Gergely Neu

According to our database, Gergely Neu authored at least 70 papers between 2007 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2025

Linear Bandits with Non-i.i.d. Noise.

Baptiste Abélès, Eugenio Clerico, Hamish Flynn, Gergely Neu

CoRR, May, 2025

Inverse Q-Learning Done Right: Offline Imitation Learning in Q^π-Realizable MDPs.

Antoine Moulin, Gergely Neu, Luca Viano

CoRR, May, 2025

Distances for Markov chains from sample streams.

Sergio Calo, Anders Jonsson, Gergely Neu, Ludovic Schwartz, Javier Segovia-Aguas

CoRR, May, 2025

Confidence Sequences for Generalized Linear Models via Regret Analysis.

Eugenio Clerico, Hamish Flynn, Wojciech Kotlowski, Gergely Neu

CoRR, April, 2025

Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning.

Antoine Moulin, Gergely Neu, Luca Viano

Proceedings of the Thirty Eighth Annual Conference on Learning Theory, 2025

Generalization bounds for mixing processes via delayed online-to-PAC conversions.

Baptiste Abélès, Eugenio Clerico, Gergely Neu

Proceedings of the International Conference on Algorithmic Learning Theory, 2025

Offline RL via Feature-Occupancy Gradient Ascent.

Gergely Neu, Nneka Okolo

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

Online-to-PAC generalization bounds under graph-mixing dependencies.

Baptiste Abélès, Gergely Neu, Eugenio Clerico

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

On the Hardness of Learning from Censored and Nonstationary Demand.

Gábor Lugosi, Mihalis G. Markakis, Gergely Neu

INFORMS J. Optim., 2024

Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently.

Sergio Calo, Anders Jonsson, Gergely Neu, Ludovic Schwartz, Javier Segovia-Aguas

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Dealing With Unbounded Gradients in Stochastic Saddle-point Optimization.

Gergely Neu, Nneka Okolo

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Optimistic Information Directed Sampling.

Gergely Neu, Matteo Papini, Ludovic Schwartz

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

Adversarial Contextual Bandits Go Kernelized.

Gergely Neu, Julia Olkhovskaya, Sattar Vakili

Proceedings of the International Conference on Algorithmic Learning Theory, 2024

Importance-Weighted Offline Learning Done Right.

Germano Gabbianelli, Gergely Neu, Matteo Papini

Proceedings of the International Conference on Algorithmic Learning Theory, 2024

Offline Primal-Dual Reinforcement Learning for Linear MDPs.

Germano Gabbianelli, Gergely Neu, Matteo Papini, Nneka Okolo

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

Online-to-PAC Conversions: Generalization Bounds via Regret Analysis.

Gábor Lugosi, Gergely Neu

CoRR, 2023

First- and Second-Order Bounds for Adversarial Linear Contextual Bandits.

Julia Olkhovskaya, Jack J. Mayo, Tim van Erven, Gergely Neu, Chen-Yu Wei

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Optimistic Planning by Regularized Dynamic Programming.

Antoine Moulin, Gergely Neu

Proceedings of the International Conference on Machine Learning, 2023

Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization.

Gergely Neu, Nneka Okolo

Proceedings of the International Conference on Algorithmic Learning Theory, 2023

Online Learning with Off-Policy Feedback.

Germano Gabbianelli, Gergely Neu, Matteo Papini

Proceedings of the International Conference on Algorithmic Learning Theory, 2023

Nonstochastic Contextual Combinatorial Bandits.

Lukas Zierahn, Dirk van der Hoeven, Nicolò Cesa-Bianchi, Gergely Neu

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Sufficient Exploration for Convex Q-learning.

Fan Lu, Prashant G. Mehta, Sean P. Meyn, Gergely Neu

CoRR, 2022

Proximal Point Imitation Learning.

Luca Viano, Angeliki Kamoutsi, Gergely Neu, Igor Krawczuk, Volkan Cevher

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits.

Gergely Neu, Julia Olkhovskaya, Matteo Papini, Ludovic Schwartz

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Generalization Bounds via Convex Analysis.

Gábor Lugosi, Gergely Neu

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

Convex Analytic Theory for Convex Q-Learning.

Fan Lu, Prashant G. Mehta, Sean P. Meyn, Gergely Neu

Proceedings of the 61st IEEE Conference on Decision and Control, 2022

2021

Robustness and risk management via distributional dynamic programming.

Mastane Achab, Gergely Neu

CoRR, 2021

Learning to maximize global influence from local observations.

Gábor Lugosi, Gergely Neu, Julia Olkhovskaya

CoRR, 2021

Online learning in MDPs with linear function approximation and bandit feedback.

Gergely Neu, Julia Olkhovskaya

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Information-Theoretic Generalization Bounds for Stochastic Gradient Descent.

Gergely Neu

Proceedings of the Conference on Learning Theory, 2021

Convex Q-Learning.

Fan Lu, Prashant G. Mehta, Sean P. Meyn, Gergely Neu

Proceedings of the 2021 American Control Conference, 2021

Logistic Q-Learning.

Joan Bas-Serrano, Sebastian Curi, Andreas Krause, Gergely Neu

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

A Unifying View of Optimism in Episodic Reinforcement Learning.

Gergely Neu, Ciara Pike-Burke

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Faster saddle-point optimization for solving large-scale Markov decision processes.

Joan Bas-Serrano, Gergely Neu

Proceedings of the 2nd Annual Conference on Learning for Dynamics and Control, 2020

Fast Rates for Online Prediction with Abstention.

Gergely Neu, Nikita Zhivotovskiy

Proceedings of the Conference on Learning Theory, 2020

Efficient and robust algorithms for adversarial linear contextual bandits.

Gergely Neu, Julia Olkhovskaya

Proceedings of the Conference on Learning Theory, 2020

Algorithmic Learning Theory 2020: Preface.

Aryeh Kontorovich, Gergely Neu

Proceedings of the Algorithmic Learning Theory, 2020

2019

Potential and pitfalls of Multi-Armed Bandits for decentralized Spatial Reuse in WLANs.

Francesc Wilhelmi, Sergio Barrachina-Muñoz, Boris Bellalta, Cristina Cano, Anders Jonsson, Gergely Neu

J. Netw. Comput. Appl., 2019

Collaborative Spatial Reuse in wireless networks via selfish Multi-Armed Bandits.

Francesc Wilhelmi, Cristina Cano, Gergely Neu, Boris Bellalta, Anders Jonsson, Sergio Barrachina-Muñoz

Ad Hoc Networks, 2019

Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates.

Carlos Riquelme, Hugo Penedones, Damien Vincent, Hartmut Maennel, Sylvain Gelly, Timothy A. Mann, André Barreto, Gergely Neu

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Beating SGD Saturation with Tail-Averaging and Minibatching.

Nicole Mücke, Gergely Neu, Lorenzo Rosasco

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Bandit Principal Component Analysis.

Wojciech Kotlowski, Gergely Neu

Proceedings of the Conference on Learning Theory, 2019

Online Influence Maximization with Local Observations.

Gábor Lugosi, Gergely Neu, Julia Olkhovskaya

Proceedings of the Algorithmic Learning Theory, 2019

2018

Wireless Optimisation via Convex Bandits: Unlicensed LTE/WiFi Coexistence.

Cristina Cano, Gergely Neu

Proceedings of the 2018 Workshop on Network Meets AI & ML, 2018

Iterate Averaging as Regularization for Stochastic Gradient Descent.

Gergely Neu, Lorenzo Rosasco

Proceedings of the Conference On Learning Theory, 2018

2017

On the Hardness of Inventory Management with Censored Demand Data.

Gábor Lugosi, Mihalis G. Markakis, Gergely Neu

CoRR, 2017

A unified view of entropy-regularized Markov decision processes.

Gergely Neu, Anders Jonsson, Vicenç Gómez

CoRR, 2017

Boltzmann Exploration Done Right.

Nicolò Cesa-Bianchi, Claudio Gentile, Gergely Neu, Gábor Lugosi

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Algorithmic Stability and Hypothesis Complexity.

Tongliang Liu, Gábor Lugosi, Gergely Neu, Dacheng Tao

Proceedings of the 34th International Conference on Machine Learning, 2017

Fast rates for online learning in Linearly Solvable Markov Decision Processes.

Gergely Neu, Vicenç Gómez

Proceedings of the 30th Conference on Learning Theory, 2017

2016

Importance Weighting Without Importance Weights: An Efficient Algorithm for Combinatorial Semi-Bandits.

Gergely Neu, Gábor Bartók

J. Mach. Learn. Res., 2016

Online learning with Erdos-Renyi side-observation graphs.

Tomás Kocák, Gergely Neu, Michal Valko

Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence, 2016

Online Learning with Noisy Side Observations.

Tomás Kocák, Gergely Neu, Michal Valko

Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016

2015

Random-Walk Perturbations for Online Combinatorial Optimization.

Luc Devroye, Gábor Lugosi, Gergely Neu

IEEE Trans. Inf. Theory, 2015

Explore no more: Improved high-probability regret bounds for non-stochastic bandits.

Gergely Neu

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

First-order regret bounds for combinatorial semi-bandits.

Gergely Neu

Proceedings of The 28th Conference on Learning Theory, 2015

2014

Near-Optimal Rates for Limited-Delay Universal Lossy Source Coding.

András György, Gergely Neu

IEEE Trans. Inf. Theory, 2014

Online Markov Decision Processes Under Bandit Feedback.

Gergely Neu, András György, Csaba Szepesvári, András Antos

IEEE Trans. Autom. Control., 2014

Online learning in MDPs with side information.

Yasin Abbasi-Yadkori, Gergely Neu

CoRR, 2014

Exploiting easy data in online optimization.

Amir Sani, Gergely Neu, Alessandro Lazaric

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Online combinatorial optimization with stochastic decision sets and adversarial losses.

Gergely Neu, Michal Valko

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Efficient learning by implicit exploration in bandit problems with side observations.

Tomás Kocák, Gergely Neu, Michal Valko, Rémi Munos

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

2013

Online tanulás nemstacionárius Markov döntési folyamatokban

Gergely Neu

PhD thesis, 2013

Online learning in episodic Markovian decision processes by relative entropy policy search.

Alexander Zimin, Gergely Neu

Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Prediction by random-walk perturbation.

Luc Devroye, Gábor Lugosi, Gergely Neu

Proceedings of the COLT 2013, 2013

An Efficient Algorithm for Learning with Semi-bandit Feedback.

Gergely Neu, Gábor Bartók

Proceedings of the Algorithmic Learning Theory - 24th International Conference, 2013

2012

The adversarial stochastic shortest path problem with unknown transition probabilities.

Gergely Neu, András György, Csaba Szepesvári

Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, 2012

2010

The Online Loop-free Stochastic Shortest-Path Problem.

Gergely Neu, András György, Csaba Szepesvári

Proceedings of the COLT 2010, 2010

2009

Training parsers by inverse reinforcement learning.

Gergely Neu, Csaba Szepesvári

Mach. Learn., 2009

2007

Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods.

Gergely Neu, Csaba Szepesvári

Proceedings of the UAI 2007, 2007