András Antos' publications

JOURNAL PAPERS

• A. Antos, G. Bartók, D. Pál, and Cs. Szepesvári, "Toward a classification of finite partial-monitoring games," (?k) Theoretical Computer Science, special issue: Algorithmic Learning Theory (ALT 2010), 2012 (accepted). Also: arXiv

• A. Antos, "On codecell convexity of optimal multiresolution scalar quantizers for continuous sources," (216k) IEEE Transactions on Information Theory, 58 (2): Feb 2012. , (in print). Abstract

• A. Antos, V. Grover, and Cs. Szepesvári, "Active learning in heteroscedastic noise," (354k) Theoretical Computer Science, special issue: Algorithmic Learning Theory (ALT 2008) (Eds.: Y. Freund, L. Györfi, Gy. Turán, T. Zeugmann), 411 (29-30): 2712-2728, June 2010. Abstract

• A. Antos, Cs. Szepesvári, and R. Munos, "Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path," Machine Learning, 71 (1): 89-129, Apr 2008. Abstract

• A. Antos, "Improved minimax bounds on the test and training distortion of empirically designed vector quantizers," IEEE Transactions on Information Theory, 51 (11): 4022-4032, Nov 2005. Abstract

• A. Antos, L. Györfi, and A. György, "Individual convergence rates in empirical vector quantizer design," IEEE Transactions on Information Theory, 51 (11): 4013-4022, Nov 2005. Abstract

• A. Antos and M. Pintér, "Nemparaméteres függvénybecslések" (Nonparametric function estimation) (216k), Alkalmazott Matematikai Lapok, 21 (1):99-129, 2004.

• A. Antos, B. Kégl, T. Linder, and G. Lugosi, "Data-dependent margin-based generalization bounds for classification," (292k) Journal of Machine Learning Research, 3 (1):73-98, 2002. Abstract

• A. Antos and I. Kontoyiannis, "Convergence properties of functional estimates for discrete distributions," (242k) Random Structures and Algorithms, special issue: Average-Case Analysis of Algorithms, 19 (3-4):163-193, 2002. Abstract

• A. Antos, "Lower bounds for the rate of convergence in nonparametric pattern recognition," Theoretical Computer Science, 284 (1):3-24, 2002. Abstract Also presented at: Statistics and Operation Research Seminars, Universitat Pompeu Fabra, Barcelona, Spain, Nov 11, 1999.

• A. Antos, L. Györfi, and M. Kohler, "Lower bounds on the rate of convergence of nonparametric regression estimates," Journal of Statistical Planning and Inference, 83:91-100, 2000. Preprint 98-11, Universität Stuttgart, Math. Inst. A, D-70511 Stuttgart, June 1998. Abstract

• A. Antos, L. Devroye, and L. Györfi, "Lower bounds for Bayes error estimation," IEEE Transactions on Pattern Analysis and Machine Intelligence, 21:643-645, 1999. Abstract

• A. Antos and G. Lugosi, "Strong minimax lower bounds for learning," Machine Learning, 30:31-56, 1998. Economics Working Paper 197, Universitat Pompeu Fabra, 08005 Barcelona, January 1997 (email). Abstract

• A. Antos, "Rekurzív számháromszögek periodicitásáról" (About the periodicity of recursive number triangles), Elektronikai technológia - Mikrotechnika, 30:212-213, 1992.

CHAPTERS OF BOOKS

• A. Antos and L. Devroye, "Rawa trees," In Mathematics and Computer Science: Algorithms, Trees, Combinatorics and Probabilities, Trends in Mathematics, 3-15 (Eds.: D. Gardy and A. Mokkadem) Birkhäuser Verlag, Basel, 2000. Abstract

REFEREED CONFERENCE PAPERS

• G. Neu, A. György, Cs. Szepesvári, and A. Antos, "Online Markov decision processes under bandit feedback," Twenty-Fourth Annual Conference on Neural Information Processing Systems (NIPS 2010), Vancouver, B.C., December 6-9, 2010. Abstract

• A. Antos, V. Grover, and Cs. Szepesvári, "Active learning in multi-armed bandits," (..k) In 19th International Conference on Algorithmic Learning Theory, ALT 2008, Proceedings, Budapest, Hungary, October 13-16, 2008. Eds.: Y. Freund, L. Györfi, Gy. Turán, T. Zeugmann, Springer-Verlag, Berlin, Heidelberg, October 2008 (v.5254 of LNCS/LNAI), pages 287-302. Abstract

• A. Antos, R. Munos, and Cs. Szepesvári, "Fitted Q-iteration in continuous action-space MDPs," Twenty-First Annual Conference on Neural Information Processing Systems (NIPS 2007), Vancouver, B.C., December 3-6, 2007. Poster. Abstract

• A. Antos, Cs. Szepesvári, and R. Munos, "Value-iteration based fitted policy iteration: learning with a single trajectory," In 2007 IEEE Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 2007), Honolulu, Hawaii, April 1-5, 2007. IEEE, Apr 2007, pages 330-337. Abstract

• A. Antos, Cs. Szepesvári, and R. Munos, "Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path," (216k) In The Nineteenth Annual Conference on Learning Theory, COLT 2006, Proceedings, Pittsburgh, PA, June 22-25, 2006. Eds.: G. Lugosi, H.U. Simon, Springer-Verlag, Berlin, Heidelberg, June 2006 (v.4005 of LNCS/LNAI), pages 574-588. Abstract Also presented at: Mathematical Foundations of Learning Theory -II (Poster), Paris, France, May 31-June 3, 2006. Extended version with detailed proofs: ps.gz

• A. Antos, "Improved minimax bounds on the test and training distortion of empirically designed vector quantizers," In The Eighteenth Annual Conference on Learning Theory, COLT'05, Proceedings, Bertinoro, Italy, June 27-30, 2005. Eds.: P. Auer, R. Meir, Springer-Verlag, Berlin, Heidelberg, June 2005 (v.3559 of LNCS/LNAI), pages 531-544. Abstract Also presented at: Groupe de Travail Apprentissage (Training Working Group), Ecole Normale Supérieure, Paris, France, Nov 20, 2006. Watch/listen the talk here! and as Invited Talk at: Artificial Intelligence Seminar, University of Alberta, Edmonton, AB, Canada, Apr 20, 2007.

• A. Antos, L. Györfi, and A. György, "Improved convergence rates in empirical vector quantizer design," In Proceedings 2004 IEEE International Symposium on Information Theory (ISIT 2004), Chicago, IL, June 27-July 2, 2004. page 301. Abstract

• A. Antos, I. Kontoyiannis, "Estimating the entropy of discrete distributions," In Proceedings 2001 IEEE International Symposium on Information Theory (ISIT 2001), Washington, D.C., June 24-29, 2001. page 45. Abstract Also presented at: Second Stochastics Seminar Stuttgart-Budapest, Universität Stuttgart, Stuttgart, Germany, Oct 9 and 12, 2000.

• A. Antos, "On nonparametric estimates of the expectation," In Limit Theorems in Probability and Statistics (A Volume in Honour of Pál Révész) (Fourth Hungarian Colloquium on Limit Theorems in Probability and Statistics), Balatonlelle, Hungary, June 28-July 2, 1999. Eds.: I. Berkes, E. Csáki, M. Csörgõ, J. Bolyai Mathematical Sociaty, Budapest, 2002, pages 101-112. Abstract
  Also presented at: Seminars, Technical University of Budapest, Budapest, Hungary, Oct 4-6, 1999.

• A. Antos, "Lower bounds on the rate of convergence of nonparametric pattern recognition," In Computational Learning Theory: 4th European Conference, EuroCOLT'99, Proceedings, Nordkirchen, Germany, March 29-31, 1999. Eds.: P. Fischer, H.U. Simon, Springer, Berlin, 1999 (v.1572 of LNCS/LNAI), pages 241-252. Abstract (IFIP WG 1.4: Student Author Award) Also presented at: Austrian, Hungarian and Slovenian Joint Meeting of Young Statisticians, Piran, Slovenia, Oct 1998 and Seminars, Universität Stuttgart, Stuttgart, Germany, Apr 1, 1999.

• A. Antos and G. Lugosi, "Strong minimax lower bounds for learning," In Proceedings of the Ninth Annual Conference on Computational Learning Theory (COLT'96), Desenzano del Garda, Italy, June 28-July 1, 1996. Eds.: A. Blum, M. Kearns, Association for Computing Machinery, New York, 1996, pages 303-309. Abstract

OTHER CONFERENCE PUBLICATIONS

• A. Antos and L. Devroye, "Rawa trees," 10th European Young Statisticians Meeting (EYSM'97), Warsaw, Poland, August 18-22, 1997. pages 16-17. Abstract
  Also presented at: ALCOM Seminars, Universitat Politecnica de Catalunya, Barcelona, Spain, June 10, 1997.

• A. Antos, F. Birloni and S. Brokhauzer "Battle for supremacy", BME TTTK Tudományos Diákköri Konferencia (Scientific Conference of Students in the Faculty of Natural and Social Sciences), Budapest, Nov 1993, advisor: ???.

• A. Antos, "Rekurzív számháromszögek periodicitásáról" (About the periodicity of recursive number triangles), BME VIK Tudományos Diákköri Konferencia (Scientific Conference of Students in the Faculty of Electrical Engineering), Budapest, Nov 1991, adviser: A. Recski.

THESES

• A. Antos, Performance limits of nonparametric estimators (241k). Ph.D. Thesis, Technical University of Budapest, Budapest, May 1999, adviser: L. Györfi. Theses.

• A. Antos, Függvényosztályok tulajdonságai és szerepe az alakfelismerésben (Properties of classes of functions and their roles in pattern recognition). M.Sc. Thesis, Technical University of Budapest, Budapest, June 1995, adviser: G. Lugosi.

PREPRINTS

• A. Antos, G. Bartók, and Cs. Szepesvári, "All non-trivial 2-armed partial-monitoring games are bandits," (?k) , 2011 (under preparation).

Back to the Home Page

Updated: Jan 10, 2012