paper-with-me

홈 › Papers

When few labeled target data suffice: a theory of semi-supervised domain adaptation via fine-tuning from multiple adaptive starts

2025-07-19 · Wooseok Ha, Yuansi Chen arxiv

Semi-supervised domain adaptation (SSDA) seeks to achieve accurate predictions in a target domain with limited labeled target data by exploiting abundant source and unlabeled target data. We study this problem under structural causal models (SCMs), which provide a statistical framework to describe distribution shifts between source and target domains as interventions in the data-generating process rather than ad hoc changes in model parameters. The central phenomenon is that, under low-dimensional interventions, source and unlabeled target data can help identify the high-dimensional shared structure, leaving only a low-dimensional target-specific correction to be learned from limited labeled target data. We formalize this principle for three canonical intervention models and propose the corresponding SSDA methods FT-DIP, FT-OLS-Src and FT-CIP. Under each intervention model, we demonstrate how extending an unsupervised domain adaptation (UDA) method to SSDA can achieve minimax-optimal target performance with limited target labels, with the labeled-target sample complexity scaling with the intervention dimension rather than the ambient dimension. When the distribution shift is underspecified, we propose the Multi-Adaptive-Start Fine-Tuning (MASFT) algorithm, which fine-tunes from multiple adaptive starts and selects among them using a small target validation set, incurring only logarithmic overhead in the number of starts. We validate the effectiveness of our proposed methods through simulated and real data experiments.

📄 PDF Abstract BibTeX arXiv:2507.14661

Code (0)

등록된 구현이 없습니다.

Tasks

Unsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Beyond Discrepancy: A Closer Look at the Theory of Distribution Shift

2024-05-29 · Robi Bhattacharjee, Nick Rittler, Kamalika Chaudhuri

Many machine learning models appear to deploy effortlessly under distribution shift, and perform well on a target distribution that is considerably different from the training distribution. Yet, learning theory of distri…

Learning Theory

A faster and simpler algorithm for learning shallow networks

2023-07-24 · Sitan Chen, Shyam Narayanan

We revisit the well-studied problem of learning a linear combination of $k$ ReLU activations given labeled examples drawn from the standard $d$-dimensional Gaussian measure. Chen et al. [CDG+23] recently gave the first a…

Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning

2026-05-24 · Ziheng Cheng, Yixiao Huang, Hanlin Zhu, Haoran Geng 외 arxiv

Diffusion models are increasingly used as powerful conditional generators, yet real deployments often involve multiple target distributions arising from different tasks, e.g., diverse prompt domains in text-to-image gene…

Text-to-Image GenerationImage RestorationDecision Making

When and How Unlabeled Data Provably Improve In-Context Learning

2025-06-18 · Yingcong Li, Xiangyu Chang, Muti Kara, Xiaofeng Liu 외

Recent research shows that in-context learning (ICL) can be effective even when demonstrations have missing or incorrect labels. To shed light on this capability, we examine a canonical setting where the demonstrations a…

In-Context LearningMissing Labels

Your Classifier can Secretly Suffice Multi-Source Domain Adaptation

2021-03-20 · NeurIPS 2020 12 · Naveen Venkat, Jogendra Nath Kundu, Durgesh Kumar Singh, Ambareesh Revanur 외

Multi-Source Domain Adaptation (MSDA) deals with the transfer of task knowledge from multiple labeled source domains to an unlabeled target domain, under a domain-shift. Existing methods aim to minimize this domain-shift…

Domain AdaptationMulti-Source Unsupervised Domain Adaptation