Federated Multi-Level Optimization over Decentralized Networks

TL;DR

This paper introduces a gossip-based distributed multi-level optimization algorithm for decentralized networks, enabling scalable and efficient solutions to complex problems like hyper-parameter tuning and reinforcement learning.

Contribution

It proposes a novel algorithm that achieves optimal sample complexity and handles multi-level optimization in decentralized network settings.

Findings

Achieves linear scaling of sample complexity with network size.

Demonstrates state-of-the-art performance on multiple applications.

Enables multi-level optimization at a single timescale in decentralized systems.

Abstract

Multi-level optimization has gained increasing attention in recent years, as it provides a powerful framework for solving complex optimization problems that arise in many fields, such as meta-learning, multi-player games, reinforcement learning, and nested composition optimization. In this paper, we study the problem of distributed multi-level optimization over a network, where agents can only communicate with their immediate neighbors. This setting is motivated by the need for distributed optimization in large-scale systems, where centralized optimization may not be practical or feasible. To address this problem, we propose a novel gossip-based distributed multi-level optimization algorithm that enables networked agents to solve optimization problems at different levels in a single timescale and share information through network propagation. Our algorithm achieves optimal sample complexity, scaling linearly with the network size, and demonstrates state-of-the-art performance on various applications, including hyper-parameter tuning, decentralized reinforcement learning, and risk-averse optimization.