vix.ing · top · new · best · stats · spec

Sequential Subspace Optimization for Quasar-Convex Optimization Problems with Inexact Gradient

2021/08/13 by Ilya Kuruzov, Kuruzov, Ilya, Fedor Stonyakin +1
Computer Science · Engineering · Mathematics · #Advanced Optimization Algorithms Research #FOS: Mathematics #Optimization and Control (math.OC) #Optimization and Variational Analysis #Sparse and Compressive Sensing Techniques

paper · pdf · doi:10.48550/arxiv.2108.06297

openalex publication_date 2021/08/13 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

Abstract

It is well-known that accelerated gradient first-order methods possess optimal complexity estimates for the class of convex smooth minimization problems. In many practical situations it makes sense to work with inexact gradient information. However, this can lead to an accumulation of corresponding inexactness in the theoretical estimates of the rate of convergence. We propose some modification of the Sequential Subspace Optimization Method (SESOP) for minimization problems with quasar-convex functions with inexact gradient. A theoretical result is obtained indicating the absence of accumulation of gradient inexactness. A numerical implementation of the proposed version of the SESOP method and its comparison with the known Similar Triangle Method with an inexact gradient is carried out.

Related