Iterated Vector Fields and Conservatism, with Applications to Federated Learning

Abstract

We study whether iterated vector fields (vector fields composed with themselves) are conservative. We give explicit examples of vector fields for which this self-composition preserves conservatism. Notably, this includes gradient vector fields of loss functions associated with some generalized linear models. As we show, characterizing the set of vector fields satisfying this condition leads to non-trivial geometric questions. In the context of federated learning, we show that when clients have loss functions whose gradients satisfy this condition, federated averaging is equivalent to gradient descent on a surrogate loss function. We leverage this to derive novel convergence results for federated learning. By contrast, we demonstrate that when the client losses violate this property, federated averaging can yield behavior which is fundamentally distinct from centralized optimization. Finally, we discuss theoretical and practical questions our analytical framework raises for federated learning.

References in corpus (6)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
• A Field Guide to Federated Optimization
• FedSplit: An algorithmic framework for fast federated optimization
• First Analysis of Local GD on Heterogeneous Data
• An Operator Splitting View of Federated Learning