paper-with-me

Papers

Second-Order Guarantees in Federated Learning

2020-12-02 · Stefan Vlaski, Elsa Rizk, Ali H. Sayed

Federated learning is a useful framework for centralized learning from distributed data under practical considerations of heterogeneity, asynchrony, and privacy. Federated architectures are frequently deployed in deep learning settings, which generally give rise to non-convex optimization problems. Nevertheless, most existing analysis are either limited to convex loss functions, or only establish first-order stationarity, despite the fact that saddle-points, which are first-order stationary, are known to pose bottlenecks in deep learning. We draw on recent results on the second-order optimality of stochastic gradient algorithms in centralized and decentralized settings, and establish second-order guarantees for a class of federated learning algorithms.

📄 PDF Abstract BibTeX arXiv:2012.01474

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningFederated Learning

Similar Papers 제목 키워드 기반

FLECS-CGD: A Federated Learning Second-Order Framework via Compression and Sketching with Compressed Gradient Differences

2022-10-18 · Artem Agafonov, Brahim Erraji, Martin Takáč

In the recent paper FLECS (Agafonov et al, FLECS: A Federated Learning Second-Order Framework via Compression and Sketching), the second-order framework FLECS was proposed for the Federated Learning problem. This method …

Federated LearningStochastic Optimization

Over-the-Air Federated Learning via Second-Order Optimization

2022-03-29 · Peng Yang, Yuning Jiang, Ting Wang, Yong Zhou 외

Federated learning (FL) is a promising learning paradigm that can tackle the increasingly prominent isolated data islands problem while keeping users' data locally with privacy and security guarantees. However, FL could …

Federated Learning

Taming Preconditioner Drift: Unlocking the Potential of Second-Order Optimizers for Federated Learning on Non-IID Data

2026-02-22 · Junkang Liu, Fanhua Shang, Hongying Liu, Jin Liu 외 arxiv

Second-order optimizers can significantly accelerate large-scale training, yet their naive federated variants are often unstable or even diverge on non-IID data. We show that a key culprit is \emph{preconditioner drift}:…

Federated Learning

Second-Order Guarantees in Centralized, Federated and Decentralized Nonconvex Optimization

2020-03-31 · Stefan Vlaski, Ali H. Sayed

Rapid advances in data collection and processing capabilities have allowed for the use of increasingly complex models that give rise to nonconvex optimization problems. These formulations, however, can be arbitrarily dif…

Fine-Grained Theoretical Analysis of Federated Zeroth-Order Optimization

2023-09-21 · NeurIPS 2023 11

Federated zeroth-order optimization (FedZO) algorithm enjoys the advantages of both zeroth-order optimization and federated learning, and has shown exceptional performance on black-box attack and softmax regression tasks…