Saved in:
Bibliographic Details
Main Authors: Clara, Gabriel, Mash'al, Yazan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.10188
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917137999724544
author Clara, Gabriel
Mash'al, Yazan
author_facet Clara, Gabriel
Mash'al, Yazan
contents We analyze gradient descent with randomly weighted data points in a linear regression model, under a generic weighting distribution. This includes various forms of stochastic gradient descent, importance sampling, but also extends to weighting distributions with arbitrary continuous values, thereby providing a unified framework to analyze the impact of various kinds of noise on the training trajectory. We characterize the implicit regularization induced through the random weighting, connect it with weighted linear regression, and derive non-asymptotic bounds for convergence in first and second moments. Leveraging geometric moment contraction, we also investigate the stationary distribution induced by the added noise. Based on these results, we discuss how specific choices of weighting distribution influence both the underlying optimization problem and statistical properties of the resulting estimator, as well as some examples for which weightings that lead to fast convergence cause bad statistical performance.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10188
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Interplay of Statistics and Noisy Optimization: Learning Linear Predictors with Random Data Weights
Clara, Gabriel
Mash'al, Yazan
Machine Learning
Computation
We analyze gradient descent with randomly weighted data points in a linear regression model, under a generic weighting distribution. This includes various forms of stochastic gradient descent, importance sampling, but also extends to weighting distributions with arbitrary continuous values, thereby providing a unified framework to analyze the impact of various kinds of noise on the training trajectory. We characterize the implicit regularization induced through the random weighting, connect it with weighted linear regression, and derive non-asymptotic bounds for convergence in first and second moments. Leveraging geometric moment contraction, we also investigate the stationary distribution induced by the added noise. Based on these results, we discuss how specific choices of weighting distribution influence both the underlying optimization problem and statistical properties of the resulting estimator, as well as some examples for which weightings that lead to fast convergence cause bad statistical performance.
title The Interplay of Statistics and Noisy Optimization: Learning Linear Predictors with Random Data Weights
topic Machine Learning
Computation
url https://arxiv.org/abs/2512.10188