English

A Note on Nesterov's Accelerated Method in Nonconvex Optimization: a Weak Estimate Sequence Approach

Optimization and Control 2020-06-16 v1

Abstract

We present a variant of accelerated gradient descent algorithms, adapted from Nesterov's optimal first-order methods, for weakly-quasi-convex and weakly-quasi-strongly-convex functions. We show that by tweaking the so-called estimate sequence method, the derived algorithm achieves optimal convergence rate for weakly-quasi-convex and weakly-quasi-strongly-convex in terms of oracle complexity. In particular, for a weakly-quasi-convex function with Lipschitz continuous gradient, we require O(1ε)O(\frac{1}{\sqrt{\varepsilon}}) iterations to acquire an ε\varepsilon-solution; for weakly-quasi-strongly-convex functions, the iteration complexity is O(ln(1ε))O\left( \ln\left(\frac{1}{\varepsilon}\right) \right). Furthermore, we discuss the implications of these algorithms for linear quadratic optimal control problem.

Keywords

Cite

@article{arxiv.2006.08548,
  title  = {A Note on Nesterov's Accelerated Method in Nonconvex Optimization: a Weak Estimate Sequence Approach},
  author = {Jingjing Bu and Mehran Mesbahi},
  journal= {arXiv preprint arXiv:2006.08548},
  year   = {2020}
}
R2 v1 2026-06-23T16:20:35.547Z