paper-with-me

홈 › Papers

Order Optimal One-Shot Distributed Learning

2019-11-02 · NeurIPS 2019 12 · Arsalan Sharifnassab, Saber Salehkaleybar, S. Jamaloddin Golestani

We consider distributed statistical optimization in one-shot setting, where there are $m$ machines each observing $n$ i.i.d. samples. Based on its observed samples, each machine then sends an $O(\log(mn))$-length message to a server, at which a parameter minimizing an expected loss is to be estimated. We propose an algorithm called Multi-Resolution Estimator (MRE) whose expected error is no larger than $\tilde{O}\big(m^{-{1}/{\max(d,2)}} n^{-1/2}\big)$, where $d$ is the dimension of the parameter space. This error bound meets existing lower bounds up to poly-logarithmic factors, and is thereby order optimal. The expected error of MRE, unlike existing algorithms, tends to zero as the number of machines ($m$) goes to infinity, even when the number of samples per machine ($n$) remains upper bounded by a constant. This property of the MRE algorithm makes it applicable in new machine learning paradigms where $m$ is much larger than $n$.

📄 PDF Abstract BibTeX arXiv:1911.00731

Code (1)

sabersalehk/MRE_C

Similar Papers 제목 키워드 기반

Order Optimal Bounds for One-Shot Federated Learning over non-Convex Loss Functions

2021-08-19 · Arsalan SharifNassab, Saber Salehkaleybar, S. Jamaloddin Golestani

We consider the problem of federated learning in a one-shot setting in which there are $m$ machines, each observing $n$ sample functions from an unknown distribution on non-convex loss functions. Let $F:[-1,1]^d\to\mathb…

Federated Learning

WONDER: Weighted one-shot distributed ridge regression in high dimensions

2019-03-22 · Edgar Dobriban, Yue Sheng

In many areas, practitioners need to analyze large datasets that challenge conventional single-machine computing. To scale up data analysis, distributed and parallel computing approaches are increasingly needed. Here we …

Distributed ComputingregressionUnityVocal Bursts Intensity Prediction

One-shot Distributed Ridge Regression in High Dimensions

2020-01-01 · ICML 2020 1 · Yue Sheng, Edgar Dobriban

To scale up data analysis, distributed and parallel computing approaches are increasingly needed. Here we study a fundamental problem in this area: How to do ridge regression in a distributed computing environment? We st…

Distributed ComputingregressionUnityVocal Bursts Intensity Prediction

A One-shot Framework for Distributed Clustered Learning in Heterogeneous Environments

2022-09-22 · Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic, Soummya Kar

The paper proposes a family of communication efficient methods for distributed learning in heterogeneous environments in which users obtain data from one of $K$ different distributions. In the proposed setup, the groupin…

ClusteringFederated Learning

Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning

2022-02-12 · Tomoya Murata, Taiji Suzuki

In recent centralized nonconvex distributed learning and federated learning, local methods are one of the promising approaches to reduce communication time. However, existing work has mainly focused on studying first-ord…

Distributed OptimizationFederated Learning