A new look at shifting regret

Details A new look at shifting regret A new look at shifting regret

2012-02-15

arxiv.org/abs/1202.3323v1

Computer Science

Learning

Scientific paper

We investigate extensions of well-known online learning algorithms such as fixed-share of Herbster and Warmuth (1998) or the methods proposed by Bousquet and Warmuth (2002). These algorithms use weight sharing schemes to perform as well as the best sequence of experts with a limited number of changes. Here we show, with a common, general, and simpler analysis, that weight sharing in fact achieves much more than what it was designed for. We use it to simultaneously prove new shifting regret bounds for online convex optimization on the simplex in terms of the total variation distance as well as new bounds for the related setting of adaptive regret. Finally, we exhibit the first logarithmic shifting bounds for exp-concave loss functions on the simplex.

Affiliated with

Also associated with

No associations

Rating

A new look at shifting regret does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A new look at shifting regret, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A new look at shifting regret will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-557904