A modular algorithm for online convex-concave optimization achieves near-optimal dynamic duality gap bounds by combining adaptive experts with a multi-predictor aggregator.
John von Neumann
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Modular Algorithm for Non-Stationary Online Convex-Concave Optimization
A modular algorithm for online convex-concave optimization achieves near-optimal dynamic duality gap bounds by combining adaptive experts with a multi-predictor aggregator.