Near-optimal method for highly smooth convex optimization

arXiv1812.08026MaRDI QIDQ6311372FDOQ6311372

Authors: Sébastien Bubeck, Qijia Jiang, Yin Tat Lee, Yuanzhi Li, Aaron Sidford 

Publication date: 19 December 2018

Abstract: We propose a near-optimal method for highly smooth convex optimization. More precisely, in the oracle model where one obtains the $p^{th}$ order Taylor expansion of a function at the query point, we propose a method with rate of convergence $ildeO(1/k^{frac3p+12})$ after $k$ queries to the oracle for any convex function whose $p^{th}$ order derivative is Lipschitz.

This page was built for publication: Near-optimal method for highly smooth convex optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6311372)