paper-with-me

홈 › Papers

A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning

2025-04-02 · Yuyang Qiu, Kibaek Kim, Farzad Yousefian

Heterogeneity in federated learning (FL) is a critical and challenging aspect that significantly impacts model performance and convergence. In this paper, we propose a novel framework by formulating heterogeneous FL as a hierarchical optimization problem. This new framework captures both local and global training process through a bilevel formulation and is capable of the following: (i) addressing client heterogeneity through a personalized learning framework; (ii) capturing pre-training process on server's side; (iii) updating global model through nonstandard aggregation; (iv) allowing for nonidentical local steps; and (v) capturing clients' local constraints. We design and analyze an implicit zeroth-order FL method (ZO-HFL), provided with nonasymptotic convergence guarantees for both the server-agent and the individual client-agents, and asymptotic guarantees for both the server-agent and client-agents in an almost sure sense. Notably, our method does not rely on standard assumptions in heterogeneous FL, such as the bounded gradient dissimilarity condition. We implement our method on image classification tasks and compare with other methods under different heterogeneous settings.

📄 PDF Abstract BibTeX arXiv:2504.01839

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learningimage-classificationImage Classification

Similar Papers 제목 키워드 기반

On Zeroth-Order Stochastic Convex Optimization via Random Walks

2014-02-11 · Tengyuan Liang, Hariharan Narayanan, Alexander Rakhlin

We propose a method for zeroth order stochastic convex optimization that attains the suboptimality rate of $\tilde{\mathcal{O}}(n^{7}T^{-1/2})$ after $T$ queries for a convex bounded function $f:{\mathbb R}^n\to{\mathbb …

Derivative-free Alternating Projection Algorithms for General Nonconvex-Concave Minimax Problems

2021-08-01 · Zi Xu, Ziqi Wang, Jingjing Shen, Yuhong Dai

In this paper, we study zeroth-order algorithms for nonconvex-concave minimax problems, which have attracted widely attention in machine learning, signal processing and many other fields in recent years. We propose a zer…

Data Poisoning

ZorBA: Zeroth-order Federated Fine-tuning of LLMs with Heterogeneous Block Activation

2026-02-19 · Chuiyang Meng, Ming Tang, Vincent W. S. Wong arxiv

Federated fine-tuning of large language models (LLMs) enables collaborative tuning across distributed clients. However, due to the large size of LLMs, local updates in federated learning (FL) may incur substantial video …

Federated Learning

Randomized Benchmarking of Local Zeroth-Order Optimizers for Variational Quantum Systems

2023-10-14 · Lucas Tecot, Cho-Jui Hsieh

In the field of quantum information, classical optimizers play an important role. From experimentalists optimizing their physical devices to theorists exploring variational quantum algorithms, many aspects of quantum inf…

Benchmarking

Stochastic Dimension-Free Zeroth-Order Estimator for High-Dimensional and High-Order PINNs

2026-03-25 · Zhangyong Liang, Huanhuan Gao arxiv

Physics-Informed Neural Networks (PINNs) for high-dimensional and high-order partial differential equations (PDEs) are primarily constrained by the $\mathcal{O}(d^k)$ spatial derivative complexity and the $\mathcal{O}(P)…