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
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.
Forward citations
Cited by 1 Pith paper
-
Decentralized Parameter-Free Online Learning with Compressed Gossip
DECO-EF achieves the first expected comparator-adaptive sublinear network-regret bounds for parameter-free decentralized online learning under compressed communication.
Discussion (0). Continue with ORCID to comment.