Sharp analysis of out-of-distribution error for "importance-weighted" estimators in the overparameterized regime

Overparameterized models that achieve zero training error are observed to generalize well on average, but degrade in performance when faced with data that is under-represented in the training sample. In this work, we study an overparameterized Gaussian mixture model imbued with a spurious feature, a...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-05
Main Authors: Kuo-Wei, Lai, Muthukumar, Vidya
Format: Article
Language:English
Subjects:
Cost analysis
Error analysis
Lower bounds
Performance degradation
Probabilistic models
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Overparameterized models that achieve zero training error are observed to generalize well on average, but degrade in performance when faced with data that is under-represented in the training sample. In this work, we study an overparameterized Gaussian mixture model imbued with a spurious feature, and sharply analyze the in-distribution and out-of-distribution test error of a cost-sensitive interpolating solution that incorporates "importance weights". Compared to recent work Wang et al. (2021), Behnia et al. (2022), our analysis is sharp with matching upper and lower bounds, and significantly weakens required assumptions on data dimensionality. Our error characterizations also apply to any choice of importance weights and unveil a novel tradeoff between worst-case robustness to distribution shift and average accuracy as a function of the importance weight magnitude.
ISSN:2331-8422