English

A Fast and Convergent Proximal Algorithm for Regularized Nonconvex and Nonsmooth Bi-level Optimization

Machine Learning 2022-06-06 v2 Optimization and Control

Abstract

Many important machine learning applications involve regularized nonconvex bi-level optimization. However, the existing gradient-based bi-level optimization algorithms cannot handle nonconvex or nonsmooth regularizers, and they suffer from a high computation complexity in nonconvex bi-level optimization. In this work, we study a proximal gradient-type algorithm that adopts the approximate implicit differentiation (AID) scheme for nonconvex bi-level optimization with possibly nonconvex and nonsmooth regularizers. In particular, the algorithm applies the Nesterov's momentum to accelerate the computation of the implicit gradient involved in AID. We provide a comprehensive analysis of the global convergence properties of this algorithm through identifying its intrinsic potential function. In particular, we formally establish the convergence of the model parameters to a critical point of the bi-level problem, and obtain an improved computation complexity O(κ3.5ϵ2)\mathcal{O}(\kappa^{3.5}\epsilon^{-2}) over the state-of-the-art result. Moreover, we analyze the asymptotic convergence rates of this algorithm under a class of local nonconvex geometries characterized by a {\L}ojasiewicz-type gradient inequality. Experiment on hyper-parameter optimization demonstrates the effectiveness of our algorithm.

Keywords

Cite

@article{arxiv.2203.16615,
  title  = {A Fast and Convergent Proximal Algorithm for Regularized Nonconvex and Nonsmooth Bi-level Optimization},
  author = {Ziyi Chen and Bhavya Kailkhura and Yi Zhou},
  journal= {arXiv preprint arXiv:2203.16615},
  year   = {2022}
}

Comments

20 pages, 1 figure, 1 table

R2 v1 2026-06-24T10:32:31.060Z