paper-with-me

홈 › Papers

TransFusion: Covariate-Shift Robust Transfer Learning for High-Dimensional Regression

2024-04-01 · Zelin He, Ying Sun, Jingyuan Liu, Runze Li

The main challenge that sets transfer learning apart from traditional supervised learning is the distribution shift, reflected as the shift between the source and target models and that between the marginal covariate distributions. In this work, we tackle model shifts in the presence of covariate shifts in the high-dimensional regression setting. Specifically, we propose a two-step method with a novel fused-regularizer that effectively leverages samples from source tasks to improve the learning performance on a target task with limited samples. Nonasymptotic bound is provided for the estimation error of the target model, showing the robustness of the proposed method to covariate shifts. We further establish conditions under which the estimator is minimax-optimal. Additionally, we extend the method to a distributed setting, allowing for a pretraining-finetuning strategy, requiring just one round of communication while retaining the estimation rate of the centralized version. Numerical tests validate our theory, highlighting the method's robustness to covariate shifts.

📄 PDF Abstract BibTeX arXiv:2404.01153

Code (1)

ZLHe0/TransFusion

Tasks

regressionTransfer Learning

Similar Papers 제목 키워드 기반

Transfer Learning for High-dimensional Quantile Regression with Distribution Shift

2024-11-29 · Ruiqi Bai, Yijiao Zhang, Hanbo Yang, Zhongyi Zhu

Information from related source studies can often enhance the findings of a target study. However, the distribution shift between target and source studies can severely impact the efficiency of knowledge transfer. In the…

quantile regressionregressionTransfer Learning

Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers

2020-10-22 · Fan Yang, Hongyang R. Zhang, Sen Wu, Christopher Ré 외

The problem of learning one task with samples from another task is central to transfer learning (TL). In this paper, we examine a fundamental question: When does combining the data samples from a source task and a target…

Multi-Task Learningtext-classificationText ClassificationTransfer Learning

Minimum-Norm Interpolation Under Covariate Shift

2024-03-31 · Neil Mallinar, Austin Zane, Spencer Frei, Bin Yu

Transfer learning is a critical part of real-world machine learning deployments and has been extensively studied in experimental works with overparameterized neural networks. However, even in the simplest setting of line…

regressionTransfer Learning

Effective Sample Size, Dimensionality, and Generalization in Covariate Shift Adaptation

2020-10-02 · Felipe Maia Polo, Renato Vicente

In supervised learning, training and test datasets are often sampled from distinct distributions. Domain adaptation techniques are thus required. Covariate shift adaptation yields good generalization performance when dom…

Dimensionality ReductionDomain Adaptationfeature selectionGeneralization Bounds

Transfer Learning in Latent Contextual Bandits with Covariate Shift Through Causal Transportability

2025-02-27 · Mingwei Deng, Ville Kyrki, Dominik Baumann

Transferring knowledge from one environment to another is an essential ability of intelligent systems. Nevertheless, when two environments are different, naively transferring all knowledge may deteriorate the performance…

Causal InferenceMulti-Armed BanditsTransfer Learning