57 search results - page 3 / 12 » Active learning in heteroscedastic noise |
JMLR
2010
13 years 5 months ago
2010
We study the problem of active learning with convex loss functions. We prove that even under bounded noise constraints, the minimax rates for proper active learning are often no b...
ALT
2006
Springer
14 years 7 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...
ICDM
2007
IEEE
14 years 5 months ago
2007
IEEE
This paper presents an active learning approach to the problem of systematic noise inference and noise elimination, specifically the inference of Associated Corruption (AC) rules...
COLT
2007
Springer
14 years 5 months ago
2007
Springer
This paper analyzes the potential advantages and theoretical challenges of “active learning” algorithms. Active learning involves sequential sampling procedures that use infor...
ICML
2006
IEEE
14 years 11 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...