Inspired by applications in pricing and con- tract design, we study the maximization of one- sided Lipschitz functions, which only provide the.
We study the maximization of one-sided Lipschitz functions, which only provide the (weaker) guarantee that they do not grow too quickly in one direction.
Jul 23, 2023 · We show that it is possible to learn a maximizer for such a function while incurring O(log log T) total regret (with a universal constant ...
Inspired by applications in pricing and contract design, we study the maximization of one-sided Lipschitz functions, which only provide the (weaker) ...
Optimal no-regret learning for one-sided lipschitz functions. P Dütting, G Guruganesh, J Schneider, JR Wang. International Conference on Machine Learning ...
Optimal No-Regret Learning for One-Sided Lipschitz Functions Paul Dütting, Guru Guruganesh, Jon Schneider, Joshua Wang International Conference on Machine ...
Optimal No-Regret Learning for One-Sided Lipschitz Functions [PMLR]. In the 40th Annual International Conference on Machine Learning (ICML 2023). G ...
NeurIPS 2023. Optimal No-Regret Learning for One-Sided Lipschitz Functions with Paul Duetting, Guru Guruganesh, and Joshua Wang. ICML 2023. U-Calibration ...
Optimal No-Regret Learning for One-Sided Lipschitz Functions Paul Dütting, Guru Guruganesh, Jon Schneider, Joshua Wang International Conference on Machine ...
In online convex optimization (OCO), Lipschitz continuity of the functions is commonly assumed in order to obtain sublinear regret.
Missing: Optimal Sided