NeurIPS2020
Acceleration with a Ball Optimization Oracle
Yair Carmon, Arun Jambulapati, Qijia Jiang, Yujia Jin, Yin Tat Lee, Aaron Sidford, Kevin Tian
被引用 51 次
摘要
Consider an oracle which takes a point and returns the minimizer of a convex function in an ball of radius around . It is straightforward to show that roughly calls to the oracle suffice to find an -approximate minimizer of in an unit ball. Perhaps surprisingly, this is not optimal: we design an accelerated algorithm which attains an -approximate minimizer with roughly oracle queries, and give a matching lower bound. Further, we implement ball optimization oracles for functions with locally stable Hessians using a variant of Newton's method. The resulting algorithm applies to a number of problems of practical and theoretical import, improving upon previous results for logistic and regression and achieving guarantees comparable to the state-of-the-art for regression.