Semi-Supervised Learning with Noisy Proxy Covariates: Generalization Bounds and Distribution Regression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Kwangho, Kim, Jisu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911735132192768
author Kim, Kwangho
Kim, Jisu
author_facet Kim, Kwangho
Kim, Jisu
contents In many modern machine learning pipelines, abundant pretrained representations serve as noisy proxy covariates, while task-specific labels remain scarce. We study semi-supervised regression in this setting, and propose a simple two stage estimator that learns kernel eigenfeatures from all proxy covariates and fits a ridge predictor on labeled data. We derive finite sample bounds showing that fast labeled sample rates are recovered when proxy perturbation is controlled and unlabeled proxy covariates are sufficiently abundant. We also show that distribution regression is a direct special case, with analogous guarantees when the finite bag size is large enough. Experiments show consistent gains over supervised and semi-supervised baselines, especially in low label regimes.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00512
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Semi-Supervised Learning with Noisy Proxy Covariates: Generalization Bounds and Distribution Regression
Kim, Kwangho
Kim, Jisu
Machine Learning
Information Theory
In many modern machine learning pipelines, abundant pretrained representations serve as noisy proxy covariates, while task-specific labels remain scarce. We study semi-supervised regression in this setting, and propose a simple two stage estimator that learns kernel eigenfeatures from all proxy covariates and fits a ridge predictor on labeled data. We derive finite sample bounds showing that fast labeled sample rates are recovered when proxy perturbation is controlled and unlabeled proxy covariates are sufficiently abundant. We also show that distribution regression is a direct special case, with analogous guarantees when the finite bag size is large enough. Experiments show consistent gains over supervised and semi-supervised baselines, especially in low label regimes.
title Semi-Supervised Learning with Noisy Proxy Covariates: Generalization Bounds and Distribution Regression
topic Machine Learning
Information Theory
url https://arxiv.org/abs/2606.00512