András Antos

27 papers A* 3B 2Journal 17Unranked 4
YearRankTypeTitle / Venue / Authors
2025 J jnl
BandiK: Efficient Multi-Task Decomposition Using a Multi-Bandit Framework.
CoRR
András Millinghoffer, András Formanek, András Antos, Péter Antal
2025 J jnl
Semi-overlapping Multi-bandit Best Arm Identification for Sequential Support Network Learning.
CoRR
András Antos, András Millinghoffer, Péter Antal
2024 — conf
Boosting Multitask Decomposition: Directness, Sequentiality, Subsampling, Cross-Gradients.
AIME (1)
András Millinghoffer, Mátyás Antal, Márk Marosi, András Formanek, András Antos, Péter Antal
2015 J jnl
Adaptive strategy for stratified Monte Carlo sampling.
J. Mach. Learn. Res.
Alexandra Carpentier, Rémi Munos, András Antos
2015 J jnl
Upper-Confidence-Bound Algorithms for Active Learning in Multi-Armed Bandits.
CoRR
Alexandra Carpentier, Alessandro Lazaric, Mohammad Ghavamzadeh, Rémi Munos, Peter Auer, András Antos
2014 J jnl
Online Markov Decision Processes Under Bandit Feedback.
IEEE Trans. Autom. Control.
Gergely Neu, András György, Csaba Szepesvári, András Antos
2013 J jnl
Toward a classification of finite partial-monitoring games.
Theor. Comput. Sci.
András Antos, Gábor Bartók, Dávid Pál, Csaba Szepesvári
2012 J jnl
On Codecell Convexity of Optimal Multiresolution Scalar Quantizers for Continuous Sources.
IEEE Trans. Inf. Theory
András Antos
2011 J jnl
Non-trivial two-armed partial-monitoring games are bandits
CoRR
András Antos, Gábor Bartók, Csaba Szepesvári
2011 J jnl
Toward a Classification of Finite Partial-Monitoring Games
CoRR
András Antos, Gábor Bartók, Dávid Pál, Csaba Szepesvári
2010 J jnl
Active learning in heteroscedastic noise.
Theor. Comput. Sci.
András Antos, Varun Grover, Csaba Szepesvári
2010 — conf
Online Markov Decision Processes under Bandit Feedback.
NIPS
Gergely Neu, András György, Csaba Szepesvári, András Antos
2008 B conf
Active Learning in Multi-armed Bandits.
ALT
András Antos, Varun Grover, Csaba Szepesvári
2008 J jnl
Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path.
Mach. Learn.
András Antos, Csaba Szepesvári, Rémi Munos
2007 — conf
Fitted Q-iteration in continuous action-space MDPs.
NIPS
András Antos, Rémi Munos, Csaba Szepesvári
2006 A* conf
Learning Near-Optimal Policies with Bellman-Residual Minimization Based Fitted Policy Iteration and a Single Sample Path.
COLT
András Antos, Csaba Szepesvári, Rémi Munos
2005 A* conf
Improved Minimax Bounds on the Test and Training Distortion of Empirically Designed Vector Quantizers.
COLT
András Antos
2005 J jnl
Improved minimax bounds on the test and training distortion of empirically designed vector quantizers.
IEEE Trans. Inf. Theory
András Antos
2005 J jnl
Individual convergence rates in empirical vector quantizer design.
IEEE Trans. Inf. Theory
András Antos, László Györfi, András György
2004 B conf
Improved convergence rates in empirical vector quantizer design.
ISIT
András Antos, László Györfi, András György
2002 J jnl
Data-dependent margin-based generalization bounds for classification.
J. Mach. Learn. Res.
András Antos, Balázs Kégl, Tamás Linder, Gábor Lugosi
2002 J jnl
Lower bounds for the rate of convergence in nonparametric pattern recognition.
Theor. Comput. Sci.
András Antos
2000 — —
Performance limits of nonparametric estimators
András Antos
1999 J jnl
Lower Bounds for Bayes Error Estimation.
IEEE Trans. Pattern Anal. Mach. Intell.
András Antos, Luc Devroye, László Györfi
1999 — conf
Lower Bounds on the Rate of Convergence of Nonparametric Pattern Recognition.
EuroCOLT
András Antos
1998 J jnl
Strong Minimax Lower Bounds for Learning.
Mach. Learn.
András Antos, Gábor Lugosi
1996 A* conf
Strong Minimax Lower Bounds for Learning.
COLT
András Antos, Gábor Lugosi