← Authors

Gergely Neu

46 papers · 2010–2025 · 7 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (7) πŸŒ‰ Interdisciplinary Bridge 🐝 Cross-Pollinator (9) πŸƒ Academic Marathon (15) πŸ—ΊοΈ Taxonomy Completionist (14) 🧭 Keyword Pioneer πŸ† Keyword Champion (4) πŸ”¬ Deep Specialist (14) πŸ—ƒοΈ Keyword Collector (136) πŸš€ Conference Pioneer πŸ“ˆ Trend Setter πŸ’Ž Century Club (46) πŸ”₯ Unstoppable (14) ⚑ Prolific Year (6)

Conferences

NIPS (15) COLT (12) AISTATS (7) ALT (7) ICML (3) JMLR (1) L4DC (1)

Top co-authors

Gabor Lugosi (5) Matteo Papini (5) Julia Olkhovskaya (5) Lorenzo Rosasco (3) Michal Valko (3) Germano Gabbianelli (3) Nneka Okolo (3) Ludovic Schwartz (3) Luca Viano (2) Antoine Moulin (2)

Research topics

Probability (1)

Keywords

regret bound (19) online learning (14) contextual bandit (6) combinatorial optimization (6) markov decision process (6) regret minimization (5) multi-armed bandit (5) bandit feedback (4) markov decision processes (3) reinforcement learning (3) stochastic gradient descent (3) linear function approximation (3) adversarial learning (3) relative entropy policy search (2) policy optimization (2) expert advice (2) bandit setting (2) learning theory (2) online prediction (2) dynamic programming (2)

Papers

Offline RL via Feature-Occupancy Gradient Ascent AISTATS 2025
Online-to-PAC generalization bounds under graph-mixing dependencies AISTATS 2025
Generalization bounds for mixing processes via delayed online-to-PAC conversions ALT 2025
Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning COLT 2025
Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently NIPS 2024
Offline Primal-Dual Reinforcement Learning for Linear MDPs AISTATS 2024
Dealing With Unbounded Gradients in Stochastic Saddle-point Optimization ICML 2024
Importance-Weighted Offline Learning Done Right ALT 2024
Adversarial Contextual Bandits Go Kernelized ALT 2024
Optimistic Information Directed Sampling COLT 2024
Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization ALT 2023
Optimistic Planning by Regularized Dynamic Programming ICML 2023
Online Learning with Off-Policy Feedback ALT 2023
Conference on Learning Theory 2023: Preface COLT 2023
First- and Second-Order Bounds for Adversarial Linear Contextual Bandits NIPS 2023
Nonstochastic Contextual Combinatorial Bandits AISTATS 2023
Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits NIPS 2022
Generalization Bounds via Convex Analysis COLT 2022
Proximal Point Imitation Learning NIPS 2022
Logistic Q-Learning AISTATS 2021
Online learning in MDPs with linear function approximation and bandit feedback. NIPS 2021
Information-Theoretic Generalization Bounds for Stochastic Gradient Descent COLT 2021
Faster saddle-point optimization for solving large-scale Markov decision processes L4DC 2020
A Unifying View of Optimism in Episodic Reinforcement Learning NIPS 2020
Algorithmic Learning Theory 2020: Preface ALT 2020
Fast Rates for Online Prediction with Abstention COLT 2020
Efficient and robust algorithms for adversarial linear contextual bandits COLT 2020
Bandit Principal Component Analysis COLT 2019
Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates NIPS 2019
Beating SGD Saturation with Tail-Averaging and Minibatching NIPS 2019
Online Influence Maximization with Local Observations ALT 2019
Iterate Averaging as Regularization for Stochastic Gradient Descent COLT 2018
Fast rates for online learning in Linearly Solvable Markov Decision Processes COLT 2017
Algorithmic Stability and Hypothesis Complexity ICML 2017
Boltzmann Exploration Done Right NIPS 2017
Online Learning with Noisy Side Observations AISTATS 2016
Importance Weighting Without Importance Weights: An Efficient Algorithm for Combinatorial Semi-Bandits JMLR 2016
Explore no more: Improved high-probability regret bounds for non-stochastic bandits NIPS 2015
First-order regret bounds for combinatorial semi-bandits COLT 2015
Efficient learning by implicit exploration in bandit problems with side observations NIPS 2014
Exploiting easy data in online optimization NIPS 2014
Online combinatorial optimization with stochastic decision sets and adversarial losses NIPS 2014
Online learning in episodic Markovian decision processes by relative entropy policy search NIPS 2013
Prediction by random-walk perturbation COLT 2013
The adversarial stochastic shortest path problem with unknown transition probabilities AISTATS 2012
Online Markov Decision Processes under Bandit Feedback NIPS 2010