REVIEW 1 cited by
Optimistic Rates for Learning with a Smooth Loss
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
Optimistic Rates for Learning with a Smooth Loss
read the original abstract
We establish an excess risk bound of O(H R_n^2 + R_n \sqrt{H L*}) for empirical risk minimization with an H-smooth loss function and a hypothesis class with Rademacher complexity R_n, where L* is the best risk achievable by the hypothesis class. For typical hypothesis classes where R_n = \sqrt{R/n}, this translates to a learning rate of O(RH/n) in the separable (L*=0) case and O(RH/n + \sqrt{L^* RH/n}) more generally. We also provide similar guarantees for online and stochastic convex optimization with a smooth non-negative objective.
Forward citations
Cited by 1 Pith paper
-
Tight Generalization Bound for AdaBoost
AdaBoost’s generalization error is Θ(d ln(nγ²/d)/(nγ²) + ln(1/δ)/n), via a new zero-margin-loss bound for voting classifiers.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.