paper-with-me

홈 › Papers

Accelerated Distributed Stochastic Non-Convex Optimization over Time-Varying Directed Networks

2024-10-11 · Yiyue Chen, Abolfazl Hashemi, Haris Vikalo

Distributed stochastic non-convex optimization problems have recently received attention due to the growing interest of signal processing, computer vision, and natural language processing communities in applications deployed over distributed learning systems (e.g., federated learning). We study the setting where the data is distributed across the nodes of a time-varying directed network, a topology suitable for modeling dynamic networks experiencing communication delays and straggler effects. The network nodes, which can access only their local objectives and query a stochastic first-order oracle to obtain gradient estimates, collaborate to minimize a global objective function by exchanging messages with their neighbors. We propose an algorithm, novel to this setting, that leverages stochastic gradient descent with momentum and gradient tracking to solve distributed non-convex optimization problems over time-varying networks. To analyze the algorithm, we tackle the challenges that arise when analyzing dynamic network systems which communicate gradient acceleration components. We prove that the algorithm's oracle complexity is $\mathcal{O}(1/\epsilon^{1.5})$, and that under Polyak-$\L$ojasiewicz condition the algorithm converges linearly to a steady error state. The proposed scheme is tested on several learning tasks: a non-convex logistic regression experiment on the MNIST dataset, an image classification task on the CIFAR-10 dataset, and an NLP classification test on the IMDB dataset. We further present numerical simulations with an objective that satisfies the PL condition. The results demonstrate superior performance of the proposed framework compared to the existing related methods.

📄 PDF Abstract BibTeX arXiv:2410.08508

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learningimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Logistic Regression Logistic Regression, despite its name, is a linear model for classification rather than regression. Logistic regression is also known in the literature as logit regression,…

Similar Papers 제목 키워드 기반

Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping

2020-05-21 · NeurIPS 2020 12 · Eduard Gorbunov, Marina Danilova, Alexander Gasnikov

In this paper, we propose a new accelerated stochastic first-order method called clipped-SSTM for smooth convex stochastic optimization with heavy-tailed distributed noise in stochastic gradients and derive the first hig…

Stochastic Optimization

Stochastic Optimization from Distributed, Streaming Data in Rate-limited Networks

2017-04-25 · Matthew Nokleby, Waheed U. Bajwa

Motivated by machine learning applications in networks of sensors, internet-of-things (IoT) devices, and autonomous agents, we propose techniques for distributed stochastic convex learning from high-rate data streams. Th…

Stochastic Optimization

Accelerated Distributed Optimization with Compression and Error Feedback

2025-03-11 · Yuan Gao, Anton Rodomanov, Jeremy Rack, Sebastian U. Stich

Modern machine learning tasks often involve massive datasets and models, necessitating distributed optimization algorithms with reduced communication overhead. Communication compression, where clients transmit compressed…

Distributed Optimization

Distributed Stochastic Consensus Optimization with Momentum for Nonconvex Nonsmooth Problems

2020-11-10 · Zhiguo Wang, Jiawei Zhang, Tsung-Hui Chang, Jian Li 외

While many distributed optimization algorithms have been proposed for solving smooth or convex problems over the networks, few of them can handle non-convex and non-smooth problems. Based on a proximal primal-dual approa…

Distributed Optimization

Accelerating Distributed Optimization: A Primal-Dual Perspective on Local Steps

2024-07-02 · Junchi Yang, Murat Yildirim, Qiu Feng

In distributed machine learning, efficient training across multiple agents with different data distributions poses significant challenges. Even with a centralized coordinator, current algorithms that achieve optimal comm…

Distributed Optimization