no code implementations • 15 Feb 2024 • Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng
Furthermore, the learnability of such problems can fail to be a property of finite character: informally, it cannot be detected by examining finite projections of the problem.
no code implementations • 24 Sep 2023 • Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng
We demonstrate that an agnostic version of the Hall complexity again characterizes error rates exactly, and exhibit an optimal learner using maximum entropy programs.
no code implementations • 24 Nov 2021 • Nathanael Ackerman, Julian Asilis, Jieqi Di, Cameron Freer, Jean-Baptiste Tristan
We introduce definitions of computable PAC learning for binary classification over computable metric spaces.