Iterative Chow Filtering for Learning with Distribution Shift

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chandrasekaran, Gautam, Gkrinias, Georgios, Klivans, Adam R., Stavropoulos, Konstantinos, Vasilyan, Arsen
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917505256128512
author Chandrasekaran, Gautam
Gkrinias, Georgios
Klivans, Adam R.
Stavropoulos, Konstantinos
Vasilyan, Arsen
author_facet Chandrasekaran, Gautam
Gkrinias, Georgios
Klivans, Adam R.
Stavropoulos, Konstantinos
Vasilyan, Arsen
contents Recent work due to Goel et al. gave the first efficient algorithms for learning with distribution shift in the challenging PQ framework. In this setting, a learner receives labeled training examples, unlabeled test examples, and must make correct predictions on the test set but is allowed to abstain from predicting on out-of-distribution points. Their results rely on ${\cal L}_2$ sandwiching approximations, a strong requirement that leads to poor bounds for several basic function classes such as DNF formulas. Here, we show that the weaker notion of ${\cal L}_1$ sandwiching suffices for efficient PQ learning. As a consequence, we obtain the first quasipolynomial-time PQ learning algorithm for DNFs under the uniform distribution and essentially match the guarantees known for ordinary PAC learning. More broadly, our bounds provide exponential improvements for several classes including constant depth circuits and constant degree polynomial threshold functions. Our main technical ingredient is Iterative Chow Filtering, a new procedure that uses low-degree Chow parameters to identify and remove test points incompatible with the training distribution.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17251
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Iterative Chow Filtering for Learning with Distribution Shift
Chandrasekaran, Gautam
Gkrinias, Georgios
Klivans, Adam R.
Stavropoulos, Konstantinos
Vasilyan, Arsen
Data Structures and Algorithms
Machine Learning
Recent work due to Goel et al. gave the first efficient algorithms for learning with distribution shift in the challenging PQ framework. In this setting, a learner receives labeled training examples, unlabeled test examples, and must make correct predictions on the test set but is allowed to abstain from predicting on out-of-distribution points. Their results rely on ${\cal L}_2$ sandwiching approximations, a strong requirement that leads to poor bounds for several basic function classes such as DNF formulas. Here, we show that the weaker notion of ${\cal L}_1$ sandwiching suffices for efficient PQ learning. As a consequence, we obtain the first quasipolynomial-time PQ learning algorithm for DNFs under the uniform distribution and essentially match the guarantees known for ordinary PAC learning. More broadly, our bounds provide exponential improvements for several classes including constant depth circuits and constant degree polynomial threshold functions. Our main technical ingredient is Iterative Chow Filtering, a new procedure that uses low-degree Chow parameters to identify and remove test points incompatible with the training distribution.
title Iterative Chow Filtering for Learning with Distribution Shift
topic Data Structures and Algorithms
Machine Learning
url https://arxiv.org/abs/2605.17251