paper-with-me

홈 › Papers

Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization

2022-02-14 · Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski

A common explanation for the failure of deep networks to generalize out-of-distribution is that they fail to recover the "correct" features. We challenge this notion with a simple experiment which suggests that ERM already learns sufficient features and that the current bottleneck is not feature learning, but robust regression. Our findings also imply that given a small amount of data from the target distribution, retraining only the last linear layer will give excellent performance. We therefore argue that devising simpler methods for learning predictors on existing features is a promising direction for future research. Towards this end, we introduce Domain-Adjusted Regression (DARE), a convex objective for learning a linear predictor that is provably robust under a new model of distribution shift. Rather than learning one function, DARE performs a domain-specific adjustment to unify the domains in a canonical latent space and learns to predict in this space. Under a natural model, we prove that the DARE solution is the minimax-optimal predictor for a constrained set of test distributions. Further, we provide the first finite-environment convergence guarantee to the minimax risk, improving over existing analyses which only yield minimax predictors after an environment threshold. Evaluated on finetuned features, we find that DARE compares favorably to prior methods, consistently achieving equal or better performance.

📄 PDF Abstract BibTeX arXiv:2202.06856

Code (2)

erosenfeld/disagree_discrep pytorch
lfhase/feat pytorch

Tasks

Domain GeneralizationOut-of-Distribution Generalizationregression

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Adjusted Wasserstein Distributionally Robust Estimator in Statistical Learning

2023-03-27 · Yiling Xie, Xiaoming Huo

We propose an adjusted Wasserstein distributionally robust estimator -- based on a nonlinear transformation of the Wasserstein distributionally robust (WDRO) estimator in statistical learning. The classic WDRO estimator …

regression

Statistical Inference for Sequential Feature Selection after Domain Adaptation

2025-01-17 · Duong Tan Loc, Nguyen Thang Loi, Vo Nguyen Le Duy

In high-dimensional regression, feature selection methods, such as sequential feature selection (SeqFS), are commonly used to identify relevant features. When data is limited, domain adaptation (DA) becomes crucial for t…

Domain Adaptationfeature selectionModel Selection

Substitute adjustment via recovery of latent variables

2024-03-01 · Jeffrey Adams, Niels Richard Hansen

The deconfounder was proposed as a method for estimating causal parameters in a context with multiple causes and unobserved confounding. It is based on recovery of a latent variable from the observed causes. We disentang…

regression

Regression-Adjusted Estimation of Quantile Treatment Effects under Covariate-Adaptive Randomizations

2021-05-31 · Liang Jiang, Peter C. B. Phillips, Yubo Tao, Yichong Zhang

Datasets from field experiments with covariate-adaptive randomizations (CARs) usually contain extra covariates in addition to the strata indicators. We propose to incorporate these additional covariates via auxiliary reg…

regression

Explaining human body responses in random vibration: Effect of motion direction, sitting posture, and anthropometry

2023-06-21 · M. M. Cvetković, R. Desai, K. N. de Winkel, G. Papaioannou 외

This study investigates the effects of anthropometric attributes, biological sex, and posture on translational body kinematic responses in translational vibrations. In total, 35 participants were recruited. Perturbations…

regression