Skip to yearly menu bar Skip to main content


Oral

FedNest: Federated Bilevel, Minimax, and Compositional Optimization

Davoud Ataee Tarzanagh · Mingchen Li · Christos Thrampoulidis · Samet Oymak

Room 309

Abstract:

Standard federated optimization methods successfully apply to stochastic problems with single-level structure. However, many contemporary ML problems - including adversarial robustness, hyperparameter tuning, actor-critic - fall undernested bilevel programming that subsumes minimax and compositional optimization. In this work, we propose FedNest: A federated alternating stochastic gradient method to address general nested problems. We establish provable convergence rates for FedNest in the presence of heterogeneous data and introduce variations for bilevel, minimax, and compositional optimization. FedNest introduces multiple innovations including federated hypergradient computation and variance reduction to address inner-level heterogeneity. We complement our theory with experiments on hyperparameter & hyper-representation learning and minimax optimization that demonstrate the benefits of our method in practice.

Chat is not available.