OGD achieves O(sqrt(T)) regret on hidden-convex losses via sharper algorithmic equivalence under Hessian compatibility, with a matching lower bound and O(T^{3/4}) bandit extension.
Unveiling hidden convexity in deep learning: A sparse signal processing perspective.arXiv preprint arXiv:2603.23831,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback
OGD achieves O(sqrt(T)) regret on hidden-convex losses via sharper algorithmic equivalence under Hessian compatibility, with a matching lower bound and O(T^{3/4}) bandit extension.