Csaba Szepesv\'ari
Identifiers
- name variant Csaba Szepesv\'ari 0.60 · backfill
Papers (36)
- Sharper Guarantees for Misspecified Kernelized Bandit Optimization cs.LG · 2026 · author #2
- To See the Unseen: on the Generalization Ability of Transformers in Symbolic Reasoning cs.AI · 2026 · author #4
- Revisiting Subgradient Dominance in Robust MDPs: Counterexamples, Hardness, and Sufficient Conditions math.OC · 2026 · author #5
- Learning What to Recommend: Minimax Optimal Simple Regret in Logistic Bandits cs.LG · 2026 · author #5
- Eluder dimension: localise it! cs.LG · 2026 · author #5
- Learning to Reason Efficiently with Discounted Reinforcement Learning cs.LG · 2025 · author #4
- Trajectory Data Suffices for Statistically Efficient Policy Evaluation in Fixed-Horizon Offline RL with Linear $q^\pi$-Realizability and Concentrability cs.LG · 2025 · author #2
- Exploration via linearly perturbed loss minimisation cs.LG · 2023 · author #4
- Distribution-Dependent Analysis of Gibbs-ERM Principle cs.LG · 2019 · author #3
- Online Algorithm for Unsupervised Sensor Selection cs.LG · 2019 · author #3
- Online Learning to Rank with Features stat.ML · 2018 · author #3
- LeapsAndBounds: A Method for Approximately Optimal Algorithm Configuration cs.LG · 2018 · author #3
- Linear Stochastic Approximation: Constant Step-Size and Iterate Averaging cs.LG · 2017 · author #2
- A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds cs.LG · 2017 · author #3
- Mixing time estimation in reversible Markov chains from a single sample path math.ST · 2017 · author #5
- Structured Best Arm Identification with Fixed Confidence cs.LG · 2017 · author #3
- Bernoulli Rank-$1$ Bandits for Click Feedback cs.LG · 2017 · author #3
- Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities cs.LG · 2017 · author #4
- SDP Relaxation with Randomized Rounding for Energy Disaggregation cs.LG · 2016 · author #3
- Multiclass Classification Calibration Functions stat.ML · 2016 · author #2
- Max-affine estimators for convex stochastic programming math.OC · 2016 · author #3
- Chaining Bounds for Empirical Risk Minimization stat.ML · 2016 · author #3
- Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models stat.ML · 2016 · author #2
- Conservative Bandits stat.ML · 2016 · author #4
- DCM Bandits: Learning to Rank with Multiple Clicks cs.LG · 2016 · author #3
- Online Learning with Gaussian Payoffs and Side Observations stat.ML · 2015 · author #3
- Fast Cross-Validation for Incremental Learning stat.ML · 2015 · author #3
- Mixing Time Estimation in Reversible Markov Chains from a Single Sample Path cs.LG · 2015 · author #3
- Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control cs.LG · 2015 · author #5
- Optimal Resource Allocation with Semi-Bandit Feedback cs.LG · 2014 · author #3
- Adaptive Monte Carlo via Bandit Allocation cs.AI · 2014 · author #4
- Online Learning under Delayed Feedback cs.LG · 2013 · author #3
- A Randomized Mirror Descent Algorithm for Large Scale Multiple Kernel Learning cs.LG · 2012 · author #3
- Non-trivial two-armed partial-monitoring games are bandits cs.LG · 2011 · author #3
- Toward a Classification of Finite Partial-Monitoring Games cs.GT · 2011 · author #4
- Estimation of R\'enyi Entropy and Mutual Information Based on Generalized Nearest-Neighbor Graphs stat.ML · 2010 · author #3
Mentions
- 1510.08108 #3 · backfill · confidence 0.70 Csaba Szepesv\'ari
- 2311.07565 #4 · arxiv_oai · confidence 0.70 Csaba Szepesv\'ari
- 1709.04073 #2 · arxiv_oai · confidence 0.70 Csaba Szepesv\'ari
- 1609.06331 #3 · arxiv_oai · confidence 0.70 Csaba Szepesv\'ari
- 1507.00066 #3 · backfill · confidence 0.70 Csaba Szepesv\'ari
- 1506.02903 #3 · backfill · confidence 0.70 Csaba Szepesv\'ari
- 1506.02632 #5 · backfill · confidence 0.70 Csaba Szepesv\'ari
- 2510.03494 #2 · arxiv_oai · confidence 0.70 Csaba Szepesv\'ari
- 1406.3840 #3 · backfill · confidence 0.70 Csaba Szepesv\'ari
- 1405.3318 #4 · backfill · confidence 0.70 Csaba Szepesv\'ari
- 2601.21167 #5 · arxiv_oai · confidence 0.70 Csaba Szepesv\'ari
- 1306.0686 #3 · backfill · confidence 0.70 Csaba Szepesv\'ari
- 2510.23486 #4 · arxiv_oai · confidence 0.70 Csaba Szepesv\'ari
- 1205.0288 #3 · backfill · confidence 0.70 Csaba Szepesv\'ari
- 1108.4961 #3 · backfill · confidence 0.70 Csaba Szepesv\'ari
- 1102.2041 #4 · backfill · confidence 0.70 Csaba Szepesv\'ari
- 1003.1954 #3 · backfill · confidence 0.70 Csaba Szepesv\'ari
Frequent Coauthors
- Andr\'as Gy\"orgy 12 shared papers
- Alex Ayoub 5 shared papers
- Tor Lattimore 4 shared papers
- Pooria Joulani 3 shared papers
- Alireza Bakhtiari 2 shared papers
- Andr\'as Antos 2 shared papers
- Aryeh Kontorovich 2 shared papers
- Bernardo \'Avila Pires 2 shared papers
- Branislav Kveton 2 shared papers
- Dale Schuurmans 2 shared papers
- Daniel Hsu 2 shared papers
- David Janz 2 shared papers
- D\'avid P\'al 2 shared papers
- G\'abor Bal\'azs 2 shared papers
- G\'abor Bart\'ok 2 shared papers
- Ruitong Huang 2 shared papers
- Shuai Liu 2 shared papers
- Sumeet Katariya 2 shared papers
- Yifan Wu 2 shared papers
- Zheng Wen 2 shared papers