OCAIMay 19, 2021

Trilevel and Multilevel Optimization using Monotone Operator Theory

arXiv:2105.09407v213 citations
AI Analysis

This work addresses optimization challenges in nested convex problems, which is incremental as it builds on existing fixed-point theory for multi-level settings.

The paper tackles the problem of solving a general class of multi-level optimization problems, particularly trilevel cases with smooth and non-smooth terms, by presenting a first-order algorithm based on fixed-point theory and analyzing its convergence rates in various parameter regimes.

We consider rather a general class of multi-level optimization problems, where a convex objective function is to be minimized subject to constraints of optimality of nested convex optimization problems. As a special case, we consider a trilevel optimization problem, where the objective of the two lower layers consists of a sum of a smooth and a non-smooth term.~Based on fixed-point theory and related arguments, we present a natural first-order algorithm and analyze its convergence and rates of convergence in several regimes of parameters.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes