A forgetting-factor regret metric with exponentially decaying weights is introduced for online zero-sum games, with tracking bounds proven for gradient, Frank-Wolfe, and gradient-free algorithms under time-varying payoffs.
Logarithmic regret algorithms for online convex optimization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Forgetting-Factor Regret for Online Zero-Sum Games
A forgetting-factor regret metric with exponentially decaying weights is introduced for online zero-sum games, with tracking bounds proven for gradient, Frank-Wolfe, and gradient-free algorithms under time-varying payoffs.