Continuous-Time Analysis for Minimax and Bilevel Problems

TL;DR

This paper introduces a unified continuous-time Lyapunov analysis framework for nested optimization problems like minimax and bilevel, providing explicit thresholds and bridging various convexity regimes.

Contribution

It presents the first modular Lyapunov template for continuous-time analysis of nested problems, applicable across multiple problem types and convexity conditions.

Findings

Unified Lyapunov template for minimax and bilevel problems.

Explicit thresholds for time-scale separation avoiding coupled ratio conditions.

Finite-time tracking bounds and Euler discretization insights.

Abstract

We study single-loop gradient-flow dynamics for nested optimization, where the outer variable evolves while auxiliary variables track the inner solution map. While existing analyses typically rely on problem- and condition-specific Lyapunov constructions, we propose, to our knowledge, the first unified Lyapunov template for continuous-time analysis that covers minimax, bilevel via a lifted penalty formulation, and min--min--max. Our proof is modular, built from reusable lemmas that yield a unified characterization of time-scale separation. This characterization bridges regimes from strong convexity/concavity to mere convexity through an error-bound condition, and produces explicit closed-form thresholds that avoid the coupled ratio conditions common in discrete-time analyses. We further compare the penalty dynamics with the ideal hyper-gradient flow, derive a finite-time tracking bound, and discuss an Euler one-step analogue; hypercleaning diagnostics show that the predicted relative time-scale regions remain visible under stable forward-Euler discretization.