Collaborative and Federated Black-box Optimization: A Bayesian Optimization Perspective

TL;DR

This paper introduces three unified Bayesian optimization frameworks for collaborative and federated black-box optimization, addressing challenges like heterogeneity, privacy, and distributed experimentation to advance federated learning towards prescriptive decision-making.

Contribution

It proposes a comprehensive Bayesian optimization perspective with three frameworks for federated BBOpt, unifying existing methods and highlighting open research questions.

Findings

Categorizes existing federated BBOpt methods within the proposed frameworks.

Identifies key open questions to enhance federated BBOpt.

Shifts federated learning towards a prescriptive paradigm in BBOpt.

Abstract

We focus on collaborative and federated black-box optimization (BBOpt), where agents optimize their heterogeneous black-box functions through collaborative sequential experimentation. From a Bayesian optimization perspective, we address the fundamental challenges of distributed experimentation, heterogeneity, and privacy within BBOpt, and propose three unifying frameworks to tackle these issues: (i) a global framework where experiments are centrally coordinated, (ii) a local framework that allows agents to make decisions based on minimal shared information, and (iii) a predictive framework that enhances local surrogates through collaboration to improve decision-making. We categorize existing methods within these frameworks and highlight key open questions to unlock the full potential of federated BBOpt. Our overarching goal is to shift federated learning from its predominantly descriptive/predictive paradigm to a prescriptive one, particularly in the context of BBOpt - an inherently sequential decision-making problem.