| 2025 | AISTATS | Online-to-PAC generalization bounds under graph-mixing dependencies. | Baptiste Abls, Gergely Neu, Eugenio Clerico |
| 2025 | AISTATS | Offline RL via Feature-Occupancy Gradient Ascent. | Gergely Neu, Nneka Okolo |
| 2025 | ALT | Generalization bounds for mixing processes via delayed online-to-PAC conversions. | Baptiste Abls, Eugenio Clerico, Gergely Neu |
| 2025 | COLT | Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning. | Antoine Moulin, Gergely Neu, Luca Viano |
| 2024 | AISTATS | Offline Primal-Dual Reinforcement Learning for Linear MDPs. | Germano Gabbianelli, Gergely Neu, Matteo Papini, Nneka Okolo |
| 2024 | ALT | Importance-Weighted Offline Learning Done Right. | Germano Gabbianelli, Gergely Neu, Matteo Papini |
| 2024 | ALT | Adversarial Contextual Bandits Go Kernelized. | Gergely Neu, Julia Olkhovskaya, Sattar Vakili |
| 2024 | COLT | Optimistic Information Directed Sampling. | Gergely Neu, Matteo Papini, Ludovic Schwartz |
| 2024 | ICML | Dealing With Unbounded Gradients in Stochastic Saddle-point Optimization. | Gergely Neu, Nneka Okolo |
| 2023 | AISTATS | Nonstochastic Contextual Combinatorial Bandits. | Lukas Zierahn, Dirk van der Hoeven, Nicol Cesa-Bianchi, Gergely Neu |
| 2023 | ALT | Online Learning with Off-Policy Feedback. | Germano Gabbianelli, Gergely Neu, Matteo Papini |
| 2023 | ALT | Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization. | Gergely Neu, Nneka Okolo |
| 2023 | ICML | Optimistic Planning by Regularized Dynamic Programming. | Antoine Moulin, Gergely Neu |
| 2022 | COLT | Generalization Bounds via Convex Analysis. | Gbor Lugosi, Gergely Neu |
| 2021 | AISTATS | Logistic Q-Learning. | Joan Bas-Serrano, Sebastian Curi, Andreas Krause, Gergely Neu |
| 2021 | COLT | Information-Theoretic Generalization Bounds for Stochastic Gradient Descent. | Gergely Neu |
| 2020 | ALT | Algorithmic Learning Theory 2020: Preface. | Aryeh Kontorovich, Gergely Neu |
| 2020 | COLT | Efficient and robust algorithms for adversarial linear contextual bandits. | Gergely Neu, Julia Olkhovskaya |
| 2020 | COLT | Fast Rates for Online Prediction with Abstention. | Gergely Neu, Nikita Zhivotovskiy |
| 2019 | ALT | Online Influence Maximization with Local Observations. | Gbor Lugosi, Gergely Neu, Julia Olkhovskaya |
| 2019 | COLT | Bandit Principal Component Analysis. | Wojciech Kotlowski, Gergely Neu |
| 2018 | COLT | Iterate Averaging as Regularization for Stochastic Gradient Descent. | Gergely Neu, Lorenzo Rosasco |
| 2018 | SIGCOMM | Wireless Optimisation via Convex Bandits: Unlicensed LTE/WiFi Coexistence. | Cristina Cano, Gergely Neu |
| 2017 | COLT | Fast rates for online learning in Linearly Solvable Markov Decision Processes. | Gergely Neu, Vicen Gmez |
| 2017 | ICML | Algorithmic Stability and Hypothesis Complexity. | Tongliang Liu, Gbor Lugosi, Gergely Neu, Dacheng Tao |
| 2016 | AISTATS | Online Learning with Noisy Side Observations. | Toms Kock, Gergely Neu, Michal Valko |
| 2016 | UAI | Online learning with Erdos-Renyi side-observation graphs. | Toms Kock, Gergely Neu, Michal Valko |
| 2015 | COLT | First-order regret bounds for combinatorial semi-bandits. | Gergely Neu |
| 2013 | ALT | An Efficient Algorithm for Learning with Semi-bandit Feedback. | Gergely Neu, Gbor Bartk |
| 2013 | COLT | Prediction by random-walk perturbation. | Luc Devroye, Gbor Lugosi, Gergely Neu |
| 2011 | ISIT | Near-optimal rates for limited-delay universal lossy source coding. | Andrs Gyrgy, Gergely Neu |
| 2010 | COLT | The Online Loop-free Stochastic Shortest-Path Problem. | Gergely Neu, Andrs Gyrgy, Csaba Szepesvri |
| 2007 | UAI | Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods. | Gergely Neu, Csaba Szepesvri |