256 search results - page 5 / 52 » On a Generalized Notion of Mistake Bounds |
ML
2007
ACM
13 years 7 months ago
2007
ACM
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
JMLR
2002
13 years 7 months ago
2002
A fundamental open problem in computational learning theory is whether there is an attribute efficient learning algorithm for the concept class of decision lists (Rivest, 1987; Bl...
JMLR
2012
11 years 10 months ago
2012
We prove logarithmic regret bounds that depend on the loss L∗ T of the competitor rather than on the number T of time steps. In the general online convex optimization setting, o...
JMLR
2002
13 years 7 months ago
2002
We define notions of stability for learning algorithms and show how to use these notions to derive generalization error bounds based on the empirical error and the leave-one-out e...
ECCC
2008
13 years 7 months ago
2008
One way to quantify how dense a multidag is in long paths is to find the largest n, m such that whichever n edges are removed, there is still a path from an original input to an ...