← Authors

Csaba Szepesvári

158 papers · 2007–2025 · 11 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (11) 🗺️ Taxonomy Completionist (48) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (10) 🏃 Academic Marathon (18) 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (8) 🌉 Interdisciplinary Bridge 🏠 Conference Loyalist (56) 🌟 Keyword Trendsetter Combo (3) 🌱 Topic Pioneer 👑 Triple Crown 🔬 Deep Specialist (11) 🏆 Keyword Champion (3) 🧬 Topic Evolution 🏆 Grand Slam 🤝 Dynamic Duo (33) ❓ The Questioner (3) 📈 Trend Setter 🚀 Conference Pioneer 🔥 Unstoppable (19) ⚡ Prolific Year (12) 💎 Century Club (158) 🗃️ Keyword Collector (201)

Conferences

NIPS (56) ICML (37) AISTATS (26) COLT (14) ALT (7) JMLR (6) UAI (4) ICLR (3) IJCAI (3) AAAI (1) L4DC (1)

Top co-authors

András György (33) Tor Lattimore (22) Branislav Kveton (16) Dale Schuurmans (15) Gellert Weisz (13) Bo Dai (11) Jincheng Mei (10) Yasin Abbasi-Yadkori (10) Mohammad Ghavamzadeh (9) Mengdi Wang (8)

Keywords

regret bound (49) online learning (31) multi-armed bandit (25) markov decision process (20) stochastic optimization (20) reinforcement learning (16) sample complexity (13) linear function approximation (12) policy iteration (9) regret analysis (8) partial monitoring (8) function approximation (8) regret minimization (7) online algorithm (7) thompson sampling (7) value function (7) contextual bandit (7) learning to rank (6) policy optimization (6) stochastic bandit (6)

Papers

Thompson Sampling for Bandit Convex Optimisation COLT 2025
Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits NIPS 2024
To Believe or Not to Believe Your LLM: Iterative Prompting for Estimating Epistemic Uncertainty NIPS 2024
Ensemble sampling for linear bandits: small ensembles suffice NIPS 2024
Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates NIPS 2024
Switching the Loss Reduces the Cost in Batch Reinforcement Learning ICML 2024
Exploration via linearly perturbed loss minimisation AISTATS 2024
Stochastic Gradient Descent for Gaussian Processes Done Right ICLR 2024
Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^\pi$-Realizability and Concentrability NIPS 2024
Confident Natural Policy Gradient for Local Planning in $q_\pi$-realizable Constrained MDPs NIPS 2024
Context-lumpable stochastic bandits NIPS 2023
Exponential Hardness of Reinforcement Learning with Linear Function Approximation COLT 2023
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice ICML 2023
Revisiting Simple Regret: Fast Rates for Returning a Good Arm ICML 2023
Stochastic Gradient Succeeds for Bandits ICML 2023
The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation ICML 2023
Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning AISTATS 2023
Online RL in Linearly $q^\pi$-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore NIPS 2023
Regret Minimization via Saddle Point Optimization NIPS 2023
Ordering-based Conditions for Global Convergence of Policy Gradient Methods NIPS 2023
Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL NIPS 2023
Optimistic Exploration with Learned Features Provably Solves Markov Decision Processes with Neural Dynamics ICLR 2023
The Role of Baselines in Policy Gradient Optimization NIPS 2022
A free lunch from the noise: Provable and practical exploration for representation learning UAI 2022
Towards painless policy optimization for constrained MDPs UAI 2022
When Is Partially Observable Reinforcement Learning Not Scary? COLT 2022
Efficient local planning with linear function approximation ALT 2022
TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions ALT 2022
The Curse of Passive Data Collection in Batch Reinforcement Learning AISTATS 2022
Faster Rates, Adaptive Algorithms, and Finite-Time Bounds for Linear Composition Optimization and Gradient TD Learning AISTATS 2022
Confident Least Square Value Iteration with Local Access to a Simulator AISTATS 2022
Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization NIPS 2022
Confident Approximate Policy Iteration for Efficient Local Planning in $q^\pi$-realizable MDPs NIPS 2022
Sample-Efficient Reinforcement Learning of Partially Observable Markov Games NIPS 2022
Near-Optimal Sample Complexity Bounds for Constrained MDPs NIPS 2022
On the Optimality of Batch Policy Optimization Algorithms ICML 2021
On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method NIPS 2021
Understanding the Effect of Stochasticity in Policy Optimization NIPS 2021
No Regrets for Learning the Prior in Bandits NIPS 2021
On the Role of Optimization in Double Descent: A Least Squares Study NIPS 2021
Online Sparse Reinforcement Learning AISTATS 2021
Adaptive Approximate Policy Iteration AISTATS 2021
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting AISTATS 2021
Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions ALT 2021
Asymptotically Optimal Information-Directed Sampling COLT 2021
**Paper retracted by author request (see pdf for retraction notice from the authors)** Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping COLT 2021
On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function COLT 2021
Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes COLT 2021
Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient ICML 2021
Bootstrapping Fitted Q-Evaluation for Off-Policy Inference ICML 2021
A Distribution-dependent Analysis of Meta Learning ICML 2021
Meta-Thompson Sampling ICML 2021
Improved Regret Bound and Experience Replay in Regularized Policy Iteration ICML 2021
Leveraging Non-uniformity in First-order Non-convex Optimization ICML 2021
Tighter Risk Certificates for Neural Networks JMLR 2021
A simpler approach to accelerated optimization: iterative averaging meets optimism ICML 2020
Online Algorithm for Unsupervised Sequential Selection with Contextual Information NIPS 2020
Differentiable Meta-Learning of Bandit Policies NIPS 2020
Variational Policy Gradient Method for Reinforcement Learning with General Utilities NIPS 2020
CoinDICE: Off-Policy Confidence Interval Estimation NIPS 2020
Randomized Exploration in Generalized Linear Bandits AISTATS 2020
Adaptive Exploration in Linear Contextual Bandit AISTATS 2020
Model Selection in Contextual Stochastic Bandit Problems NIPS 2020
PAC-Bayes Analysis Beyond the Usual Bounds NIPS 2020
ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool NIPS 2020
Efficient Planning in Large MDPs with Weak Linear Function Approximation NIPS 2020
Escaping the Gravitational Pull of Softmax NIPS 2020
Model-Based Reinforcement Learning with Value-Targeted Regression L4DC 2020
Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers JMLR 2020
On the Global Convergence Rates of Softmax Policy Gradient Methods ICML 2020
Learning with Good Feature Representations in Bandits and in RL with a Generative Model ICML 2020
Exploration by Optimisation in Partial Monitoring COLT 2020
Model-Based Reinforcement Learning with Value-Targeted Regression ICML 2020
Behaviour Suite for Reinforcement Learning ICLR 2020
Online Algorithm for Unsupervised Sensor Selection AISTATS 2019
Think out of the "Box": Generically-Constrained Asynchronous Composite Optimization and Hedging NIPS 2019
Detecting Overfitting via Adversarial Examples NIPS 2019
Perturbed-History Exploration in Stochastic Multi-Armed Bandits IJCAI 2019
An Information-Theoretic Approach to Minimax Regret in Partial Monitoring COLT 2019
POLITEX: Regret Bounds for Policy Iteration using Expert Prediction ICML 2019
Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits ICML 2019
Perturbed-History Exploration in Stochastic Linear Bandits UAI 2019
BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback UAI 2019
Model-Free Linear Quadratic Control via Reduction to Expert Prediction AISTATS 2019
An Exponential Tail Bound for the Deleted Estimate AAAI 2019
An Exponential Efron-Stein Inequality for $L_q$ Stable Learning Rules ALT 2019
Cleaning up the neighborhood: A full classification for adversarial partial monitoring ALT 2019
Online Learning to Rank with Features ICML 2019
Distribution-Dependent Analysis of Gibbs-ERM Principle COLT 2019
CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration ICML 2019
LeapsAndBounds: A Method for Approximately Optimal Algorithm Configuration ICML 2018
Bandits with Delayed, Aggregated Anonymous Feedback ICML 2018
Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers ICML 2018
TopRank: A practical algorithm for online stochastic ranking NIPS 2018
PAC-Bayes bounds for stable algorithms with instance-dependent priors NIPS 2018
Linear Stochastic Approximation: How Far Does Constant Step-Size and Iterate Averaging Go? AISTATS 2018
Following the Leader and Fast Rates in Online Linear Prediction: Curved Constraint Sets and Other Regularities JMLR 2017
A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds ALT 2017
Stochastic Rank-1 Bandits AISTATS 2017
The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits AISTATS 2017
Unsupervised Sequential Sensor Acquisition AISTATS 2017
Multi-view Matrix Factorization for Linear Dynamical System Estimation NIPS 2017
Structured Best Arm Identification with Fixed Confidence ALT 2017
Online Learning to Rank in Stochastic Click Models ICML 2017
Bernoulli Rank-1 Bandits for Click Feedback IJCAI 2017
Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities NIPS 2016
(Bandit) Convex Optimization with Biased Noisy Gradient Oracles AISTATS 2016
Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models COLT 2016
Regularized Policy Iteration with Nonparametric Function Spaces JMLR 2016
DCM Bandits: Learning to Rank with Multiple Clicks ICML 2016
Conservative Bandits ICML 2016
Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control ICML 2016
Shifting Regret, Mirror Descent, and Matrices ICML 2016
SDP Relaxation with Randomized Rounding for Energy Disaggregation NIPS 2016
Exploiting Symmetries to Construct Efficient MCMC Algorithms With an Application to SLAM AISTATS 2015
Fast Cross-Validation for Incremental Learning IJCAI 2015
Online Learning with Gaussian Payoffs and Side Observations NIPS 2015
Linear Multi-Resource Allocation with Semi-Bandit Feedback NIPS 2015
Mixing Time Estimation in Reversible Markov Chains from a Single Sample Path NIPS 2015
Deterministic Independent Component Analysis ICML 2015
Cascading Bandits: Learning to Rank in the Cascade Model ICML 2015
On Identifying Good Options under Combinatorially Structured Feedback in Finite Noisy Environments ICML 2015
Near-optimal max-affine estimators for convex regression AISTATS 2015
Combinatorial Cascading Bandits NIPS 2015
Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits AISTATS 2015
Toward Minimax Off-policy Value Estimation AISTATS 2015
Universal Option Models NIPS 2014
Online Learning in Markov Decision Processes with Changing Cost Sequences ICML 2014
A Finite-Sample Generalization Bound for Semiparametric Regression: Partially Linear Models AISTATS 2014
Adaptive Monte Carlo via Bandit Allocation ICML 2014
Online Learning with Costly Features and Labels NIPS 2013
Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions NIPS 2013
A Randomized Mirror Descent Algorithm for Large Scale Multiple Kernel Learning ICML 2013
Online Learning under Delayed Feedback ICML 2013
Cost-sensitive Multiclass Classification Risk Bounds ICML 2013
Characterizing the Representer Theorem ICML 2013
Online-to-Confidence-Set Conversions and Application to Sparse Stochastic Bandits AISTATS 2012
The adversarial stochastic shortest path problem with unknown transition probabilities AISTATS 2012
Deep Representations and Codes for Image Auto-Annotation NIPS 2012
Regret Bounds for the Adaptive Control of Linear Quadratic Systems COLT 2011
Improved Algorithms for Linear Stochastic Bandits NIPS 2011
-Armed Bandits JMLR 2011
Agnostic KWIK learning and efficient approximate reinforcement learning COLT 2011
Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments COLT 2011
Error Propagation for Approximate Policy and Value Iteration NIPS 2010
Online Markov Decision Processes under Bandit Feedback NIPS 2010
Parametric Bandits: The Generalized Linear Case NIPS 2010
A Markov-Chain Monte Carlo Approach to Simultaneous Localization and Mapping AISTATS 2010
Estimation of Rényi Entropy and Mutual Information Based on Generalized Nearest-Neighbor Graphs NIPS 2010
REGO: Rank-based Estimation of Renyi Information using Euclidean Graph Optimization AISTATS 2010
Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation NIPS 2009
A General Projection Property for Distribution Families NIPS 2009
Multi-Step Dyna Planning for Policy Evaluation and Control NIPS 2009
Finite-Time Bounds for Fitted Value Iteration JMLR 2008
Regularized Policy Iteration NIPS 2008
A Convergent $O(n)$ Temporal-difference Algorithm for Off-policy Learning with Linear Function Approximation NIPS 2008
Online Optimization in X-Armed Bandits NIPS 2008
Fitted Q-iteration in continuous action-space MDPs NIPS 2007