Research map / Learning theory and algorithms / Kernels and regression theory
Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks
Mohammadreza Mousavi Kalan, Zalan Fabian, Salman Avestimehr, Mahdi Soltanolkotabi
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 |
|---|---|---|---|
| Increase source sample count when transfer distance is large | Weighted empirical-risk transfer learning for linear and one-hidden-layer networks · Synthetic linear and fixed-output-layer neural network experiments, large-distance target T2 | target generalization error | No clear effect |
| Increase source sample count when transfer distance is small | Weighted empirical-risk transfer learning for linear and one-hidden-layer networks · Synthetic linear and fixed-output-layer neural network experiments, small-distance target T1 | target generalization error | Improved |
| Increase target sample count | Weighted empirical-risk transfer learning for linear and one-hidden-layer networks · Synthetic experiments across transfer-distance regimes | target generalization error | Improved |
| Increase transfer distance from the source task | Source-only transfer learning · Synthetic linear and fixed-output-layer neural network experiments | target generalization error | Mixed |
| Use source-only transfer across target tasks with different noise levels | One-hidden-layer network trained on cat breeds · ImageNet dog breeds, big cats, butterflies, and planes | target test loss ordering | Mixed |
Closest papers by meaning
- A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning (NeurIPS 2025 · similarity 0.87)
- Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing (NeurIPS 2026 · similarity 0.87)
- Features are fate: a theory of transfer learning in high-dimensional regression (ICML 2025 · similarity 0.87)
- Universality in Transfer Learning for Linear Models (NeurIPS 2024 · similarity 0.86)
- On Transferring Transferability: Towards a Theory for Size Generalization (NeurIPS 2025 · similarity 0.86)
- Wasserstein Transfer Learning (NeurIPS 2025 · similarity 0.85)
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.
