cs.LGNov 18, 2026

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

Authors: Molly Wang

Organizations: Imperial Business School

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 [μ,L][μ,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 χ∈[1,L/μ]χ\in[1,L/μ], we establish the exact worst-case bias per unit heterogeneity, (L−μχ)/(2μLχ)(L-μχ)/(2μL\sqrtχ), 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.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 26, 2026

SCAFFOLD under Hessian Similarity: Sharp Convergence Rates

One of the main challenges of federated learning is heterogeneous data split among the clients, leading to biased local updates called client drift. The SCAFFOLD algorithm (Karimireddy et al., 2020) corrects client drift with control variates, but its relation to the similarity of client data is not yet fully understood: the original similarity-based guarantees cover only quadratics with a stronger second-order similarity assumption, and a follow-up weakly convex analysis (Luo et al., 2025) obtains a Lδ\sqrt{Lδ} dependence for LL-smooth losses with averaged Hessian similarity δδ. We analyze SCAFFOLD with minibatch-based control variates and establish linear dependence on Hessian similarity beyond quadratics, for both convex and nonconvex objectives. In particular, for convex objectives with exact gradients, RR SCAFFOLD rounds with KK local steps lead to an objective gap of order (L/K+δ)D02/R(L/K+δ)D_0^2/R, where D0D_0 is the initial distance to a minimizer. When K=Θ(L/δ)K=Θ(L/δ), it improves the minibatch SGD rate by a factor Θ(L/δ)Θ(L/δ). For nonconvex objectives, we prove an analogous stationarity guarantee under uniform Hessian similarity for a client-selection variant. In both settings, we extend these guarantees to stochastic gradients and prove matching lower bounds for the analyzed methods with constant local stepsizes. We also show that, under partial participation, even identical clients need not obtain the full communication benefit of additional local steps.
Oct 3, 2026

Asking the Crowd the Right Question: Bias-Cancelling Weights for Federated Learning

A federated objective is a weighted sum of client risks, and the weights are almost always fixed in advance. We treat them instead as the only instrument of a wisdom-of-crowds mechanism: clients are noisy views of one truth, each seeing it through an independent distortion that is unbiased across the crowd. That the optimal weights are inversely proportional to the clients' error energies is classical; we begin at the question that answer presupposes, which energies belong there and whether a crowd can recover them from itself. Excess risk on the truth is of the exact order of the aggregate bias energy, so no optimizer can repair a bad weight vector; the truth itself is identifiable only up to a linear tilt, so subtracting estimated client biases provably reproduces uniform weighting. The expected per-client second moments, however, are exactly identified from the law of the crowd's disagreement by a well-conditioned linear inversion, a step random-effects meta-analysis cannot take because a source reports once; their realized counterparts are estimable up to an incoherence floor the algorithm can measure. This yields CROWD, which reads the disagreement off the optimization trajectory at no extra cost and matches a Bayesian minimax lower bound in the same constant: per instance as the horizon grows, and unconditionally as the prior becomes diffuse. For arbitrary distortions it stays competitive with the optimal weights, at a ratio governed by a geometric incoherence the algorithm can measure. On real scans split into sites with their own miscalibrated detectors it attains the oracle excess risk; on a companion federation that pulls bias and noise apart, weighting by noise variance is worse than not weighting at all, and CROWD is not.
May 16, 2025

Heterogeneity-Aware Client Sampling for Optimal and Efficient Federated Learning

Federated learning (FL) commonly involves clients with diverse communication and computational capabilities. Such heterogeneity can significantly distort the optimization dynamics and lead to objective inconsistency, where the global model converges to an incorrect stationary point potentially far from the pursued optimum. Despite its critical impact, the joint effect of communication and computation heterogeneity has remained largely unexplored, due to the intrinsic complexity of their interaction. In this paper, we reveal the fundamentally distinct mechanisms through which heterogeneous communication and computation drive inconsistency in FL. To the best of our knowledge, this is the first unified theoretical analysis of general heterogeneous FL, offering a principled understanding of how these two forms of heterogeneity jointly distort the optimization trajectory under arbitrary choices of local solvers. Motivated by these insights, we propose Federated Heterogeneity-Aware Client Sampling, FedACS, a universal method to eliminate all types of objective inconsistency. We theoretically prove that FedACS converges to the correct optimum at a rate of O(1/R)O(1/\sqrt{R}), even in dynamic heterogeneous environments. Extensive experiments across multiple datasets show that FedACS outperforms state-of-the-art and category-specific baselines by 4.3%-36%, while reducing communication costs by 22%-89% and computation loads by 14%-105%, respectively.