Trading Regret Rate for Computational Efficiency in Online Learning with Limited Feedback thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Trading Regret Rate for Computational Efficiency in Online Learning with Limited Feedback

Published on Aug 26, 20093127 Views

We study low regret algorithms for online learning with limited feedback, where there is an additional constraint on the computational power of the learner. Focusing on multi-armed bandit with side in