Numerical methods in large-scale optimization: inexact oracle and primal-dual analysis
arXiv:2009.04458
Abstract
This is a short summary of already published results on accelerated first and zero-order optimization methods, as well as accelerated methods for problems with linear constraints. This short summary is a requirement for obtaining a degree of doctor of sciences in Russian Federation. The details can be found in the papers listed in the introduction.
References in corpus (3)
- Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn's Algorithm
- An Accelerated Proximal Coordinate Gradient Method and its Application to Regularized Empirical Risk Minimization
- An Accelerated Directional Derivative Method for Smooth Stochastic Convex Optimization