15 search results - page 1 / 3 » On the Stability of Empirical Risk Minimization in the Prese... |
CORR
2010
Springer
13 years 4 months ago
2010
Springer
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...
JMLR
2006
13 years 4 months ago
2006
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...
ATAL
2009
Springer
13 years 11 months ago
2009
Springer
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...
JMLR
2010
12 years 11 months ago
2010
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...
NIPS
2007
13 years 6 months ago
2007
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...