59 search results - page 4 / 12 » Minimax Bounds for Active Learning |
ALT
2006
Springer
14 years 5 months ago
2006
Springer
Most of the existing active learning algorithms are based on the realizability assumption: The learner’s hypothesis class is assumed to contain a target function that perfectly c...
COLT
2010
Springer
13 years 6 months ago
2010
Springer
We study the regret of an online learner playing a multi-round game in a Banach space B against an adversary that plays a convex function at each round. We characterize the minima...
NIPS
2007
13 years 10 months ago
2007
We present a simple, agnostic active learning algorithm that works for any hypothesis class of bounded VC dimension, and any data distribution. Our algorithm extends a scheme of C...
ALT
2010
Springer
13 years 10 months ago
2010
Springer
Online learning and kernel learning are two active research topics in machine learning. Although each of them has been studied extensively, there is a limited effort in addressing ...
COLT
2010
Springer
13 years 6 months ago
2010
Springer
We consider a bandit problem which involves sequential sampling from two populations (arms). Each arm produces a noisy reward realization which depends on an observable random cov...