Active Learning with a Drifting DistributionDownload PDFOpen Website

2011 (modified: 11 Nov 2022)NIPS 2011Readers: Everyone
Abstract: We study the problem of active learning in a stream-based setting, allowing the distribution of the examples to change over time. We prove upper bounds on the number of prediction mistakes and number of label requests for established disagreement-based active learning algorithms, both in the realizable case and under Tsybakov noise. We further prove minimax lower bounds for this problem.
0 Replies

Loading