Gergely Neu -- publications

J. Olkhovskaya, J. Mayo, T. van Erven, G. Neu, C.-Y. Wei: First-and Second-Order Bounds for Adversarial Linear Contextual Bandits. In Advances in Neural Information Processing Systems 36 (NeurIPS), 2023.
A. Moulin, G. Neu: Optimistic planning via regularized dynamic programming. In Proceedings of the 40th International Conference on Machine Learning (ICML), pp. 25337-25357, 2023.
L. Zierahn, D. van der Hoeven, N. Cesa-Bianchi, G. Neu: Nonstochastic Contextual Combinatorial Bandits. In Proceedings of the Twenty-sixth International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 8771-8813, 2023.
G. Neu, N. Okolo: Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization. In Proceedings of the 34th International Conference on Algorithmic Learning Theory (ALT), pp. 1101-1123, 2023.
G. Gabbianelli, G. Neu, M. Papini: Online learning with off-policy feedback. In Proceedings of the 34th International Conference on Algorithmic Learning Theory (ALT), pp. 620-641, 2023.
L. Viano, A. Kamoutsi, G. Neu, I. Krawczuk, V. Cevher: Proximal Point Imitation Learning. In Advances in Neural Information Processing Systems 35 (NeurIPS), 2022.
G. Neu, J. Olkhovskaya, M. Papini, L. Schwartz: Lifting the information ratio: An information-theoretic analysis of Thompson sampling for Contextual bandits. In Advances in Neural Information Processing Systems 35 (NeurIPS), 2022.
G. Lugosi and G. Neu: Generalization bounds via convex analysis. In Proceedings of the 34th Annual Conference on Learning Theory (COLT), pp. 3524-3546, 2022. [slides]
G. Neu and J. Olkhovskaya: Online learning in MDPs with linear function approximation and bandit feedback. In Advances in Neural Information Processing Systems 34 (NeurIPS), pp. 10407-10417, 2021.
G. Neu, G. K. Dziugaite, M. Haghifam, D. M. Roy: Information-Theoretic Generalization Bounds for Stochastic Gradient Descent. In Proceedings of the 33nd Annual Conference on Learning Theory (COLT), pp. 3526-3545, 2021.
J. Bas-Serrano, S. Curi, A. Krause and G. Neu: Logistic Q-Learning. In Proceedings of the Twenty-fourth International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 3610-3618, 2021. [slides]
G. Neu and C. Pike-Burke: A Unifying View of Optimism in Episodic Reinforcement Learning. In Advances in Neural Information Processing Systems 33 (NeurIPS), pp. 1392-1403, 2020. [slides]
G. Neu and J. Olkhovskaya: Efficient and robust algorithms for adversarial linear contextual bandits. In Proceedings of the 32nd Annual Conference on Learning Theory (COLT), pp. 3049-3068, 2020.
G. Neu and N. Zhivotovskiy: Fast rates for online prediction with abstention. In Proceedings of the 32nd Annual Conference on Learning Theory (COLT), pp. 3030–3048, 2020.
J. Bas-Serrano and G. Neu: Faster saddle-point optimization for solving large-scale Markov decision processes. In Conference on Learning for Dynamics and Control (L4DC), pp. 413–423, 2020.
N. Mücke, G. Neu and L. Rosasco: Beating SGD saturation with tail-averaging and minibatching. In Advances in Neural Information Processing Systems 32 (NeurIPS), pp. 12568-12577, 2019.
C. Riquelme, H. Penedones, D. Vincent, H. Maennel, S. Gelly, T. Mann, A. Barreto and G. Neu: Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates. In Advances in Neural Information Processing Systems 32 (NeurIPS), pp. 11872-11882, 2019.
W. Kotłowski and G. Neu: Bandit Principal Component Analysis. In Proceedings of the 32nd Annual Conference on Learning Theory (COLT), pp. 1994-2024, 2019. [slides]
G. Lugosi, G. Neu and J. Olkhovskaya : Online influence maximization with local observations. In Proceedings of the 30th International Conference on Algorithmic Learning Theory (ALT), pp. 557-580, 2019.
G. Neu and L. Rosasco: Iterate averaging as regularization for stochastic gradient descent. In Proceedings of the 31st Annual Conference on Learning Theory (COLT), pp. 3222-3242, 2018.
N. Cesa-Bianchi, C. Gentile, G. Lugosi and G. Neu: Boltzmann exploration done right. In Advances in Neural Information Processing Systems 30 (NeurIPS), pp. 6284-6293, 2017. [poster]
G. Neu and V. Gómez: Fast rates for online learning in Linearly Solvable Markov Decision Processes. In Proceedings of the 30th Annual Conference on Learning Theory (COLT), pp. 1567-1588, 2017. [slides]
T. Liu, G. Lugosi, G. Neu and D. Tao: Algorithmic stability and hypothesis complexity. In Proceedings of the 34th International Conference on Machine Learning (ICML), pp. 2159-2167, 2017.
T. Kocák, G. Neu and M. Valko: Online learning with Erdős-Rényi side-observation graphs. In Proceedings of the 32nd Conference on Uncertainty in Artificial Intelligence (UAI), pp. 339-346, 2016.
T. Kocák, G. Neu and M. Valko: Online learning with noisy side observations. In Proceedings of the Nineteenth International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 1186-1194, 2016.
G. Neu: Explore no more: Improved high-probability regret bounds for non-stochastic bandits. In Advances in Neural Information Processing Systems 28 (NeurIPS), pp. 3150-3158, 2015. [poster] [slides]
G. Neu: First-order regret bounds for combinatorial semi-bandits. In Proceedings of the 28th Annual Conference on Learning Theory (COLT), pp. 1360-1375, 2015.[poster] [slides]
G. Neu and M. Valko: Online Combinatorial Optimization with Stochastic Decision Sets and Adversarial Losses. In Advances in Neural Information Processing Systems 27 (NeurIPS), pp. 2780-2788, 2014. [poster] [slides]
T. Kocák, G. Neu, M. Valko and R. Munos: Efficient Learning by Implicit Exploration in Bandit Problems with Side Observations. In Advances in Neural Information Processing Systems 27 (NeurIPS), pp. 613-621, 2014. [poster] [slides]
A. Sani, G. Neu and A. Lazaric: Exploiting Easy Data in Online Optimization. In Advances in Neural Information Processing Systems 27 (NeurIPS), pp. 810-818, 2014. [poster] [spotlight] [talk]
A. Zimin and G. Neu: Online Learning in Episodic Markov Decision Processes by Relative Entropy Policy Search. In Advances in Neural Information Processing Systems 26 (NeurIPS), pp. 1583-1591, 2013. [poster] [slides]
G. Neu and G. Bartók: An Efficient Algorithm for Learning with Semi-Bandit Feedback. In Proceedings of the 24th International Conference on Algorithmic Learning Theory (ALT), pp. 234-248, 2013. [poster] [slides] Full version in JMLR '16.
L. Devroye, G. Lugosi and G. Neu: Prediction by Random-Walk Perturbation. In Proceedings of the 26th Annual Conference on Learning Theory (COLT), pp. 460-473, 2013. [slides] Full version in IEEE T-IT '15.
G. Neu, A. György, and Cs. Szepesvári: The Adversarial Stochastic Shortest Path Problem with Unknown Transition Probabilities. In Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 805-813, 2012. [supplement] [poster]
A. György and G. Neu: Near-Optimal Rates for Limited-Delay Universal Lossy Source Coding. In 2011 IEEE International Symposium on Information Theory, pp. 2218-2222, 2011.Full version in IEEE T-IT '14.
G. Neu, A. György, Cs. Szepesvári and A. Antos: Online Markov Decision Processes under Bandit Feedback. In Advances in Neural Information Processing Systems 23 (NeurIPS), pp. 1804-1812, 2010. [poster] [spotlight] Full version in IEEE TAC '14.
G. Neu, A. György, and Cs. Szepesvári: The Online Loop-free Stochastic Shortest-Path Problem. In Proceedings of The 23rd Conference on Learning Theory (COLT), pp. 231-243, 2010.
G. Neu and Cs. Szepesvári: Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods. In Proceedings of the 23rd Conference on Uncertainty in Artificial Intelligence (UAI), pp. 295-302, 2007.