Pith. sign in

REVIEW 1 cited by

Online Convex Optimization with Unconstrained Domains and Losses

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

arxiv 1703.02622 v1 pith:K4YMEZ5E submitted 2017-03-07 cs.LG stat.ML

classification cs.LGstat.ML
keywords optimizationboundrequirerescaledexpalgorithmalgorithmsconvexfunctions
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose an online convex optimization algorithm (RescaledExp) that achieves optimal regret in the unconstrained setting without prior knowledge of any bounds on the loss functions. We prove a lower bound showing an exponential separation between the regret of existing algorithms that require a known bound on the loss functions and any algorithm that does not require such knowledge. RescaledExp matches this lower bound asymptotically in the number of iterations. RescaledExp is naturally hyperparameter-free and we demonstrate empirically that it matches prior optimization algorithms that require hyperparameter optimization.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Decentralized Parameter-Free Online Learning with Compressed Gossip

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    DECO-EF achieves the first expected comparator-adaptive sublinear network-regret bounds for parameter-free decentralized online learning under compressed communication.

Pith tools