DeepAI AI Chat
Log In Sign Up

A Penalty Based Method for Communication-Efficient Decentralized Bilevel Programming

11/08/2022
by   Parvin Nazari, et al.
0

Bilevel programming has recently received attention in the literature, due to a wide range of applications, including reinforcement learning and hyper-parameter optimization. However, it is widely assumed that the underlying bilevel optimization problem is solved either by a single machine or in the case of multiple machines connected in a star-shaped network, i.e., federated learning setting. The latter approach suffers from a high communication cost on the central node (e.g., parameter server) and exhibits privacy vulnerabilities. Hence, it is of interest to develop methods that solve bilevel optimization problems in a communication-efficient decentralized manner. To that end, this paper introduces a penalty function based decentralized algorithm with theoretical guarantees for this class of optimization problems. Specifically, a distributed alternating gradient-type algorithm for solving consensus bilevel programming over a decentralized network is developed. A key feature of the proposed algorithm is to estimate the hyper-gradient of the penalty function via decentralized computation of matrix-vector products and few vector communications, which is then integrated within our alternating algorithm to give the finite-time convergence analysis under different convexity assumptions. Owing to the generality of this complexity analysis, our result yields convergence rates for a wide variety of consensus problems including minimax and compositional optimization. Empirical results on both synthetic and real datasets demonstrate that the proposed method works well in practice.

READ FULL TEXT
06/10/2021

A Decentralized Adaptive Momentum Method for Solving a Class of Min-Max Optimization Problems

Min-max saddle point games have recently been intensely studied, due to ...
02/10/2023

On Penalty-based Bilevel Gradient Descent Method

Bilevel optimization enjoys a wide range of applications in hyper-parame...
01/25/2019

DADAM: A Consensus-based Distributed Adaptive Gradient Method for Online Optimization

Adaptive gradient-based optimization methods such as ADAGRAD, RMSPROP, a...
12/06/2022

Decentralized Stochastic Gradient Descent Ascent for Finite-Sum Minimax Problems

Minimax optimization problems have attracted significant attention in re...
05/04/2022

FEDNEST: Federated Bilevel, Minimax, and Compositional Optimization

Standard federated optimization methods successfully apply to stochastic...
03/19/2023

On the Convergence of Decentralized Federated Learning Under Imperfect Information Sharing

Decentralized learning and optimization is a central problem in control ...
02/28/2023

Implicit Bilevel Optimization: Differentiating through Bilevel Optimization Programming

Bilevel Optimization Programming is used to model complex and conflictin...