paper-with-me

Papers

Optimal Algorithms in Linear Regression under Covariate Shift: On the Importance of Precondition

2025-02-13 · Yuanshi Liu, Haihan Zhang, Qian Chen, Cong Fang

A common pursuit in modern statistical learning is to attain satisfactory generalization out of the source data distribution (OOD). In theory, the challenge remains unsolved even under the canonical setting of covariate shift for the linear model. This paper studies the foundational (high-dimensional) linear regression where the ground truth variables are confined to an ellipse-shape constraint and addresses two fundamental questions in this regime: (i) given the target covariate matrix, what is the min-max \emph{optimal} algorithm under covariate shift? (ii) for what kinds of target classes, the commonly-used SGD-type algorithms achieve optimality? Our analysis starts with establishing a tight lower generalization bound via a Bayesian Cramer-Rao inequality. For (i), we prove that the optimal estimator can be simply a certain linear transformation of the best estimator for the source distribution. Given the source and target matrices, we show that the transformation can be efficiently computed via a convex program. The min-max optimal analysis for SGD leverages the idea that we recognize both the accumulated updates of the applied algorithms and the ideal transformation as preconditions on the learning variables. We provide sufficient conditions when SGD with its acceleration variants attain optimality.

📄 PDF Abstract BibTeX arXiv:2502.09047

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…
SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Agnostic Learning of Mixed Linear Regressions with EM and AM Algorithms

2024-06-03 · Avishek Ghosh, Arya Mazumdar

Mixed linear regression is a well-studied problem in parametric statistics and machine learning. Given a set of samples, tuples of covariates and labels, the task of mixed linear regression is to find a small list of lin…

regression

Near-Optimal Linear Regression under Distribution Shift

2021-06-23 · Qi Lei, Wei Hu, Jason D. Lee

Transfer learning is essential when sufficient data comes from the source domain, with scarce labeled data from the target domain. We develop estimators that achieve minimax linear risk for linear regression problems und…

regressionTransfer Learning

Differentially Private Regression with Unbounded Covariates

2022-02-19 · Jason Milionis, Alkis Kalavasis, Dimitris Fotakis, Stratis Ioannidis

We provide computationally efficient, differentially private algorithms for the classical regression settings of Least Squares Fitting, Binary Regression and Linear Regression with unbounded covariates. Prior to our work…

regression

Feature Adaptation for Sparse Linear Regression

2023-05-26 · NeurIPS 2023 11

Sparse linear regression is a central problem in high-dimensional statistics. We study the correlated random design setting, where the covariates are drawn from a multivariate Gaussian $N(0,\Sigma)$, and we seek an estim…

regression

Contextual Strongly Convex Simulation Optimization: Optimize then Predict with Inexact Solutions

2025-12-06 · Nifei Lin, Heng Luo, L. Jeff Hong arxiv

In this work, we study contextual strongly convex simulation optimization and adopt an "optimize then predict" (OTP) approach for real-time decision making. In the offline stage, simulation optimization is conducted acro…

Decision Making