From Local SGD to Local Fixed-Point Methods for Federated Learning

Introductory lectures on convex optimization: a basic course

Nesterov, Y · 2004

Earlier work this paper cites.

Fixed-Point Algorithms for Inverse Problems in Science and Engineering

Bauschke, H. H., Burachik, R. S., Combettes, P. L., Elser, V., Luke, D. R., and Wolkowicz, H. (eds.) · 2011

Earlier work this paper cites.

On decomposing the proximal map

Yu, Y.-L · 2013

Earlier work this paper cites.

Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function

Richtárik, P. and Takáč, M · 2014

Earlier work this paper cites.

Compositions and convex combinations of averaged nonexpansive operators

Combettes, P. L. and Yamada, I · 2015

Earlier work this paper cites.

A class of randomized primal-dual algorithms for distributed optimization

Pesquet, J.-C. and Repetti, A · 2015

Earlier work this paper cites.

Convergence rate analysis of several splitting schemes

Davis, D. and Yin, W · 2016

Earlier work this paper cites.

Federated learning: Strategies for improving communication efficiency

Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., and Bacon, D · 2016

Cited alongside, same era.

Analysis and design of optimization algorithms via integral quadratic constraints

Lessard, L., Recht, B., and Packards, A · 2016

Cited alongside, same era.

Convex Analysis and Monotone Operator Theory in Hilbert Spaces

Bauschke, H. H. and Combettes, P. L · 2017

Cited alongside, same era.

Distributed optimization with arbitrary local solvers

Ma, C., Konečný, J., Jaggi, M., Smith, V., Jordan, M. I., Richtárik, P., and Takáč, M · 2017

Cited alongside, same era.

Communication-efficient learning of deep networks from decentralized data

McMahan, H. B., Moore, E., Ramage, D., Hampson, S., and Agüera y Arcas, B · 2017

Cited alongside, same era.

Distributed fixed point methods with compressed iterates

On the convergence of local descent methods in federated learning

Original

Haddadpour, F. and Mahdavi, M · 2019

Later among the works it cites.

Gradient descent with compressed iterates

Khaled, A. and Richtárik, P · 2019

Later among the works it cites.

First analysis of local GD on heterogeneous data

Khaled, A., Mishchenko, K., and Richtárik, P · 2019

Later among the works it cites.

Local SGD Converges Fast and Communicates Little

Stich, S. U · 2019

Later among the works it cites.

A fixed point framework for recovering signals from nonlinear transformations

Original

Combettes, P. L. and Woodstock, Z. C · 2020

Closest in time.

Tighter theory for local SGD on identical and heterogeneous data