Preprint
Jul 2026
The Price of Hidden Curvature: Improved Lower Bounds for Bandit Convex Optimization
Improved lower bounds are established on the minimax expected regret of stochastic bandit convex optimization for $1$-Lipschitz functions on the $d$-dimensional Euclidean ball, showing that stochastic bandit convex optimization is fundamentally harder than linear bandits.
Nived Rajaraman, Yanjun Han
· 1 citation