← Authors

Yevgeny Seldin

27 papers · 2006–2024 · 6 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (6) πŸƒ Academic Marathon (18) πŸŒ‰ Interdisciplinary Bridge 🐝 Cross-Pollinator (13) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (13) πŸ”¬ Deep Specialist (12) 🌱 Topic Pioneer πŸ† Keyword Champion πŸ—ƒοΈ Keyword Collector (87) πŸš€ Conference Pioneer πŸ“ˆ Trend Setter πŸ’Ž Century Club (27) πŸ”₯ Unstoppable (8) ❓ The Questioner

Conferences

NIPS (14) COLT (4) ICML (4) AISTATS (2) JMLR (2) ALT (1)

Top co-authors

Julian Zimmert (6) Saeed Masoudian (4) NicolΓ² Cesa-bianchi (4) Christian Igel (3) Yi-Shan Wu (3) ChloΓ© Rouyer (3) Andres Masegosa (2) Peter Bartlett (2) Tobias Sommer Thune (2) Naftali Tishby (2)

Research topics

Statistics (1)

Keywords

regret bound (19) multi-armed bandit (17) adversarial bandit (7) online learning (7) stochastic bandit (5) delayed feedback (4) adversarial learning (4) tsallis entropy (3) pac-bayesian bound (3) concentration inequality (3) adversarial setting (3) pac-bayesian analysis (3) bandit algorithm (2) kl divergence (2) statistical learning (2) learning theory (2) empirical bernstein (2) online mirror descent (2) pac-bayes bound (2) weighted majority vote (2)

Papers

A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays NIPS 2024
Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss NIPS 2024
Delayed Bandits: When Do Intermediate Observations Help? ICML 2023
Split-kl and PAC-Bayes-split-kl Inequalities for Ternary Random Variables NIPS 2022
A Near-Optimal Best-of-Both-Worlds Algorithm for Online Learning with Feedback Graphs NIPS 2022
A Best-of-Both-Worlds Algorithm for Bandits with Delayed Feedback NIPS 2022
Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits JMLR 2021
Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote NIPS 2021
Improved Analysis of the Tsallis-INF Algorithm in Stochastically Constrained Adversarial Bandits and Stochastic Bandits with Adversarial Corruptions COLT 2021
An Algorithm for Stochastic and Adversarial Bandits with Switching Costs ICML 2021
An Optimal Algorithm for Adversarial Bandits with Arbitrary Delays AISTATS 2020
Tsallis-INF for Decoupled Exploration and Exploitation in Multi-armed Bandits COLT 2020
Second Order PAC-Bayesian Bounds for the Weighted Majority Vote NIPS 2020
Nonstochastic Multiarmed Bandits with Unrestricted Delays NIPS 2019
An Optimal Algorithm for Stochastic and Adversarial Bandits AISTATS 2019
Adaptation to Easy Data in Prediction with Limited Advice NIPS 2018
Factored Bandits NIPS 2018
An Improved Parametrization and Analysis of the EXP3++ Algorithm for Stochastic and Adversarial Bandits COLT 2017
A Strongly Quasiconvex PAC-Bayesian Bound ALT 2017
Prediction with Limited Advice and Multiarmed Bandits with Paid Observations ICML 2014
One Practical Algorithm for Both Stochastic and Adversarial Bandits ICML 2014
PAC-Bayes-Empirical-Bernstein Inequality NIPS 2013
Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions NIPS 2013
Open Problem: Adversarial Multiarmed Bandits with Limited Advice COLT 2013
PAC-Bayesian Analysis of Contextual Bandits NIPS 2011
PAC-Bayesian Analysis of Co-clustering and Beyond JMLR 2010
Information Bottleneck for Non Co-Occurrence Data NIPS 2006