Research map / Learning theory and algorithms / Sample complexity
High-dimensional Parameter Transfer With Fused-Regularizer
Zelin He, Ying Sun, Jingyuan Liu, Runze Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use TransMission instead of Agg-Lasso | Linear regression transfer · h=20, rho=0.4 | prediction error: 1.439 -> 0.404 | Improved |
| use TransMission instead of TransHDGLM | Linear regression transfer · h=20, rho=0.4 | prediction error: 0.805 -> 0.404 | Improved |
| use TransMission instead of Single-Lasso when contrast and shift are large | Linear regression transfer · h=20, rho=0.4 | prediction error: 0.886 -> 0.404 | Improved |
| use TransMission instead of Single-Lasso with small contrast | Logistic regression transfer · h=5, no shift | accuracy: 0.534 -> 0.647 | Hurt |
| use TransMission instead of TransHDGLM under both shifts | Logistic regression transfer · h=25, both shifts | accuracy: 0.524 -> 0.588 | Improved |
| use TransMission instead of TransGLM | GTEx gene expression · average MSE | MSE: 59.18 -> 41.92 | Improved |
| use TransMission instead of Trans-GLM | MNIST-C digit 8 · accuracy | accuracy: 90.28 -> 94.81 | Improved |
| use TransMission instead of Trans-GLM | MNIST-C digit 4 · accuracy | accuracy: 90.08 -> 87.87 | Hurt |
| increase source sample size nS for distributed variant (ablation) | D-TransMission · rho=0, h=20 | prediction error: 1.054 -> 0.260 | Improved |
Closest papers by meaning
- Transfer Learning for Benign Overfitting in High-Dimensional Linear Regression (NeurIPS 2025 · similarity 0.84)
- Enhancing Transfer Learning with Flexible Nonparametric Posterior Sampling (ICLR 2024 · similarity 0.83)
- A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning (NeurIPS 2025 · similarity 0.83)
- Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing (NeurIPS 2026 · similarity 0.82)
- Minimum-Norm Interpolation Under Covariate Shift (ICML 2024 · similarity 0.82)
- Parameter Estimation in DAGs from Incomplete Data via Optimal Transport (ICML 2024 · similarity 0.81)
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.
