01:03:32

Jelani Nelson, "Recent advances in streaming and private heavy hitters"

57:59

Maryam Fazel, "Policy Optimization for Learning Control Policies"

01:06:24

Alon Orlitsky, "Robust learning from untrusted sources: The best things in life are (almost) free"

53:33

Tutorial: Statistical Inference in Distributed or Constrained Settings (Part 2)

01:06:46

Tutorial: Statistical Inference in Distributed or Constrained Settings (Part 1)

01:02:29

Tutorial: Statistical Foundations of Reinforcement Learning (Part 2)

56:17

Tutorial: Statistical Foundations of Reinforcement Learning (Part 1)

15:34

Finite-Time Analysis of Asynchronous Stochastic Approximation and Q-Learning

14:53

A Closer Look at Small-loss Bounds for Bandits with Graph Feedback

14:56

Dimension-Free Bounds for Chasing Convex Functions

13:34

Covariance-adapting algorithm for semi-bandits with application to sparse rewards

15:31

Tsallis-INF for Decoupled Exploration and Exploitation in Multi-armed Bandits

15:31

A Greedy Anytime Algorithm for Sparse PCA

14:37

Domain Compression: A New Primitive

15:07

Selfish Robustness and Equilibria in Multi-Player Bandits

15:56

Learning a Single Neuron with Gradient Methods

15:11

High probability guarantees for stochastic convex optimization

14:13

Gradient descent algorithms for Bures-Wasserstein barycenters

15:20

Exploration by Optimisation in Partial Monitoring

12:22

PAC learning with stable and private predictions

15:05

Halpern Iteration for Near-Optimal and Parameter-Free Monotone Inclusion and Strong Solutions

14:01

Tight Lower Bounds for Combinatorial Multi-Armed Bandits

13:41

Universal Approximation with Deep Narrow Networks

09:39

On the Convergence of Stochastic Gradient Descent with Low-Rank Projections for Convex Low-Rank

13:22

From Nesterov's Estimate Sequence to Riemannian Acceleration

14:45

Reasoning About Generalization via Conditional Mutual Information

14:59

Asymptotic Errors for High-Dimensional Convex Penalized Linear Regression beyond Gaussian Matrices

15:16

No-Regret Prediction in Marginally Stable Systems

13:03

Information Directed Sampling for Linear Partial Monitoring

15:28

Consistent recovery threshold of hidden nearest neighbor graphs

14:49

ID3 Learns Juntas for Smoothed Product Distributions

12:35

An O(m/eps^3.5)-Cost Algorithm for Semidefinite Programs with Diagonal Constraints

11:50

How Good is SGD with Random Shuffling?

13:25

Adaptive Submodular Maximization under Stochastic Item Cost

15:05

Faster Projection-free Online Learning

11:00

Optimality and Approximation with Policy Gradient Methods

13:04

Provably Efficient Reinforcement Learning with Linear Function Approximation

15:01

How to trap a gradient flow

13:31

Nearly Non-Expansive Bounds for Mahalanobis Hard Thresholding

14:25

Sharper Bounds for Uniformly Stable Algorithms

12:31

Active Local Learning

14:58

Locally Private Hypothesis Selection

14:09

Learning over-parametrized neural networks-Going beyond NTKs

15:21

Approximation Schemes for ReLU Regression

15:10

Reducibility and Statistical-Computational Gaps from Secret Leakage

14:57

Coordination without communication: optimal regret in two players multi-armed bandits

13:40

Information Theoretic Optimal Learning of Gaussian Graphical Models

14:58

Logsmooth Gradient Concentration and Tighter Runtimes for Metropolized Hamiltonian Monte Carlo

15:01

A Fast Spectral Algorithm for Mean Estimation with Sub-Gaussian Rates

14:36

Taking a hint: How to leverage loss predictors in contextual bandits

15:20

ODE-Inspired Analysis for the Biological Version of Oja’s Rule in Solving Streaming PCA

14:22

Calibrated Surrogate Losses for Adversarially Robust Classification

13:55

Rigorous Guarantees for Tyler's M-Estimator via Quantum Expansion

15:14

Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal

14:42

Efficient improper learning for online logistic regression

14:56

Learning Halfspaces with Massart Noise Under Structured Distributions

15:18

Online Learning with Vector Costs and Bandits with Knapsacks

12:58

Near-Optimal Methods for Minimizing Star-Convex Functions and Beyond

14:36

Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimes

12:47

Improper Learning for Non-Stochastic Control