Research map / Label-efficient and robust learning / Domain adaptation and generalization
Co-Regularization Enhances Knowledge Transfer in High Dimensions
Shuo Shuo Liu, Haotian Lin, Matthew Reimherr, Runze Li
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a co-regularization transfer learning method for high-dimensional generalized linear models that directly exploits beneficial source-domain knowledge instead of relying on a two-step regularization that assumes the pre-trained model resembles the target.
Problem
Transfer learning for high-dimensional models relies on two-step regularization that assumes the pre-trained source model closely resembles the target, which fails when they differ.
Approach
A co-regularization process that jointly learns target and source-related parameters to directly extract beneficial knowledge from the source domain, relaxing the assumption that the source model closely matches the target.
Experimental setup
Builds on: two-step regularization transfer learning
Closest papers by meaning
- Transfer Learning for Benign Overfitting in High-Dimensional Linear Regression (NeurIPS 2025 · similarity 0.86)
- On Hypothesis Transfer Learning of Functional Linear Models (ICML 2024 · similarity 0.86)
- Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing (NeurIPS 2026 · similarity 0.85)
- A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning (NeurIPS 2025 · similarity 0.85)
- Transfer Learning for Diffusion Models (NeurIPS 2024 · similarity 0.84)
- Universality in Transfer Learning for Linear Models (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
