New algorithms achieve regret roughly ||u||G(sqrt(T)+k) under adversarial gradient corruption in unconstrained online convex optimization, with a matching lower bound when G is known.
Stochastic dueling bandits with adversarial corruption
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
-
Unconstrained Robust Online Convex Optimization
New algorithms achieve regret roughly ||u||G(sqrt(T)+k) under adversarial gradient corruption in unconstrained online convex optimization, with a matching lower bound when G is known.