Model
Iterative regularization for convex regularizers
Robust Learning under Strong Noise via SQs
Online Active Model Selection for Pre-trained Classifiers
Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates
Measure Transport with Kernel Stein Discrepancy
LassoNet: Neural Networks with Feature Sparsity
Quantifying the Privacy Risks of Learning High-Dimensional Graphical Models
Fork or Fail: Cycle-Consistent Training with Many-to-One Mappings
A Scalable Gradient Free Method for Bayesian Experimental Design with Implicit Models
Self-Concordant Analysis of Generalized Linear Bandits with Forgetting
Transforming Gaussian Processes With Normalizing Flows
Optimizing Percentile Criterion using Robust MDPs
Bayesian Inference with Certifiable Adversarial Robustness
Reinforcement Learning in Parametric MDPs with Exponential Families
Towards a Theoretical Understanding of the Robustness of Variational Autoencoders
LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads
A Stein Goodness-of-test for Exponential Random Graph Models
When OT meets MoM: Robust estimation of Wasserstein Distance
A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces
Generalized Spectral Clustering via Gromov-Wasserstein Learning
When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence
Latent Gaussian process with composite likelihoods and numerical quadrature
Why did the distribution change?
Context-Specific Likelihood Weighting
Local SGD: Unified Theory and New Efficient Methods
Faster Kernel Interpolation for Gaussian Processes
Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture Models
A Contraction Approach to Model-based Reinforcement Learning
Hierarchical Clustering via Sketches and Hierarchical Correlation Clustering
Approximate Message Passing with Spectral Initialization for Generalized Linear Models
An Adaptive-MCMC Scheme for Setting Trajectory Lengths in Hamiltonian Monte Carlo
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting
Convergence Properties of Stochastic Hypergradients
Improving Adversarial Robustness via Unlabeled Out-of-Domain Data
Stable ResNet
Hadamard Wirtinger Flow for Sparse Phase Retrieval
Sparse Algorithms for Markovian Gaussian Processes
Noise Contrastive Meta-Learning for ConditionalDensity Estimation using Kernel Mean Embeddings
Asymptotics of Ridge(less) Regression under General Source Condition
Explicit Regularization of Stochastic Gradient Methods through Duality
Continuum-Armed Bandits: A Function Space Perspective
Online Sparse Reinforcement Learning
High-Dimensional Feature Selection for Sample Efficient Treatment Effect Estimation
Projection-Free Optimization on Uniformly Convex Sets
Mirrorless Mirror Descent: A Natural Derivation of Mirror Descent
Model updating after interventions paradoxically introduces bias
Group testing for connected communities
Clustering multilayer graphs with missing nodes
Aligning Time Series on Incomparable Spaces
On the role of data in PAC-Bayes
Approximating Lipschitz continuous functions with GroupSort neural networks
Learning Matching Representations for Individualized Organ Transplantation Allocation
Stochastic Gradient Descent Meets Distribution Regression
Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Models
Spectral Tensor Train Parameterization of Deep Learning Layers
Longitudinal Variational Autoencoder
Fractional moment-preserving initialization schemes for training deep neural networks
Stochastic Linear Bandits Robust to Adversarial Attacks
Benchmarking Simulation-Based Inference
Variational Autoencoder with Learned Latent Structure
Revisiting Projection-free Online Learning: the Strongly Convex Case
Moment-Based Variational Inference for Stochastic Differential Equations
Variational inference for nonlinear ordinary differential equations
CWY Parametrization: a Solution for Parallelized Optimization of Orthogonal and Stiefel Matrices
Federated f-Differential Privacy
Learning Partially Known Stochastic Dynamics with Empirical PAC Bayes
Smooth Bandit Optimization: Generalization to Holder Space
Momentum Improves Optimization on Riemannian Manifolds
Instance-Wise Minimax-Optimal Algorithms for Logistic Bandits
Fourier Bases for Solving Permutation Puzzles
On Information Gain and Regret Bounds in Gaussian Process Bandits
Adaptive Approximate Policy Iteration
Distribution Regression for Sequential Data
Reinforcement Learning for Constrained Markov Decision Processes
Understanding and Mitigating Exploding Inverses in Invertible Neural Networks
Latent variable modeling with random features
Active Learning with Maximum Margin Sparse Gaussian Processes
The Unexpected Deterministic and Universal Behavior of Large Softmax Classifiers
Causal Inference under Networked Interference and Intervention Policy Enhancement
Variable Selection with Rigorous Uncertainty Quantification using Deep Bayesian Neural Networks: Posterior Concentration and Bernstein-von Mises Phenomenon
Learning User Preferences in Non-Stationary Environments
Automatic structured variational inference
No-regret Algorithms for Multi-task Bayesian Optimization
(ends 9:30 AM)
9:45 a.m.
Mentorship:
Mentorship Session 7
(ends 11:45 AM)
noon
Fairness / Privacy / Decision Making / Data Cleaning [12:00-1:00]
Oral s 12:00-1:00
[12:00] Private optimization without constraint violations
[12:15] Learning Smooth and Fair Representations
[12:30] Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration
[12:45] PClean: Bayesian Data Cleaning at Scale with Domain-Specific Probabilistic Programming
(ends 1:00 PM)
1 p.m.
Generalization / Reinforcement Learning / Optimization [1:00-2:00]
Oral s 1:00-2:00
[1:00] Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders
[1:15] Does Invariant Risk Minimization Capture Invariance?
[1:30] Density of States Estimation for Out of Distribution Detection
[1:45] Quick Streaming Algorithms for Maximization of Monotone Submodular Functions in Linear Time
(ends 2:00 PM)
2:15 p.m.
Deep Learning / High-dimensionality [2:15-3:15]
Oral s 2:15-3:15
[2:15] Sketch based Memory for Neural Networks
[2:30] Associative Convolutional Layers
[2:45] Deep Fourier Kernel for Self-Attentive Point Processes
[3:00] Uniform Consistency of Cross-Validation Estimators for High-Dimensional Ridge Regression
(ends 3:15 PM)
3:15 p.m.
Learning Theory [3:15-4:15]
Oral s 3:15-4:15
[3:15] A constrained risk inequality for general losses
[3:30] Misspecification in Prediction Problems and Robustness via Improper Learning
[3:45] Minimax Optimal Regression over Sobolev Spaces via Laplacian Regularization on Neighborhood Graphs
[4:00] Faster Kernel Interpolation for Gaussian Processes
(ends 4:15 PM)