Newshot

Faster to the Wrong Answer: The Price of Local Updates in Federated Optimization

Summary

arXiv:2611.24057v1 Announce Type: new Abstract: Local computation can improve the conditioning of federated updates but may also introduce bias, causing their fixed point to differ from the global minimizer. We characterize the minimum worst-case bias achievable under a prescribed conditioning bound. We consider strongly convex quadratic client objectives with Hessian eigenvalues in $[\mu,L]$ and local updates represented by a shared positive spectral filter. Client heterogeneity is measured by the root-mean-square gradient at the global minimizer. For a uniform surrogate condition number bounded by $\chi\in[1,L/\mu]$, we establish the exact worst-case bias per unit heterogeneity, $(L-\mu\chi)/(2\mu L\sqrt{\chi})$, and show that local gradient descent with sufficiently small step sizes and proximal updates attain this bound. Our analysis reduces populations of arbitrary dimension, including noncommuting Hessians, to distributions over scalar curvatures. This reduction provides optimali…

Original text(via arXiv cs.LG)

Computer Science > Machine Learning

Title:Faster to the Wrong Answer: The Price of Local Updates in Federated Optimization

Abstract:Local computation can improve the conditioning of federated updates but may also introduce bias, causing their fixed point to differ from the global minimizer. We characterize the minimum worst-case bias achievable under a prescribed conditioning bound. We consider strongly convex quadratic client objectives with Hessian eigenvalues in $[\mu,L]$ and local updates represented by a shared positive spectral filter. Client heterogeneity is measured by the root-mean-square gradient at the global minimizer. For a uniform surrogate condition number bounded by $\chi\in[1,L/\mu]$, we establish the exact worst-case bias per unit heterogeneity, $(L-\mu\chi)/(2\mu L\sqrt{\chi})$, and show that local gradient descent with sufficiently small step sizes and proximal updates attain this bound. Our analysis reduces populations of arbitrary dimension, including noncommuting Hessians, to distributions over scalar curvatures. This reduction provides optimality certificates and worst-case constructions involving at most three scalar clients. We further extend the sharp proximal bias bound to smooth strongly convex objectives beyond quadratics and quantify the error introduced by inexact local solves.
Comments:18 pages, 1 figure; includes supplementary proofs and reproduction code
Subjects:Machine Learning (cs.LG)
Cite as:arXiv:2611.24057 [cs.LG]
(or arXiv:2611.24057v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2611.24057 arXiv-issued DOI via DataCite (pending registration)

Submission history

Access Paper:

  • HTML (experimental)

Ancillary files (details):

  • code/LICENSE
  • code/reproduce.py
  • code/requirements.txt
  • code/results.json

Additional Features

  • Audio Summary

Current browse context:

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by arXiv cs.LG
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗