default search action
Gergely Neu
Person information
- affiliation: Pompeu Fabra University, DTIC, Barcelona, Spain
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [j8]Gábor Lugosi
, Mihalis G. Markakis
On the Hardness of Learning from Censored and Nonstationary Demand. INFORMS J. Optim. 6(2): 63-83 (2024) - [c47]Germano Gabbianelli, Gergely Neu, Matteo Papini, Nneka Okolo:
Offline Primal-Dual Reinforcement Learning for Linear MDPs. AISTATS 2024: 3169-3177 - [c46]Germano Gabbianelli, Gergely Neu, Matteo Papini:
Importance-Weighted Offline Learning Done Right. ALT 2024: 614-634 - [c45]Gergely Neu, Julia Olkhovskaya, Sattar Vakili:
Adversarial Contextual Bandits Go Kernelized. ALT 2024: 907-929 - [c44]Gergely Neu, Matteo Papini, Ludovic Schwartz:
Optimistic Information Directed Sampling. COLT 2024: 3970-4006 - [c43]Gergely Neu, Nneka Okolo:
Dealing With Unbounded Gradients in Stochastic Saddle-point Optimization. ICML 2024 - [i47]Gergely Neu, Nneka Okolo:
Dealing with unbounded gradients in stochastic saddle-point optimization. CoRR abs/2402.13903 (2024) - [i46]Gergely Neu, Matteo Papini, Ludovic Schwartz:
Optimistic Information Directed Sampling. CoRR abs/2402.15411 (2024) - [i45]Gergely Neu, Nneka Okolo:
Offline RL via Feature-Occupancy Gradient Ascent. CoRR abs/2405.13755 (2024) - [i44]Sergio Calo, Anders Jonsson, Gergely Neu, Ludovic Schwartz, Javier Segovia-Aguas:
Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently. CoRR abs/2406.04056 (2024) - [i43]Baptiste Abélès, Eugenio Clerico, Gergely Neu:
Generalization bounds for mixing processes via delayed online-to-PAC conversions. CoRR abs/2406.12600 (2024) - [i42]Baptiste Abélès, Eugenio Clerico, Gergely Neu:
Online-to-PAC generalization bounds under graph-mixing dependencies. CoRR abs/2410.08977 (2024) - 2023
- [c42]Lukas Zierahn
Nonstochastic Contextual Combinatorial Bandits. AISTATS 2023: 8771-8813 - [c41]Germano Gabbianelli, Gergely Neu, Matteo Papini:
Online Learning with Off-Policy Feedback. ALT 2023: 620-641 - [c40]Gergely Neu, Nneka Okolo:
Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization. ALT 2023: 1101-1123 - [c39]Antoine Moulin, Gergely Neu:
Optimistic Planning by Regularized Dynamic Programming. ICML 2023: 25337-25357 - [c38]Julia Olkhovskaya, Jack J. Mayo, Tim van Erven, Gergely Neu, Chen-Yu Wei:
First- and Second-Order Bounds for Adversarial Linear Contextual Bandits. NeurIPS 2023 - [e2]Gergely Neu, Lorenzo Rosasco:
The Thirty Sixth Annual Conference on Learning Theory, COLT 2023, 12-15 July 2023, Bangalore, India. Proceedings of Machine Learning Research 195, PMLR 2023 [contents] - [i41]Antoine Moulin, Gergely Neu:
Optimistic Planning by Regularized Dynamic Programming. CoRR abs/2302.14004 (2023) - [i40]Julia Olkhovskaya, Jack J. Mayo, Tim van Erven, Gergely Neu, Chen-Yu Wei:
First- and Second-Order Bounds for Adversarial Linear Contextual Bandits. CoRR abs/2305.00832 (2023) - [i39]Germano Gabbianelli, Gergely Neu, Nneka Okolo, Matteo Papini:
Offline Primal-Dual Reinforcement Learning for Linear MDPs. CoRR abs/2305.12944 (2023) - [i38]Gábor Lugosi, Gergely Neu:
Online-to-PAC Conversions: Generalization Bounds via Regret Analysis. CoRR abs/2305.19674 (2023) - [i37]Germano Gabbianelli, Gergely Neu, Matteo Papini:
Importance-Weighted Offline Learning Done Right. CoRR abs/2309.15771 (2023) - [i36]Gergely Neu, Julia Olkhovskaya, Sattar Vakili:
Adversarial Contextual Bandits Go Kernelized. CoRR abs/2310.01609 (2023) - 2022
- [c37]Fan Lu, Prashant G. Mehta, Sean P. Meyn, Gergely Neu:
Convex Analytic Theory for Convex Q-Learning. CDC 2022: 4065-4071 - [c36]Gábor Lugosi, Gergely Neu:
Generalization Bounds via Convex Analysis. COLT 2022: 3524-3546 - [c35]Gergely Neu, Julia Olkhovskaya, Matteo Papini, Ludovic Schwartz:
Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits. NeurIPS 2022 - [c34]Luca Viano, Angeliki Kamoutsi, Gergely Neu, Igor Krawczuk, Volkan Cevher:
Proximal Point Imitation Learning. NeurIPS 2022 - [i35]Gergely Neu, Gábor Lugosi:
Generalization Bounds via Convex Analysis. CoRR abs/2202.04985 (2022) - [i34]Gergely Neu, Julia Olkhovskaya, Matteo Papini, Ludovic Schwartz:
Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits. CoRR abs/2205.13924 (2022) - [i33]Germano Gabbianelli, Matteo Papini, Gergely Neu:
Online Learning with Off-Policy Feedback. CoRR abs/2207.08956 (2022) - [i32]Luca Viano, Angeliki Kamoutsi, Gergely Neu, Igor Krawczuk, Volkan Cevher:
Proximal Point Imitation Learning. CoRR abs/2209.10968 (2022) - [i31]Fan Lu, Prashant G. Mehta, Sean P. Meyn, Gergely Neu:
Sufficient Exploration for Convex Q-learning. CoRR abs/2210.09409 (2022) - [i30]Gergely Neu, Nneka Okolo:
Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization. CoRR abs/2210.12057 (2022) - 2021
- [c33]Joan Bas-Serrano, Sebastian Curi, Andreas Krause, Gergely Neu:
Logistic Q-Learning. AISTATS 2021: 3610-3618 - [c32]Fan Lu, Prashant G. Mehta
Convex Q-Learning. ACC 2021: 4749-4756 - [c31]Gergely Neu:
Information-Theoretic Generalization Bounds for Stochastic Gradient Descent. COLT 2021: 3526-3545 - [c30]Gergely Neu, Julia Olkhovskaya:
Online learning in MDPs with linear function approximation and bandit feedback. NeurIPS 2021: 10407-10417 - [i29]Gergely Neu:
Information-Theoretic Generalization Bounds for Stochastic Gradient Descent. CoRR abs/2102.00931 (2021) - [i28]Gábor Lugosi, Gergely Neu, Julia Olkhovskaya:
Learning to maximize global influence from local observations. CoRR abs/2109.11909 (2021) - [i27]Mastane Achab, Gergely Neu:
Robustness and risk management via distributional dynamic programming. CoRR abs/2112.15430 (2021) - 2020
- [c29]Aryeh Kontorovich, Gergely Neu:
Algorithmic Learning Theory 2020: Preface. ALT 2020: 1-2 - [c28]Gergely Neu, Nikita Zhivotovskiy:
Fast Rates for Online Prediction with Abstention. COLT 2020: 3030-3048 - [c27]Gergely Neu, Julia Olkhovskaya:
Efficient and robust algorithms for adversarial linear contextual bandits. COLT 2020: 3049-3068 - [c26]Joan Bas-Serrano, Gergely Neu:
Faster saddle-point optimization for solving large-scale Markov decision processes. L4DC 2020: 413-423 - [c25]Gergely Neu, Ciara Pike-Burke:
A Unifying View of Optimism in Episodic Reinforcement Learning. NeurIPS 2020 - [e1]Aryeh Kontorovich, Gergely Neu:
Algorithmic Learning Theory, ALT 2020, 8-11 February 2020, San Diego, CA, USA. Proceedings of Machine Learning Research 117, PMLR 2020 [contents] - [i26]Gergely Neu, Nikita Zhivotovskiy:
Fast Rates for Online Prediction with Abstention. CoRR abs/2001.10623 (2020) - [i25]Gergely Neu, Julia Olkhovskaya:
Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits. CoRR abs/2002.00287 (2020) - [i24]Gergely Neu, Julia Olkhovskaya:
Online learning in MDPs with linear function approximation and bandit feedback. CoRR abs/2007.01612 (2020) - [i23]Gergely Neu, Ciara Pike-Burke:
A Unifying View of Optimism in Episodic Reinforcement Learning. CoRR abs/2007.01891 (2020) - [i22]Joan Bas-Serrano, Sebastian Curi, Andreas Krause, Gergely Neu:
Logistic $Q$-Learning. CoRR abs/2010.11151 (2020)
2010 – 2019
- 2019
- [j7]Francesc Wilhelmi
Collaborative Spatial Reuse in wireless networks via selfish Multi-Armed Bandits. Ad Hoc Networks 88: 129-141 (2019) - [j6]Francesc Wilhelmi
Potential and pitfalls of Multi-Armed Bandits for decentralized Spatial Reuse in WLANs. J. Netw. Comput. Appl. 127: 26-42 (2019) - [c24]Gábor Lugosi, Gergely Neu, Julia Olkhovskaya:
Online Influence Maximization with Local Observations. ALT 2019: 557-580 - [c23]Wojciech Kotlowski, Gergely Neu:
Bandit Principal Component Analysis. COLT 2019: 1994-2024 - [c22]Carlos Riquelme, Hugo Penedones, Damien Vincent, Hartmut Maennel, Sylvain Gelly, Timothy A. Mann, André Barreto, Gergely Neu:
Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates. NeurIPS 2019: 11872-11882 - [c21]Nicole Mücke, Gergely Neu, Lorenzo Rosasco:
Beating SGD Saturation with Tail-Averaging and Minibatching. NeurIPS 2019: 12568-12577 - [i21]Wojciech Kotlowski, Gergely Neu:
Bandit Principal Component Analysis. CoRR abs/1902.03035 (2019) - [i20]Nicole Mücke, Gergely Neu, Lorenzo Rosasco:
Beating SGD Saturation with Tail-Averaging and Minibatching. CoRR abs/1902.08668 (2019) - [i19]Hugo Penedones, Carlos Riquelme, Damien Vincent, Hartmut Maennel, Timothy A. Mann, André Barreto, Sylvain Gelly, Gergely Neu:
Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates. CoRR abs/1906.07987 (2019) - [i18]Joan Bas-Serrano, Gergely Neu:
Faster saddle-point optimization for solving large-scale Markov decision processes. CoRR abs/1909.10904 (2019) - 2018
- [c20]Gergely Neu, Lorenzo Rosasco:
Iterate Averaging as Regularization for Stochastic Gradient Descent. COLT 2018: 3222-3242 - [c19]Cristina Cano
Wireless Optimisation via Convex Bandits: Unlicensed LTE/WiFi Coexistence. NetAI@SIGCOMM 2018: 41-47 - [i17]Cristina Cano, Gergely Neu:
Wireless Optimisation via Convex Bandits: Unlicensed LTE/WiFi Coexistence. CoRR abs/1802.04327 (2018) - [i16]Gergely Neu, Lorenzo Rosasco:
Iterate averaging as regularization for stochastic gradient descent. CoRR abs/1802.08009 (2018) - [i15]Julia Olkhovskaya, Gergely Neu, Gábor Lugosi:
Online Influence Maximization with Local Observations. CoRR abs/1805.11022 (2018) - [i14]Francesc Wilhelmi, Sergio Barrachina-Muñoz, Cristina Cano, Boris Bellalta, Anders Jonsson, Gergely Neu:
Potential and Pitfalls of Multi-Armed Bandits for Decentralized Spatial Reuse in WLANs. CoRR abs/1805.11083 (2018) - 2017
- [c18]Gergely Neu, Vicenç Gómez
Fast rates for online learning in Linearly Solvable Markov Decision Processes. COLT 2017: 1567-1588 - [c17]Tongliang Liu, Gábor Lugosi, Gergely Neu, Dacheng Tao:
Algorithmic Stability and Hypothesis Complexity. ICML 2017: 2159-2167 - [c16]Nicolò Cesa-Bianchi, Claudio Gentile, Gergely Neu, Gábor Lugosi:
Boltzmann Exploration Done Right. NIPS 2017: 6284-6293 - [i13]Gergely Neu, Vicenç Gómez:
Fast rates for online learning in Linearly Solvable Markov Decision Processes. CoRR abs/1702.06341 (2017) - [i12]Tongliang Liu, Gábor Lugosi, Gergely Neu, Dacheng Tao:
Algorithmic stability and hypothesis complexity. CoRR abs/1702.08712 (2017) - [i11]Gergely Neu, Anders Jonsson, Vicenç Gómez:
A unified view of entropy-regularized Markov decision processes. CoRR abs/1705.07798 (2017) - [i10]Nicolò Cesa-Bianchi, Claudio Gentile, Gábor Lugosi, Gergely Neu:
Boltzmann Exploration Done Right. CoRR abs/1705.10257 (2017) - [i9]Gábor Lugosi, Mihalis G. Markakis, Gergely Neu:
On the Hardness of Inventory Management with Censored Demand Data. CoRR abs/1710.05739 (2017) - [i8]Francesc Wilhelmi, Cristina Cano, Gergely Neu, Boris Bellalta, Anders Jonsson, Sergio Barrachina-Muñoz:
Collaborative Spatial Reuse in Wireless Networks via Selfish Multi-Armed Bandits. CoRR abs/1710.11403 (2017) - 2016
- [j5]Gergely Neu, Gábor Bartók:
Importance Weighting Without Importance Weights: An Efficient Algorithm for Combinatorial Semi-Bandits. J. Mach. Learn. Res. 17: 154:1-154:21 (2016) - [c15]Tomás Kocák, Gergely Neu, Michal Valko:
Online Learning with Noisy Side Observations. AISTATS 2016: 1186-1194 - [c14]Tomás Kocák, Gergely Neu, Michal Valko:
Online learning with Erdos-Renyi side-observation graphs. UAI 2016 - 2015
- [j4]Luc Devroye, Gábor Lugosi, Gergely Neu
Random-Walk Perturbations for Online Combinatorial Optimization. IEEE Trans. Inf. Theory 61(7): 4099-4106 (2015) - [c13]Gergely Neu:
First-order regret bounds for combinatorial semi-bandits. COLT 2015: 1360-1375 - [c12]Gergely Neu:
Explore no more: Improved high-probability regret bounds for non-stochastic bandits. NIPS 2015: 3168-3176 - [i7]Gergely Neu:
First-order regret bounds for combinatorial semi-bandits. CoRR abs/1502.06354 (2015) - [i6]Gergely Neu, Gábor Bartók:
Importance weighting without importance weights: An efficient algorithm for combinatorial semi-bandits. CoRR abs/1503.05087 (2015) - [i5]Gergely Neu:
Explore no more: improved high-probability regret bounds for non-stochastic bandits. CoRR abs/1506.03271 (2015) - 2014
- [j3]Gergely Neu
Online Markov Decision Processes Under Bandit Feedback. IEEE Trans. Autom. Control. 59(3): 676-691 (2014) - [j2]András György
Near-Optimal Rates for Limited-Delay Universal Lossy Source Coding. IEEE Trans. Inf. Theory 60(5): 2823-2834 (2014) - [c11]Tomás Kocák, Gergely Neu, Michal Valko, Rémi Munos:
Efficient learning by implicit exploration in bandit problems with side observations. NIPS 2014: 613-621 - [c10]Amir Sani, Gergely Neu, Alessandro Lazaric:
Exploiting easy data in online optimization. NIPS 2014: 810-818 - [c9]Gergely Neu, Michal Valko:
Online combinatorial optimization with stochastic decision sets and adversarial losses. NIPS 2014: 2780-2788 - [i4]Yasin Abbasi-Yadkori, Gergely Neu:
Online learning in MDPs with side information. CoRR abs/1406.6812 (2014) - 2013
- [b1]Gergely Neu:
Online tanulás nemstacionárius Markov döntési folyamatokban. Budapest University of Technology and Economics, Hungary, 2013 - [c8]Gergely Neu
An Efficient Algorithm for Learning with Semi-bandit Feedback. ALT 2013: 234-248 - [c7]Luc Devroye, Gábor Lugosi, Gergely Neu:
Prediction by random-walk perturbation. COLT 2013: 460-473 - [c6]Alexander Zimin, Gergely Neu:
Online learning in episodic Markovian decision processes by relative entropy policy search. NIPS 2013: 1583-1591 - [i3]Luc Devroye, Gábor Lugosi, Gergely Neu:
Prediction by Random-Walk Perturbation. CoRR abs/1302.5797 (2013) - [i2]Gergely Neu, Gábor Bartók:
An efficient algorithm for learning with semi-bandit feedback. CoRR abs/1305.2732 (2013) - 2012
- [c5]Gergely Neu, András György, Csaba Szepesvári:
The adversarial stochastic shortest path problem with unknown transition probabilities. AISTATS 2012: 805-813 - [i1]Gergely Neu, Csaba Szepesvári:
Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods. CoRR abs/1206.5264 (2012) - 2011
- [c4]András György
Near-optimal rates for limited-delay universal lossy source coding. ISIT 2011: 2218-2222 - 2010
- [c3]Gergely Neu, András György, Csaba Szepesvári:
The Online Loop-free Stochastic Shortest-Path Problem. COLT 2010: 231-243 - [c2]Gergely Neu, András György, Csaba Szepesvári, András Antos:
Online Markov Decision Processes under Bandit Feedback. NIPS 2010: 1804-1812
2000 – 2009
- 2009
- [j1]Gergely Neu
Training parsers by inverse reinforcement learning. Mach. Learn. 77(2-3): 303-337 (2009) - 2007
- [c1]Gergely Neu, Csaba Szepesvári:
Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods. UAI 2007: 295-302
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-12-01 00:16 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: