Does data interpolation contradict statistical optimality?
1 version
AR
Alexander Rakhlin
cs.LGstat.MLmath.STstat.THmath.OCcs.AIcs.GTcs.ITmath.ITcs.SY
On Valency
published · living versionsPreprints & journals
105 papers in the corpus · 2009–2026Oracle-Efficient and Parameter-Free Agnostic Smoothed Online Learning
0 citations
Exact simulation of diffusions and improved algorithms for log-concave sampling
0 citations
Learning with Simulators: No Regret in a Computationally Bounded World
0 citations
The Sample Complexity of Multiclass and Sparse Contextual Bandits
0 citations
Self-Normalized Martingales and Uniform Regret Bounds for Linear Regression
0 citations
End-to-End Efficient RL for Linear Bellman Complete MDPs with Deterministic Transitions
0 citations
Demonstration Experiments
0 citations
Characterizing Online and Private Learnability under Distributional Constraints via Generalized Smoothness
0 citations
High-accuracy log-concave sampling with stochastic queries
0 citations
High-accuracy sampling for diffusion models and log-concave distributions
0 citations
A Gapped Scale-Sensitive Dimension and Lower Bounds for Offset Rademacher Complexity
0 citations
Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits
0 citations
Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning
0 citations
On the Minimax Regret of Sequential Probability Assignment via Square-Root Entropy
0 citations
Beyond Covariance Matrix: The Statistical Complexity of Private Linear Regression
0 citations
Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective
0 citations
Decision Making in Changing Environments: Robustness, Query-Based Learning, and Differential Privacy
0 citations
GaussMark: A Practical Approach for Structural Watermarking of Language Models
0 citations
Refined Risk Bounds for Unbounded Losses via Transductive Priors
0 citations
How Does Variance Shape the Regret in Contextual Bandits?
1 citation
Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
2 citations
Random Latent Exploration for Deep Reinforcement Learning
1 citation
Near-Optimal Learning and Planning in Separated Latent MDPs
0 citations
Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
2 citations
The Power of Resets in Online Reinforcement Learning
1 citation
Online Estimation via Offline Estimation: An Information-Theoretic Framework
1 citation
Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data
0 citations
On the Performance of Empirical Risk Minimization with Smoothed Data
0 citations
Foundations of Reinforcement Learning and Interactive Decision Making
0 citations
When is Agnostic Reinforcement Learning Statistically Tractable?
0 citations
Efficient Model-Free Exploration in Low-Rank MDPs
1 citation
Convex and Non-convex Optimization Under Generalized Smoothness
10 citations
On the Variance, Admissibility, and Stability of Empirical Risk Minimization
0 citations
On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring
3 citations
Convergence of Adam Under Relaxed Assumptions
11 citations
Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
2 citations
Tight Bounds for -Regret via the Decision-Estimation Coefficient
0 citations
Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making
0 citations
Model-Free Reinforcement Learning with the Decision-Estimation Coefficient
4 citations
On the Complexity of Adversarial Decision Making
4 citations
Rate of convergence of the smoothed empirical Wasserstein distance
3 citations
Damped Online Newton Step for Portfolio Selection
3 citations
Smoothed Online Learning is as Easy as Statistical Learning
3 citations
The Statistical Complexity of Interactive Decision Making
9 citations
On Submodular Contextual Bandits
0 citations
Intrinsic Dimension Estimation Using Wasserstein Distances
2 citations
Deep learning: a statistical viewpoint
203 citations
On the Minimal Error of Empirical Risk Minimization
0 citations
Top- eXtreme Contextual Bandits with Arm Hierarchy
8 citations
Learning the Linear Quadratic Regulator from Nonlinear Observations
4 citations
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.