Abstract--Recently Kutin and Niyogi investigated several notions of algorithmic stability--a property of a learning map conceptually similar to continuity--showing that training-st...
We study some stability properties of algorithms which minimize (or almost-minimize) empirical error over Donsker classes of functions. We show that, as the number n of samples gr...
Experimental analysis of agent strategies in multiagent systems presents a tradeoff between granularity and statistical confidence. Collecting a large amount of data about each s...
The problem of characterizing learnability is the most basic question of statistical learning theory. A fundamental and long-standing answer, at least for the case of supervised c...
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...