FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models

• URL: http://arxiv.org/abs/2510.27486v2
• Date: Mon, 10 Nov 2025 16:37:40 GMT
• Title: FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models
• Authors: Junkang Liu, Fanhua Shang, Kewen Zhu, Hongying Liu, Yuanyuan Liu, Jin Liu,
• Abstract summary: AdamW has become one of the most effective generalizations for training large-scale models.<n>We propose the first underlineFederated underlineAdamW algorithm, called textttFedAdamW, for training and fine-tuning various large models.
• Score: 27.658955798426323
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AdamW has become one of the most effective optimizers for training large-scale models. We have also observed its effectiveness in the context of federated learning (FL). However, directly applying AdamW in federated learning settings poses significant challenges: (1) due to data heterogeneity, AdamW often yields high variance in the second-moment estimate $\boldsymbol{v}$; (2) the local overfitting of AdamW may cause client drift; and (3) Reinitializing moment estimates ($\boldsymbol{v}$, $\boldsymbol{m}$) at each round slows down convergence. To address these challenges, we propose the first \underline{Fed}erated \underline{AdamW} algorithm, called \texttt{FedAdamW}, for training and fine-tuning various large models. \texttt{FedAdamW} aligns local updates with the global update using both a \textbf{local correction mechanism} and decoupled weight decay to mitigate local overfitting. \texttt{FedAdamW} efficiently aggregates the \texttt{mean} of the second-moment estimates to reduce their variance and reinitialize them. Theoretically, we prove that \texttt{FedAdamW} achieves a linear speedup convergence rate of $\mathcal{O}(\sqrt{(L \Delta \sigma_l^2)/(S K R \epsilon^2)}+(L \Delta)/R)$ without \textbf{heterogeneity assumption}, where $S$ is the number of participating clients per round, $K$ is the number of local iterations, and $R$ is the total number of communication rounds. We also employ PAC-Bayesian generalization analysis to explain the effectiveness of decoupled weight decay in local training. Empirically, we validate the effectiveness of \texttt{FedAdamW} on language and vision Transformer models. Compared to several baselines, \texttt{FedAdamW} significantly reduces communication rounds and improves test accuracy. The code is available in https://github.com/junkangLiu0/FedAdamW.

Related papers

• Arithmetic-Mean $μ$P for Modern Architectures: A Unified Learning-Rate Scale for CNNs and ResNets [9.94514344279733]
  Arithmetic-Mean $mu$P constrains not each individual layer but the network-wide average one-step pre-activation second moment to a constant scale.<n>We prove that, for one- and two-dimensional convolutional networks, the maximal-update learning rate satisfies $etastar(L)propto L-3/2$; with zero padding, boundary effects are constant-level as $Ngg k$.
  arXiv  Detail & Related papers  (2025-10-05T19:22:50Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• Simple Convergence Proof of Adam From a Sign-like Descent Perspective [58.89890024903816]
  We show that Adam achieves the optimal rate of $cal O(frac1Ts14)$ rather than the previous $cal O(fracln TTs14)$.<n>Our theoretical analysis provides new insights into the role of momentum as a key factor ensuring convergence.
  arXiv  Detail & Related papers  (2025-07-08T13:19:26Z)
• Proving the Limited Scalability of Centralized Distributed Optimization via a New Lower Bound Construction [57.93371273485736]
  We consider a centralized distributed learning setup where all workers jointly find an unbiased bound LDeltaepsilon2,$ better poly-logarithmically in $n$, even in the homogeneous (i.i.d.) case, where all workers access the same distribution.
  arXiv  Detail & Related papers  (2025-06-30T13:27:39Z)
• On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm [52.95596504632859]
  This paper establishes the convergence rate $frac1Ksum_k=1KEleft[||nabla f(xk)||_1right]leq O(fracsqrtdCK1/4)$ for AdamW measured by $ell_1$ norm.<n>We extend our result to NAdamW, an AdamW variant that employs a double-momentum mechanism, and demonstrate that it maintains the same convergence rate.
  arXiv  Detail & Related papers  (2025-05-17T05:02:52Z)
• The Effectiveness of Local Updates for Decentralized Learning under Data Heterogeneity [15.394956794959615]
  We revisit two fundamental decentralized optimization methods, Decentralized Gradient Tracking (DGT) and Decentralized Gradient Descent (DGD)<n>We prove that local DGT achieves communication complexity $tildemathcalO Big(fracLmu(K+1) + fracdelta + mumu (1 - rho) + fracrho (1 - rho)2 cdot fracL+ deltamuBig)$, %zhize
  arXiv  Detail & Related papers  (2024-03-23T00:01:34Z)
• Towards Bias Correction of FedAvg over Nonuniform and Time-Varying Communications [26.597515045714502]
  Federated learning (FL) is a decentralized learning framework wherein a parameter server (PS) and a collection of clients collaboratively train a model via a global objective. We show that when the channel conditions are heterogeneous across clients are changing over time, the FedFederated Postponed global model fails to postpone the gossip-type information mixing errors.
  arXiv  Detail & Related papers  (2023-06-01T01:52:03Z)
• Training \eta-VAE by Aggregating a Learned Gaussian Posterior with a Decoupled Decoder [0.553073476964056]
  Current practices in VAE training often result in a trade-off between the reconstruction fidelity and the continuity$/$disentanglement of the latent space. We present intuitions and a careful analysis of the antagonistic mechanism of the two losses, and propose a simple yet effective two-stage method for training a VAE. We evaluate the method using a medical dataset intended for 3D skull reconstruction and shape completion, and the results indicate promising generative capabilities of the VAE trained using the proposed method.
  arXiv  Detail & Related papers  (2022-09-29T13:49:57Z)
• Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis [121.9821494461427]
  We show how to significantly reduce the number of neurons required for two-layer ReLU networks. We also prove new lower bounds that improve upon prior work, and that under certain assumptions, are best possible.
  arXiv  Detail & Related papers  (2022-06-26T06:51:31Z)
• Faster Rates for Compressed Federated Learning with Client-Variance Reduction [23.169998435268504]
  We show that COFIG and FRECON converge within $O(frac(1+omega)sqrtNSepsilon2)$ communication rounds. In the convex setting COFIG converges within $O(frac(1+omega)sqrtNSepsilon2)$ communication rounds, which, to the best of our knowledge, is the first result.
  arXiv  Detail & Related papers  (2021-12-24T16:28:18Z)
• Distributed Saddle-Point Problems Under Similarity [173.19083235638104]
  We show that a given suboptimality $epsilon0$ is achieved master/workers networks in $Omegabig. We then propose algorithms matching the lower bounds either types of networks (up to log-overs) We assess effectiveness of the proposed algorithms on a robust logistic regression problem.
  arXiv  Detail & Related papers  (2021-07-22T14:25:16Z)
• Provable Robustness of Adversarial Training for Learning Halfspaces with Noise [95.84614821570283]
  We analyze the properties of adversarial learning adversarially robust halfspaces in the presence of label noise. To the best of our knowledge, this is the first work to show that adversarial training prov yields classifiers in noise.
  arXiv  Detail & Related papers  (2021-04-19T16:35:38Z)
• Optimal Robust Linear Regression in Nearly Linear Time [97.11565882347772]
  We study the problem of high-dimensional robust linear regression where a learner is given access to $n$ samples from the generative model $Y = langle X,w* rangle + epsilon$ We propose estimators for this problem under two settings: (i) $X$ is L4-L2 hypercontractive, $mathbbE [XXtop]$ has bounded condition number and $epsilon$ has bounded variance and (ii) $X$ is sub-Gaussian with identity second moment and $epsilon$ is
  arXiv  Detail & Related papers  (2020-07-16T06:44:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.