English

Near-optimal method for highly smooth convex optimization

Optimization and Control 2019-06-25 v2

Abstract

We propose a near-optimal method for highly smooth convex optimization. More precisely, in the oracle model where one obtains the pthp^{th} order Taylor expansion of a function at the query point, we propose a method with rate of convergence O~(1/k3p+12)\tilde{O}(1/k^{\frac{ 3p +1}{2}}) after kk queries to the oracle for any convex function whose pthp^{th} order derivative is Lipschitz.

Keywords

Cite

@article{arxiv.1812.08026,
  title  = {Near-optimal method for highly smooth convex optimization},
  author = {Sébastien Bubeck and Qijia Jiang and Yin Tat Lee and Yuanzhi Li and Aaron Sidford},
  journal= {arXiv preprint arXiv:1812.08026},
  year   = {2019}
}

Comments

15 pages

R2 v1 2026-06-23T06:47:59.267Z