REVIEW 1 cited by
Mirror Descent Meets Fixed Share (and feels no regret)
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Mirror descent with an entropic regularizer is known to achieve shifting regret bounds that are logarithmic in the dimension. This is done using either a carefully designed projection or by a weight sharing technique. Via a novel unified analysis, we show that these two approaches deliver essentially equivalent bounds on a notion of regret generalizing shifting, adaptive, discounted, and other related regrets. Our analysis also captures and extends the generalized weight sharing technique of Bousquet and Warmuth, and can be refined in several ways, including improvements for small losses and adaptive tuning of parameters.
Forward citations
Cited by 1 Pith paper
-
Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability
For mixable and exp-concave losses, a continuous fixed-share exponential-weights method attains dynamic regret of order O(d log T (1 + T^{1/3} P_T^{2/3})), improving the known d^{10/3} factor to d.
Discussion (0). Continue with ORCID to comment.