We discuss two approaches for choosing a strategy in a two-player game. We suppose that the game is played a large number of rounds, which allows the players to use observations o...
Empirical risk minimization offers well-known learning guarantees when training and test data come from the same domain. In the real world, though, we often wish to adapt a classi...
John Blitzer, Koby Crammer, Alex Kulesza, Fernando...
This work characterizes the generalization ability of algorithms whose predictions are linear in the input vector. To this end, we provide sharp bounds for Rademacher and Gaussian...
Motivated by applications in computer graphics, visualization, and scienti c computation, we study the computational complexity of the following problem: Given a set S of n points...
T ORDER REGRESSION (EXTENDED ABSTRACT) Kurt Driessensa Saso Dzeroskib a Department of Computer Science, University of Waikato, Hamilton, New Zealand (kurtd@waikato.ac.nz) b Departm...