Work

Near-optimal method for highly smooth convex optimization

Year: 2018

Type: preprint

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 $\tilde{O}(1/k^{\frac{ 3p +1}{2}})$ after $k$ queries to the oracle for any convex function whose $p^{th}$ order derivative is Lipschitz.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1812.08026

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

Institutions: Microsoft (United States), Stanford University, University of Washington, Carnegie Mellon University

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2964511245

Cites:

Cited by: 28

Related to: 10