Federated Bayesian Optimization via Thompson Sampling

Abstract

Bayesian optimization (BO) is a prominent approach to optimizing expensive-to-evaluate black-box functions. The massive computational capability of edge devices such as mobile phones, coupled with privacy concerns, has led to a surging interest in federated learning (FL) which focuses on collaborative training of deep neural networks (DNNs) via first-order optimization techniques. However, some common machine learning tasks such as hyperparameter tuning of DNNs lack access to gradients and thus require zeroth-order/black-box optimization. This hints at the possibility of extending BO to the FL setting (FBO) for agents to collaborate in these black-box optimization tasks. This paper presents federated Thompson sampling (FTS) which overcomes a number of key challenges of FBO and FL in a principled way: We (a) use random Fourier features to approximate the Gaussian process surrogate model used in BO, which naturally produces the parameters to be exchanged between agents, (b) design FTS based on Thompson sampling, which significantly reduces the number of parameters to be exchanged, and (c) provide a theoretical convergence guarantee that is robust against heterogeneous agents, which is a major challenge in FL and FBO. We empirically demonstrate the effectiveness of FTS in terms of communication efficiency, computational efficiency, and practical performance.

arXiv commentAccepted to 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Extended version with proofs and additional experimental details and results, 25 pages

References in corpus (12)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Optimization in Heterogeneous Networks
• Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer
• Decentralized Data Fusion and Active Sensing with Mobile Sensors for Modeling and Predicting Spatiotemporal Traffic Phenomena
• Adversarially Robust Optimization with Gaussian Processes
• Collaborative Machine Learning with Incentive-Aware Model Rewards
• Parallel Gaussian Process Regression with Low-Rank Covariance Matrix Approximations
• Differentially Private Bayesian Optimization
• Decentralized High-Dimensional Bayesian Optimization with Factor Graphs
• Implicit Posterior Variational Inference for Deep Gaussian Processes
• R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games
• Private Outsourced Bayesian Optimization

Cited by in corpus (3)

• Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning
• A Robust Federated Learning Approach for Combating Attacks Against IoT Systems Under non-IID Challenges
• Collaborative and Federated Black-box Optimization: A Bayesian Optimization Perspective