65 search results - page 1 / 13 » A bound on the label complexity of agnostic active learning |
ICML
2007
IEEE
14 years 5 months ago
2007
IEEE
We study the label complexity of pool-based active learning in the agnostic PAC model. Specifically, we derive general bounds on the number of label requests made by the A2 algori...
NIPS
2007
13 years 6 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...
PKDD
2010
Springer
13 years 2 months ago
2010
Springer
Active learning [1] is a branch of Machine Learning in which the learning algorithm, instead of being directly provided with pairs of problem instances and their solutions (their l...
ICML
2006
IEEE
14 years 5 months ago
2006
IEEE
We state and analyze the first active learning algorithm which works in the presence of arbitrary forms of noise. The algorithm, A2 (for Agnostic Active), relies only upon the ass...
NIPS
2004
13 years 6 months ago
2004
act out the core search problem of active learning schemes, to better understand the extent to which adaptive labeling can improve sample complexity. We give various upper and low...