A regularized online Newton method achieves polylogarithmic regret in convex bandits with linear vanishing noise under quadratic growth.
Online convex optimization in the bandit setting: Gradient descent without a gradient
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Regularized Online Newton Method for Stochastic Convex Bandits with Linear Vanishing Noise
A regularized online Newton method achieves polylogarithmic regret in convex bandits with linear vanishing noise under quadratic growth.