| Mode | Name | Size | |
|---|
| -rw-r--r-- | 0408007v1 | 174982 | logstatsplain |
| -rw-r--r-- | Abernethy - An efficient algorithm for bandit linear optimization, 2008.pdf | 2959246 | logstatsplain |
| -rw-r--r-- | Abernethy, Hazan, Rakhlin - An efficient algorithm for bandit linear optimization.pdf | 343630 | logstatsplain |
| -rw-r--r-- | An optimal high probability algorithm for the contextual bandit problem, 2010.pdf | 165877 | logstatsplain |
| -rw-r--r-- | Audibert, Bubeck - Minmax policies for bandit games.pdf | 538911 | logstatsplain |
| -rw-r--r-- | Audibert, Bubeck - Regret bounds and minimax policies under partial monitoring, 2010.pdf | 332528 | logstatsplain |
| -rw-r--r-- | Aueur, Cesa, Fischer - Finite-time analysis of the multiarmed bandit problem, 2002.pdf | 207856 | logstatsplain |
| -rw-r--r-- | Aueur, Cesa, Freund, Schapire - The nonstochastic multiarmed bandit problem, 2002.pdf | 275770 | logstatsplain |
| -rw-r--r-- | Cesa, Lugosi - Prediction, learning and games, 2006.pdf | 3706034 | logstatsplain |
| -rw-r--r-- | Cesa, Lugosi, Stoltz - Minimizing regret with label efficient prediction, 2005.pdf | 375956 | logstatsplain |
| -rw-r--r-- | Freedman - On tail probabilities for martingales, 1972.pdf | 1476654 | logstatsplain |
| -rw-r--r-- | Massart - Concentration Inequalities and Model Selection, 2003.pdf | 1584747 | logstatsplain |
| -rw-r--r-- | Stoltz - Incomplete information and internal regret in prediction of individual sequences, 2005.pdf | 1957541 | logstatsplain |
| -rw-r--r-- | TCS08.pdf | 449972 | logstatsplain |
| -rw-r--r-- | Zinkevich - Online convex programming and generalized infinitesimal gradient ascent (technical), 2003.pdf | 266814 | logstatsplain |
| -rw-r--r-- | Zinkevich - Online convex programming and generalized infinitesimal gradient ascent, 2003.pdf | 228882 | logstatsplain |
