Identifiers
-
name variant
Alexander Rakhlin
0.60 · backfill
Papers (104)
-
Learning with Simulators: No Regret in a Computationally Bounded World
cs.LG · 2026 · author #4
-
The Sample Complexity of Multiclass and Sparse Contextual Bandits
cs.LG · 2026 · author #7
-
Self-Normalized Martingales and Uniform Regret Bounds for Linear Regression
stat.ML · 2026 · author #3
-
End-to-End Efficient RL for Linear Bellman Complete MDPs with Deterministic Transitions
cs.LG · 2026 · author #2
-
Demonstration Experiments
math.ST · 2026 · author #3
-
High-accuracy log-concave sampling with stochastic queries
math.ST · 2026 · author #4
-
High-accuracy sampling for diffusion models and log-concave distributions
cs.LG · 2026 · author #4
-
Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits
cs.LG · 2025 · author #3
-
On the Minimax Regret of Sequential Probability Assignment via Square-Root Entropy
cs.LG · 2025 · author #3
-
Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective
cs.LG · 2025 · author #2
-
Decision Making in Changing Environments: Robustness, Query-Based Learning, and Differential Privacy
cs.LG · 2025 · author #2
-
GaussMark: A Practical Approach for Structural Watermarking of Language Models
cs.CR · 2025 · author #3
-
Refined Risk Bounds for Unbounded Losses via Transductive Priors
stat.ML · 2024 · author #2
-
How Does Variance Shape the Regret in Contextual Bandits?
cs.LG · 2024 · author #3
-
Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
cs.LG · 2024 · author #5
-
Random Latent Exploration for Deep Reinforcement Learning
cs.LG · 2024 · author #4
-
Near-Optimal Learning and Planning in Separated Latent MDPs
cs.LG · 2024 · author #4
-
Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
cs.LG · 2024 · author #6
-
The Power of Resets in Online Reinforcement Learning
cs.LG · 2024 · author #3
-
Online Estimation via Offline Estimation: An Information-Theoretic Framework
stat.ML · 2024 · author #4
-
Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data
cs.LG · 2024 · author #2
-
On the Performance of Empirical Risk Minimization with Smoothed Data
stat.ML · 2024 · author #2
-
Foundations of Reinforcement Learning and Interactive Decision Making
cs.LG · 2023 · author #2
-
When is Agnostic Reinforcement Learning Statistically Tractable?
cs.LG · 2023 · author #3
-
Efficient Model-Free Exploration in Low-Rank MDPs
cs.LG · 2023 · author #4
-
Convex and Non-convex Optimization Under Generalized Smoothness
math.OC · 2023 · author #4
-
On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring
cs.LG · 2023 · author #4
-
Convergence of Adam Under Relaxed Assumptions
math.OC · 2023 · author #2
-
Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
cs.LG · 2023 · author #3
-
Tight Bounds for $\gamma$-Regret via the Decision-Estimation Coefficient
cs.LG · 2023 · author #2
-
Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making
stat.ML · 2023 · author #2
-
Model-Free Reinforcement Learning with the Decision-Estimation Coefficient
cs.LG · 2022 · author #4
-
On the Complexity of Adversarial Decision Making
cs.LG · 2022 · author #2
-
Rate of convergence of the smoothed empirical Wasserstein distance
math.PR · 2022 · author #4
-
Damped Online Newton Step for Portfolio Selection
cs.LG · 2022 · author #2
-
Smoothed Online Learning is as Easy as Statistical Learning
stat.ML · 2022 · author #4
-
The Statistical Complexity of Interactive Decision Making
cs.LG · 2021 · author #4
-
On Submodular Contextual Bandits
cs.LG · 2021 · author #2
-
Intrinsic Dimension Estimation Using Wasserstein Distances
stat.ML · 2021 · author #4
-
Deep learning: a statistical viewpoint
math.ST · 2021 · author #3
-
On the Minimal Error of Empirical Risk Minimization
math.ST · 2021 · author #2
-
Top-$k$ eXtreme Contextual Bandits with Arm Hierarchy
stat.ML · 2021 · author #2
-
Learning the Linear Quadratic Regulator from Nonlinear Observations
cs.LG · 2020 · author #7
-
Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective
cs.LG · 2020 · author #2
-
Fast Mixing of Multi-Scale Langevin Dynamics under the Manifold Hypothesis
stat.ML · 2020 · author #3
-
On Suboptimality of Least Squares with Application to Estimation of Convex Bodies
math.ST · 2020 · author #2
-
Learning nonlinear dynamical systems from a single trajectory
cs.LG · 2020 · author #2
-
Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles
cs.LG · 2020 · author #2
-
Generative Modeling with Denoising Auto-Encoders and Langevin Sampling
stat.ML · 2020 · author #3
-
$\ell_{\infty}$ Vector Contraction for Rademacher Complexity
cs.LG · 2019 · author #2
-
Data Driven Estimation of Stochastic Switched Linear Systems of Unknown Order
eess.SY · 2019 · author #2
-
On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels
math.ST · 2019 · author #2
-
Breast Tumor Cellularity Assessment using Deep Neural Networks
eess.IV · 2019 · author #1
-
Optimality of Maximum Likelihood for Log-Concave Density Estimation and Bounded Convex Regression
math.ST · 2019 · author #3
-
Nonparametric Finite Time LTI System Identification
eess.SY · 2019 · author #2
-
Consistency of Interpolation with Laplace Kernels is a High-Dimensional Phenomenon
stat.ML · 2018 · author #1
-
Near optimal finite time identification of arbitrary linear dynamical systems
cs.SY · 2018 · author #2
-
Just Interpolate: Kernel "Ridgeless" Regression Can Generalize
math.ST · 2018 · author #2
-
Does data interpolation contradict statistical optimality?
stat.ML · 2018 · author #2
-
Angiodysplasia Detection and Localization Using Deep Convolutional Neural Networks
cs.CV · 2018 · author #3
-
Online Learning: Sufficient Statistics and the Burkholder Method
cs.LG · 2018 · author #2
-
Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning
cs.CV · 2018 · author #2
-
Deep Convolutional Neural Networks for Breast Cancer Histology Image Analysis
cs.CV · 2018 · author #1
-
Theory of Deep Learning IIb: Optimization Properties of SGD
cs.LG · 2018 · author #3
-
Size-Independent Sample Complexity of Neural Networks
cs.LG · 2017 · author #2
-
Pediatric Bone Age Assessment Using Deep Convolutional Neural Networks
cs.CV · 2017 · author #2
-
Fisher-Rao Metric, Geometry, and Complexity of Neural Networks
cs.LG · 2017 · author #3
-
Weighted Message Passing and Minimum Energy Flow for Heterogeneous Stochastic Block Models with Side Information
math.ST · 2017 · author #3
-
ZigZag: A new approach to adaptive online learning
cs.LG · 2017 · author #2
-
Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis
cs.LG · 2017 · author #2
-
A Tutorial on Online Supervised Learning with Applications to Node Classification in Social Networks
cs.LG · 2016 · author #1
-
On Detection and Structural Reconstruction of Small-World Random Networks
math.ST · 2016 · author #3
-
Inference via Message Passing on Partially Labeled Stochastic Block Models
math.ST · 2016 · author #3
-
Distributed Estimation of Dynamic Parameters : Regret Analysis
math.OC · 2016 · author #2
-
BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits
cs.LG · 2016 · author #1
-
Finite-time Analysis of the Distributed Detection Problem
cs.SY · 2015 · author #2
-
On Equivalence of Martingale Tail Bounds and Deterministic Regret Inequalities
math.PR · 2015 · author #1
-
Adaptive Online Learning
cs.LG · 2015 · author #2
-
Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints
cs.LG · 2015 · author #1
-
Learning with Square Loss: Localization through Offset Rademacher Complexity
stat.ML · 2015 · author #2
-
Computational and Statistical Boundaries for Submatrix Localization in a Large Noisy Matrix
math.ST · 2015 · author #3
-
Sequential Probability Assignment with Binary Alphabets and Large Classes of Experts
cs.IT · 2015 · author #1
-
Escaping the Local Minima via Simulated Annealing: Optimization of Approximately Convex Functions
math.NA · 2015 · author #4
-
Online Nonparametric Regression with General Loss Functions
stat.ML · 2015 · author #1
-
Online Optimization : Competing with Dynamic Comparators
cs.LG · 2015 · author #2
-
Distributed Detection : Finite-time Analysis and Impact of Network Topology
math.OC · 2014 · author #2
-
Geometric Inference for General High-Dimensional Linear Inverse Problems
math.ST · 2014 · author #3
-
On Zeroth-Order Stochastic Convex Optimization via Random Walks
cs.LG · 2014 · author #3
-
Online Nonparametric Regression
stat.ML · 2014 · author #1
-
Optimization, Learning, and Games with Predictable Sequences
cs.LG · 2013 · author #1
-
Online Learning of Dynamic Parameters in Social Networks
math.OC · 2013 · author #2
-
Efficient Sampling from Time-Varying Log-Concave Distributions
stat.ML · 2013 · author #2
-
Empirical entropy, minimax regret and minimax risk
math.ST · 2013 · author #1
-
Competing With Strategies
stat.ML · 2013 · author #2
-
Online Learning with Predictable Sequences
stat.ML · 2012 · author #1
-
Relax and Localize: From Value to Algorithms
cs.LG · 2012 · author #1
-
Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization
cs.LG · 2011 · author #1
-
No Internal Regret via Neighborhood Watch
cs.LG · 2011 · author #2
-
Stochastic convex optimization with bandit feedback
math.OC · 2011 · author #5
-
Online Learning: Stochastic and Constrained Adversaries
stat.ML · 2011 · author #1
-
Online Learning: Beyond Regret
stat.ML · 2010 · author #1
-
Information-based complexity, feedback and dynamics in convex programming
cs.IT · 2010 · author #2
-
Online Learning via Sequential Complexities
cs.LG · 2010 · author #1
-
A Stochastic View of Optimal Regret through Minimax Duality
cs.LG · 2009 · author #4
Mentions
-
2410.21621
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2505.20268
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2502.10581
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2503.17823
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2407.13755
#4 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2205.02128
#4 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2501.14928
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2501.13941
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2410.05117
#5 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2410.12713
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2406.07920
#4 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2405.21046
#6 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2404.15417
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2404.10122
#4 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2403.17091
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2302.05430
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2307.03997
#4 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2402.14987
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2312.16730
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2304.13972
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2306.01264
#4 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2310.06113
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2211.14250
#4 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2303.03327
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2112.13487
#4 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2305.00684
#4 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2304.05889
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2002.00107
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2206.13063
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2202.04690
#4 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2106.04018
#4 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2202.07574
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2112.02165
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2103.09177
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2102.12066
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2102.07800
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2010.03799
#7 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2010.03104
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1908.10292
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1808.00387
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1711.01530
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1709.03907
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1604.06474
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1502.06134
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1502.01988
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1404.4408
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2002.04926
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2006.11166
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2006.04046
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1909.04617
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2004.14681
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1903.05315
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1508.05170
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1712.06541
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1911.06468
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1905.01743
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1804.08024
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1803.01207
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1812.11167
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1712.05053
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1806.09471
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1802.00752
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1803.07617
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1801.02254
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1308.1147
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1702.03849
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1704.04010
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1608.09014
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1603.06923
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1603.00576
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1602.02196
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1510.03925
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1503.01212
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1109.5647
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1501.07340
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1501.06598
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1501.06225
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1409.8606
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1006.1138
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1208.3728
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1402.2667
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1402.2594
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1311.1869
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1310.0432
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1309.5977
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1302.2672
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1204.0870
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1108.6088
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1104.5070
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1011.3168
#1 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
0903.5328
#4 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2603.23461
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2603.06941
#3 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
2606.13576
#4 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1510.03925
#1 · backfill · confidence 0.70
Alexander Rakhlin
-
1902.01848
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1812.01251
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1512.09311
#2 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1501.07242
#4 · arxiv_oai · confidence 0.70
Alexander Rakhlin
-
1107.1744
#5 · arxiv_oai · confidence 0.70
Alexander Rakhlin