Gergely Neu - RankMe

116 papers A* 24A 9B 10C 1Journal 61Unranked 10

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Confidence Sequences for Generalized Linear Models via Regret Analysis. CoRR Eugenio Clerico, Hamish Flynn, Wojciech Kotlowski, Gergely Neu
2025	J	`jnl`	Distances for Markov chains from sample streams. CoRR Sergio Calo, Anders Jonsson, Gergely Neu, Ludovic Schwartz, Javier Segovia-Aguas
2025	B	`conf`	Generalization bounds for mixing processes via delayed online-to-PAC conversions. ALT Baptiste Abélès, Eugenio Clerico, Gergely Neu
2025	J	`jnl`	Inverse Q-Learning Done Right: Offline Imitation Learning in Q CoRR Antoine Moulin, Gergely Neu, Luca Viano
2025	J	`jnl`	Linear Bandits with Non-i.i.d. Noise. CoRR Baptiste Abélès, Eugenio Clerico, Hamish Flynn, Gergely Neu
2025	A	`conf`	Offline RL via Feature-Occupancy Gradient Ascent. AISTATS Gergely Neu, Nneka Okolo
2025	A	`conf`	Online-to-PAC generalization bounds under graph-mixing dependencies. AISTATS Baptiste Abélès, Gergely Neu, Eugenio Clerico
2025	A*	`conf`	Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning. COLT Antoine Moulin, Gergely Neu, Luca Viano
2025	J	`jnl`	Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning. CoRR Antoine Moulin, Gergely Neu, Luca Viano
2025	J	`jnl`	Sparse Optimistic Information Directed Sampling. CoRR Ludovic Schwartz, Hamish Flynn, Gergely Neu
2024	B	`conf`	Adversarial Contextual Bandits Go Kernelized. ALT Gergely Neu, Julia Olkhovskaya, Sattar Vakili
2024	A*	`conf`	Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently. NeurIPS Sergio Calo, Anders Jonsson, Gergely Neu, Ludovic Schwartz, Javier Segovia-Aguas
2024	J	`jnl`	Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently. CoRR Sergio Calo, Anders Jonsson, Gergely Neu, Ludovic Schwartz, Javier Segovia-Aguas
2024	A*	`conf`	Dealing With Unbounded Gradients in Stochastic Saddle-point Optimization. ICML Gergely Neu, Nneka Okolo
2024	J	`jnl`	Dealing with unbounded gradients in stochastic saddle-point optimization. CoRR Gergely Neu, Nneka Okolo
2024	J	`jnl`	Generalization bounds for mixing processes via delayed online-to-PAC conversions. CoRR Baptiste Abélès, Eugenio Clerico, Gergely Neu
2024	B	`conf`	Importance-Weighted Offline Learning Done Right. ALT Germano Gabbianelli, Gergely Neu, Matteo Papini
2024	A	`conf`	Offline Primal-Dual Reinforcement Learning for Linear MDPs. AISTATS Germano Gabbianelli, Gergely Neu, Matteo Papini, Nneka Okolo
2024	J	`jnl`	Offline RL via Feature-Occupancy Gradient Ascent. CoRR Gergely Neu, Nneka Okolo
2024	J	`jnl`	On the Hardness of Learning from Censored and Nonstationary Demand. INFORMS J. Optim. Gábor Lugosi, Mihalis G. Markakis, Gergely Neu
2024	J	`jnl`	Online-to-PAC generalization bounds under graph-mixing dependencies. CoRR Baptiste Abélès, Eugenio Clerico, Gergely Neu
2024	A*	`conf`	Optimistic Information Directed Sampling. COLT Gergely Neu, Matteo Papini, Ludovic Schwartz
2024	J	`jnl`	Optimistic Information Directed Sampling. CoRR Gergely Neu, Matteo Papini, Ludovic Schwartz
2023	J	`jnl`	Adversarial Contextual Bandits Go Kernelized. CoRR Gergely Neu, Julia Olkhovskaya, Sattar Vakili
2023	B	`conf`	Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization. ALT Gergely Neu, Nneka Okolo
2023	A*	`conf`	First- and Second-Order Bounds for Adversarial Linear Contextual Bandits. NeurIPS Julia Olkhovskaya, Jack J. Mayo, Tim van Erven, Gergely Neu, Chen-Yu Wei
2023	J	`jnl`	First- and Second-Order Bounds for Adversarial Linear Contextual Bandits. CoRR Julia Olkhovskaya, Jack J. Mayo, Tim van Erven, Gergely Neu, Chen-Yu Wei
2023	J	`jnl`	Importance-Weighted Offline Learning Done Right. CoRR Germano Gabbianelli, Gergely Neu, Matteo Papini
2023	A	`conf`	Nonstochastic Contextual Combinatorial Bandits. AISTATS Lukas Zierahn, Dirk van der Hoeven, Nicolò Cesa-Bianchi, Gergely Neu
2023	J	`jnl`	Offline Primal-Dual Reinforcement Learning for Linear MDPs. CoRR Germano Gabbianelli, Gergely Neu, Nneka Okolo, Matteo Papini
2023	B	`conf`	Online Learning with Off-Policy Feedback. ALT Germano Gabbianelli, Gergely Neu, Matteo Papini
2023	J	`jnl`	Online-to-PAC Conversions: Generalization Bounds via Regret Analysis. CoRR Gábor Lugosi, Gergely Neu
2023	A*	`conf`	Optimistic Planning by Regularized Dynamic Programming. ICML Antoine Moulin, Gergely Neu
2023	J	`jnl`	Optimistic Planning by Regularized Dynamic Programming. CoRR Antoine Moulin, Gergely Neu
2023	A*	`ed.`	The Thirty Sixth Annual Conference on Learning Theory, COLT 2023, 12-15 July 2023, Bangalore, India. COLT Gergely Neu, Lorenzo Rosasco
2022	—	`conf`	Convex Analytic Theory for Convex Q-Learning. CDC Fan Lu, Prashant G. Mehta, Sean P. Meyn, Gergely Neu
2022	J	`jnl`	Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization. CoRR Gergely Neu, Nneka Okolo
2022	A*	`conf`	Generalization Bounds via Convex Analysis. COLT Gábor Lugosi, Gergely Neu
2022	J	`jnl`	Generalization Bounds via Convex Analysis. CoRR Gergely Neu, Gábor Lugosi
2022	A*	`conf`	Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits. NeurIPS Gergely Neu, Julia Olkhovskaya, Matteo Papini, Ludovic Schwartz
2022	J	`jnl`	Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits. CoRR Gergely Neu, Julia Olkhovskaya, Matteo Papini, Ludovic Schwartz
2022	J	`jnl`	Online Learning with Off-Policy Feedback. CoRR Germano Gabbianelli, Matteo Papini, Gergely Neu
2022	A*	`conf`	Proximal Point Imitation Learning. NeurIPS Luca Viano, Angeliki Kamoutsi, Gergely Neu, Igor Krawczuk, Volkan Cevher
2022	J	`jnl`	Proximal Point Imitation Learning. CoRR Luca Viano, Angeliki Kamoutsi, Gergely Neu, Igor Krawczuk, Volkan Cevher
2022	J	`jnl`	Sufficient Exploration for Convex Q-learning. CoRR Fan Lu, Prashant G. Mehta, Sean P. Meyn, Gergely Neu
2021	C	`conf`	Convex Q-Learning. ACC Fan Lu, Prashant G. Mehta, Sean P. Meyn, Gergely Neu
2021	A*	`conf`	Information-Theoretic Generalization Bounds for Stochastic Gradient Descent. COLT Gergely Neu
2021	J	`jnl`	Information-Theoretic Generalization Bounds for Stochastic Gradient Descent. CoRR Gergely Neu
2021	J	`jnl`	Learning to maximize global influence from local observations. CoRR Gábor Lugosi, Gergely Neu, Julia Olkhovskaya
2021	A	`conf`	Logistic Q-Learning. AISTATS Joan Bas-Serrano, Sebastian Curi, Andreas Krause, Gergely Neu
2021	A*	`conf`	Online learning in MDPs with linear function approximation and bandit feedback. NeurIPS Gergely Neu, Julia Olkhovskaya
2021	J	`jnl`	Robustness and risk management via distributional dynamic programming. CoRR Mastane Achab, Gergely Neu
2020	A*	`conf`	A Unifying View of Optimism in Episodic Reinforcement Learning. NeurIPS Gergely Neu, Ciara Pike-Burke
2020	J	`jnl`	A Unifying View of Optimism in Episodic Reinforcement Learning. CoRR Gergely Neu, Ciara Pike-Burke
2020	B	`conf`	Algorithmic Learning Theory 2020: Preface. ALT Aryeh Kontorovich, Gergely Neu
2020	B	`ed.`	Algorithmic Learning Theory, ALT 2020, 8-11 February 2020, San Diego, CA, USA. ALT Aryeh Kontorovich, Gergely Neu
2020	J	`jnl`	Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits. CoRR Gergely Neu, Julia Olkhovskaya
2020	A*	`conf`	Efficient and robust algorithms for adversarial linear contextual bandits. COLT Gergely Neu, Julia Olkhovskaya
2020	A*	`conf`	Fast Rates for Online Prediction with Abstention. COLT Gergely Neu, Nikita Zhivotovskiy
2020	J	`jnl`	Fast Rates for Online Prediction with Abstention. CoRR Gergely Neu, Nikita Zhivotovskiy
2020	—	`conf`	Faster saddle-point optimization for solving large-scale Markov decision processes. L4DC Joan Bas-Serrano, Gergely Neu
2020	J	`jnl`	Logistic $Q$-Learning. CoRR Joan Bas-Serrano, Sebastian Curi, Andreas Krause, Gergely Neu
2020	J	`jnl`	Online learning in MDPs with linear function approximation and bandit feedback. CoRR Gergely Neu, Julia Olkhovskaya
2019	A*	`conf`	Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates. NeurIPS Carlos Riquelme, Hugo Penedones, Damien Vincent, Hartmut Maennel, Sylvain Gelly, Timothy A. Mann, André Barreto, Gergely Neu
2019	J	`jnl`	Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates. CoRR Hugo Penedones, Carlos Riquelme, Damien Vincent, Hartmut Maennel, Timothy A. Mann, André Barreto, Sylvain Gelly, Gergely Neu
2019	A*	`conf`	Bandit Principal Component Analysis. COLT Wojciech Kotlowski, Gergely Neu
2019	J	`jnl`	Bandit Principal Component Analysis. CoRR Wojciech Kotlowski, Gergely Neu
2019	A*	`conf`	Beating SGD Saturation with Tail-Averaging and Minibatching. NeurIPS Nicole Mücke, Gergely Neu, Lorenzo Rosasco
2019	J	`jnl`	Beating SGD Saturation with Tail-Averaging and Minibatching. CoRR Nicole Mücke, Gergely Neu, Lorenzo Rosasco
2019	J	`jnl`	Collaborative Spatial Reuse in wireless networks via selfish Multi-Armed Bandits. Ad Hoc Networks Francesc Wilhelmi, Cristina Cano, Gergely Neu, Boris Bellalta, Anders Jonsson, Sergio Barrachina-Muñoz
2019	J	`jnl`	Faster saddle-point optimization for solving large-scale Markov decision processes. CoRR Joan Bas-Serrano, Gergely Neu
2019	B	`conf`	Online Influence Maximization with Local Observations. ALT Gábor Lugosi, Gergely Neu, Julia Olkhovskaya
2019	J	`jnl`	Potential and pitfalls of Multi-Armed Bandits for decentralized Spatial Reuse in WLANs. J. Netw. Comput. Appl. Francesc Wilhelmi, Sergio Barrachina-Muñoz, Boris Bellalta, Cristina Cano, Anders Jonsson, Gergely Neu
2018	A*	`conf`	Iterate Averaging as Regularization for Stochastic Gradient Descent. COLT Gergely Neu, Lorenzo Rosasco
2018	J	`jnl`	Iterate averaging as regularization for stochastic gradient descent. CoRR Gergely Neu, Lorenzo Rosasco
2018	J	`jnl`	Online Influence Maximization with Local Observations. CoRR Julia Olkhovskaya, Gergely Neu, Gábor Lugosi
2018	J	`jnl`	Potential and Pitfalls of Multi-Armed Bandits for Decentralized Spatial Reuse in WLANs. CoRR Francesc Wilhelmi, Sergio Barrachina-Muñoz, Cristina Cano, Boris Bellalta, Anders Jonsson, Gergely Neu
2018	—	`conf`	Wireless Optimisation via Convex Bandits: Unlicensed LTE/WiFi Coexistence. NetAI@SIGCOMM Cristina Cano, Gergely Neu
2018	J	`jnl`	Wireless Optimisation via Convex Bandits: Unlicensed LTE/WiFi Coexistence. CoRR Cristina Cano, Gergely Neu
2017	J	`jnl`	A unified view of entropy-regularized Markov decision processes. CoRR Gergely Neu, Anders Jonsson, Vicenç Gómez
2017	A*	`conf`	Algorithmic Stability and Hypothesis Complexity. ICML Tongliang Liu, Gábor Lugosi, Gergely Neu, Dacheng Tao
2017	J	`jnl`	Algorithmic stability and hypothesis complexity. CoRR Tongliang Liu, Gábor Lugosi, Gergely Neu, Dacheng Tao
2017	—	`conf`	Boltzmann Exploration Done Right. NIPS Nicolò Cesa-Bianchi, Claudio Gentile, Gergely Neu, Gábor Lugosi
2017	J	`jnl`	Boltzmann Exploration Done Right. CoRR Nicolò Cesa-Bianchi, Claudio Gentile, Gábor Lugosi, Gergely Neu
2017	J	`jnl`	Collaborative Spatial Reuse in Wireless Networks via Selfish Multi-Armed Bandits. CoRR Francesc Wilhelmi, Cristina Cano, Gergely Neu, Boris Bellalta, Anders Jonsson, Sergio Barrachina-Muñoz
2017	A*	`conf`	Fast rates for online learning in Linearly Solvable Markov Decision Processes. COLT Gergely Neu, Vicenç Gómez
2017	J	`jnl`	Fast rates for online learning in Linearly Solvable Markov Decision Processes. CoRR Gergely Neu, Vicenç Gómez
2017	J	`jnl`	On the Hardness of Inventory Management with Censored Demand Data. CoRR Gábor Lugosi, Mihalis G. Markakis, Gergely Neu
2016	J	`jnl`	Importance Weighting Without Importance Weights: An Efficient Algorithm for Combinatorial Semi-Bandits. J. Mach. Learn. Res. Gergely Neu, Gábor Bartók
2016	A	`conf`	Online Learning with Noisy Side Observations. AISTATS Tomás Kocák, Gergely Neu, Michal Valko
2016	A	`conf`	Online learning with Erdos-Renyi side-observation graphs. UAI Tomás Kocák, Gergely Neu, Michal Valko
2015	—	`conf`	Explore no more: Improved high-probability regret bounds for non-stochastic bandits. NIPS Gergely Neu
2015	J	`jnl`	Explore no more: improved high-probability regret bounds for non-stochastic bandits. CoRR Gergely Neu
2015	A*	`conf`	First-order regret bounds for combinatorial semi-bandits. COLT Gergely Neu
2015	J	`jnl`	First-order regret bounds for combinatorial semi-bandits. CoRR Gergely Neu
2015	J	`jnl`	Importance weighting without importance weights: An efficient algorithm for combinatorial semi-bandits. CoRR Gergely Neu, Gábor Bartók
2015	J	`jnl`	Random-Walk Perturbations for Online Combinatorial Optimization. IEEE Trans. Inf. Theory Luc Devroye, Gábor Lugosi, Gergely Neu
2014	—	`conf`	Efficient learning by implicit exploration in bandit problems with side observations. NIPS Tomás Kocák, Gergely Neu, Michal Valko, Rémi Munos
2014	—	`conf`	Exploiting easy data in online optimization. NIPS Amir Sani, Gergely Neu, Alessandro Lazaric
2014	J	`jnl`	Near-Optimal Rates for Limited-Delay Universal Lossy Source Coding. IEEE Trans. Inf. Theory András György, Gergely Neu
2014	J	`jnl`	Online Markov Decision Processes Under Bandit Feedback. IEEE Trans. Autom. Control. Gergely Neu, András György, Csaba Szepesvári, András Antos
2014	—	`conf`	Online combinatorial optimization with stochastic decision sets and adversarial losses. NIPS Gergely Neu, Michal Valko
2014	J	`jnl`	Online learning in MDPs with side information. CoRR Yasin Abbasi-Yadkori, Gergely Neu
2013	B	`conf`	An Efficient Algorithm for Learning with Semi-bandit Feedback. ALT Gergely Neu, Gábor Bartók
2013	J	`jnl`	An efficient algorithm for learning with semi-bandit feedback CoRR Gergely Neu, Gábor Bartók
2013	—	`conf`	Online learning in episodic Markovian decision processes by relative entropy policy search. NIPS Alexander Zimin, Gergely Neu
2013	—	`—`	Online tanulás nemstacionárius Markov döntési folyamatokban Gergely Neu
2013	J	`jnl`	Prediction by Random-Walk Perturbation CoRR Luc Devroye, Gábor Lugosi, Gergely Neu
2013	A*	`conf`	Prediction by random-walk perturbation. COLT Luc Devroye, Gábor Lugosi, Gergely Neu
2012	J	`jnl`	Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods CoRR Gergely Neu, Csaba Szepesvári
2012	A	`conf`	The adversarial stochastic shortest path problem with unknown transition probabilities. AISTATS Gergely Neu, András György, Csaba Szepesvári
2011	B	`conf`	Near-optimal rates for limited-delay universal lossy source coding. ISIT András György, Gergely Neu
2010	—	`conf`	Online Markov Decision Processes under Bandit Feedback. NIPS Gergely Neu, András György, Csaba Szepesvári, András Antos
2010	A*	`conf`	The Online Loop-free Stochastic Shortest-Path Problem. COLT Gergely Neu, András György, Csaba Szepesvári
2009	J	`jnl`	Training parsers by inverse reinforcement learning. Mach. Learn. Gergely Neu, Csaba Szepesvári
2007	A	`conf`	Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods. UAI Gergely Neu, Csaba Szepesvári