Saved in:
Bibliographic Details
Main Authors: Dexheimer, Niklas, Schmidt-Hieber, Johannes
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.17567
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929605939560448
author Dexheimer, Niklas
Schmidt-Hieber, Johannes
author_facet Dexheimer, Niklas
Schmidt-Hieber, Johannes
contents Forward gradient descent (FGD) has been proposed as a biologically more plausible alternative of gradient descent as it can be computed without backward pass. Considering the linear model with $d$ parameters, previous work has found that the prediction error of FGD is, however, by a factor $d$ slower than the prediction error of stochastic gradient descent (SGD). In this paper we show that by computing $\ell$ FGD steps based on each training sample, this suboptimality factor becomes $d/(\ell \wedge d)$ and thus the suboptimality of the rate disappears if $\ell \gtrsim d.$ We also show that FGD with repeated sampling can adapt to low-dimensional structure in the input distribution. The main mathematical challenge lies in controlling the dependencies arising from the repeated sampling process.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17567
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving the Convergence Rates of Forward Gradient Descent with Repeated Sampling
Dexheimer, Niklas
Schmidt-Hieber, Johannes
Statistics Theory
Machine Learning
Neural and Evolutionary Computing
62L20, 62J05
Forward gradient descent (FGD) has been proposed as a biologically more plausible alternative of gradient descent as it can be computed without backward pass. Considering the linear model with $d$ parameters, previous work has found that the prediction error of FGD is, however, by a factor $d$ slower than the prediction error of stochastic gradient descent (SGD). In this paper we show that by computing $\ell$ FGD steps based on each training sample, this suboptimality factor becomes $d/(\ell \wedge d)$ and thus the suboptimality of the rate disappears if $\ell \gtrsim d.$ We also show that FGD with repeated sampling can adapt to low-dimensional structure in the input distribution. The main mathematical challenge lies in controlling the dependencies arising from the repeated sampling process.
title Improving the Convergence Rates of Forward Gradient Descent with Repeated Sampling
topic Statistics Theory
Machine Learning
Neural and Evolutionary Computing
62L20, 62J05
url https://arxiv.org/abs/2411.17567