Timezone: »

 
Poster
Active Learning with a Drifting Distribution
Liu Yang

Mon Dec 12 10:00 AM -- 02:59 PM (PST) @

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.

Author Information

Liu Yang (CMU)

More from the Same Authors