Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Gergely Neu

Information-Theoretic Generalization Bounds for Stochastic Gradient Descent


Feb 01, 2021
Gergely Neu


  Access Paper or Ask Questions

Logistic $Q$-Learning


Oct 21, 2020
Joan Bas-Serrano, Sebastian Curi, Andreas Krause, Gergely Neu


  Access Paper or Ask Questions

A Unifying View of Optimism in Episodic Reinforcement Learning


Jul 03, 2020
Gergely Neu, Ciara Pike-Burke


  Access Paper or Ask Questions

Online learning in MDPs with linear function approximation and bandit feedback


Jul 03, 2020
Gergely Neu, Julia Olkhovskaya


  Access Paper or Ask Questions

Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits


Feb 01, 2020
Gergely Neu, Julia Olkhovskaya


  Access Paper or Ask Questions

Fast Rates for Online Prediction with Abstention


Jan 28, 2020
Gergely Neu, Nikita Zhivotovskiy

* 19 pages 

  Access Paper or Ask Questions

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


Sep 22, 2019
Joan Bas-Serrano, Gergely Neu


  Access Paper or Ask Questions

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


Jun 19, 2019
Hugo Penedones, Carlos Riquelme, Damien Vincent, Hartmut Maennel, Timothy Mann, Andre Barreto, Sylvain Gelly, Gergely Neu


  Access Paper or Ask Questions

Beating SGD Saturation with Tail-Averaging and Minibatching


Feb 22, 2019
Nicole MĂĽcke, Gergely Neu, Lorenzo Rosasco


  Access Paper or Ask Questions

Bandit Principal Component Analysis


Feb 08, 2019
Wojciech Kotłowski, Gergely Neu


  Access Paper or Ask Questions

Online Influence Maximization with Local Observations


May 28, 2018
Julia Olkhovskaya, Gergely Neu, Gábor Lugosi


  Access Paper or Ask Questions

Iterate averaging as regularization for stochastic gradient descent


Feb 22, 2018
Gergely Neu, Lorenzo Rosasco


  Access Paper or Ask Questions

Boltzmann Exploration Done Right


Nov 07, 2017
Nicolò Cesa-Bianchi, Claudio Gentile, Gábor Lugosi, Gergely Neu


  Access Paper or Ask Questions

On the Hardness of Inventory Management with Censored Demand Data


Oct 16, 2017
Gábor Lugosi, Mihalis G. Markakis, Gergely Neu


  Access Paper or Ask Questions

Algorithmic stability and hypothesis complexity


Aug 03, 2017
Tongliang Liu, Gábor Lugosi, Gergely Neu, Dacheng Tao


  Access Paper or Ask Questions

Fast rates for online learning in Linearly Solvable Markov Decision Processes


Jun 06, 2017
Gergely Neu, Vicenç Gómez


  Access Paper or Ask Questions

A unified view of entropy-regularized Markov decision processes


May 22, 2017
Gergely Neu, Anders Jonsson, Vicenç Gómez


  Access Paper or Ask Questions

Importance weighting without importance weights: An efficient algorithm for combinatorial semi-bandits


Aug 31, 2016
Gergely Neu, Gábor Bartók

* To appear in JMLR 

  Access Paper or Ask Questions

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


Nov 03, 2015
Gergely Neu

* To appear at NIPS 2015 

  Access Paper or Ask Questions

First-order regret bounds for combinatorial semi-bandits


Jun 10, 2015
Gergely Neu

* To appear at COLT 2015 

  Access Paper or Ask Questions

Online learning in MDPs with side information


Jun 26, 2014
Yasin Abbasi-Yadkori, Gergely Neu


  Access Paper or Ask Questions

An efficient algorithm for learning with semi-bandit feedback


May 13, 2013
Gergely Neu, Gábor Bartók

* submitted to ALT 2013 

  Access Paper or Ask Questions

Prediction by Random-Walk Perturbation


Feb 23, 2013
Luc Devroye, Gábor Lugosi, Gergely Neu


  Access Paper or Ask Questions

Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods


Jun 20, 2012
Gergely Neu, Csaba Szepesvari

* Appears in Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence (UAI2007) 

  Access Paper or Ask Questions