Search the dblp DataBase

Publications of Author

1. András Antos
   Improved Minimax Bounds on the Test and Training Distortion of Empirically Designed Vector Quantizers. [Citation Graph (0, 0)][DBLP]
   COLT, 2005, pp:531-544 [Conf]
   
2. András Antos, Gábor Lugosi
   Strong Minimax Lower Bounds for Learning. [Citation Graph (0, 0)][DBLP]
   COLT, 1996, pp:303-309 [Conf]
   
3. András Antos, Csaba Szepesvári, Rémi Munos
   Learning Near-Optimal Policies with Bellman-Residual Minimization Based Fitted Policy Iteration and a Single Sample Path. [Citation Graph (0, 0)][DBLP]
   COLT, 2006, pp:574-588 [Conf]
   
4. András Antos
   Lower Bounds on the Rate of Convergence of Nonparametric Pattern Recognition. [Citation Graph (0, 0)][DBLP]
   EuroCOLT, 1999, pp:241-252 [Conf]
   
5. András Antos, Balázs Kégl, Tamás Linder, Gábor Lugosi
   Data-dependent margin-based generalization bounds for classification. [Citation Graph (0, 0)][DBLP]
   Journal of Machine Learning Research, 2002, v:3, n:, pp:73-98 [Journal]
   
6. András Antos, Gábor Lugosi
   Strong Minimax Lower Bounds for Learning. [Citation Graph (0, 0)][DBLP]
   Machine Learning, 1998, v:30, n:1, pp:31-56 [Journal]
   
7. András Antos, Luc Devroye, László Györfi
   Lower Bounds for Bayes Error Estimation. [Citation Graph (0, 0)][DBLP]
   IEEE Trans. Pattern Anal. Mach. Intell., 1999, v:21, n:7, pp:643-645 [Journal]
   
8. András Antos
   Lower bounds for the rate of convergence in nonparametric pattern recognition. [Citation Graph (0, 0)][DBLP]
   Theor. Comput. Sci., 2002, v:284, n:1, pp:3-24 [Journal]
   
9. András Antos
   Improved minimax bounds on the test and training distortion of empirically designed vector quantizers. [Citation Graph (0, 0)][DBLP]
   IEEE Transactions on Information Theory, 2005, v:51, n:11, pp:4022-4032 [Journal]
   
10. András Antos, László Györfi, A. Gyorgy
    Individual convergence rates in empirical vector quantizer design. [Citation Graph (0, 0)][DBLP]
    IEEE Transactions on Information Theory, 2005, v:51, n:11, pp:4013-4022 [Journal]
    
11. 
    Active Learning in Multi-armed Bandits. [Citation Graph (, )][DBLP]
    
    
12. 
    Fitted Q-iteration in continuous action-space MDPs. [Citation Graph (, )][DBLP]