Saved in:
Bibliographic Details
Main Authors: Sharifnassab, Arsalan, Salehkaleybar, Saber, Golestani, S. Jamaloddin
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2108.08677
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917583108702208
author Sharifnassab, Arsalan
Salehkaleybar, Saber
Golestani, S. Jamaloddin
author_facet Sharifnassab, Arsalan
Salehkaleybar, Saber
Golestani, S. Jamaloddin
contents 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 $F:[-1,1]^d\to\mathbb{R}$ be the expected loss function with respect to this unknown distribution. The goal is to find an estimate of the minimizer of $F$. Based on its observations, each machine generates a signal of bounded length $B$ and sends it to a server. The server collects signals of all machines and outputs an estimate of the minimizer of $F$. We show that the expected loss of any algorithm is lower bounded by $\max\big(1/(\sqrt{n}(mB)^{1/d}), 1/\sqrt{mn}\big)$, up to a logarithmic factor. We then prove that this lower bound is order optimal in $m$ and $n$ by presenting a distributed learning algorithm, called Multi-Resolution Estimator for Non-Convex loss function (MRE-NC), whose expected loss matches the lower bound for large $mn$ up to polylogarithmic factors.
format Preprint
id arxiv_https___arxiv_org_abs_2108_08677
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Order Optimal Bounds for One-Shot Federated Learning over non-Convex Loss Functions
Sharifnassab, Arsalan
Salehkaleybar, Saber
Golestani, S. Jamaloddin
Machine Learning
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 $F:[-1,1]^d\to\mathbb{R}$ be the expected loss function with respect to this unknown distribution. The goal is to find an estimate of the minimizer of $F$. Based on its observations, each machine generates a signal of bounded length $B$ and sends it to a server. The server collects signals of all machines and outputs an estimate of the minimizer of $F$. We show that the expected loss of any algorithm is lower bounded by $\max\big(1/(\sqrt{n}(mB)^{1/d}), 1/\sqrt{mn}\big)$, up to a logarithmic factor. We then prove that this lower bound is order optimal in $m$ and $n$ by presenting a distributed learning algorithm, called Multi-Resolution Estimator for Non-Convex loss function (MRE-NC), whose expected loss matches the lower bound for large $mn$ up to polylogarithmic factors.
title Order Optimal Bounds for One-Shot Federated Learning over non-Convex Loss Functions
topic Machine Learning
url https://arxiv.org/abs/2108.08677