908 search results - page 5 / 182 » Interactive regret minimization |
112
click to vote
COLT
2010
Springer
14 years 9 months ago
2010
Springer
In standard online learning, the goal of the learner is to maintain an average loss that is "not too big" compared to the loss of the best-performing function in a fixed...
COLT
2004
Springer
15 years 3 months ago
2004
Springer
We investigate label efficient prediction, a variant, proposed by Helmbold and Panizza, of the problem of prediction with expert advice. In this variant, the forecaster, after gues...
101
click to vote
COLT
2008
Springer
15 years 1 months ago
2008
Springer
Standard no-internal-regret (NIR) algorithms compute a fixed point of a matrix, and hence typically require O(n3 ) run time per round of learning, where n is the dimensionality of...
68
Voted
COLT
2008
Springer
15 years 1 months ago
2008
Springer
ICML
2009
IEEE
16 years 14 days ago
2009
IEEE
We study online learning in an oblivious changing environment. The standard measure of regret bounds the difference between the cost of the online learner and the best decision in...