AI Paper Atlas

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

NeurIPS 2020 · Learning theory and algorithms › Kernels and regression theory · approach: High-dimensional asymptotic generalization · 16 citations (OpenAlex)

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 changedWhereMeasuredEffect
Increase source sample count when transfer distance is largeWeighted empirical-risk transfer learning for linear and one-hidden-layer networks · Synthetic linear and fixed-output-layer neural network experiments, large-distance target T2target generalization errorNo clear effect
Increase source sample count when transfer distance is smallWeighted empirical-risk transfer learning for linear and one-hidden-layer networks · Synthetic linear and fixed-output-layer neural network experiments, small-distance target T1target generalization errorImproved
Increase target sample countWeighted empirical-risk transfer learning for linear and one-hidden-layer networks · Synthetic experiments across transfer-distance regimestarget generalization errorImproved
Increase transfer distance from the source taskSource-only transfer learning · Synthetic linear and fixed-output-layer neural network experimentstarget generalization errorMixed
Use source-only transfer across target tasks with different noise levelsOne-hidden-layer network trained on cat breeds · ImageNet dog breeds, big cats, butterflies, and planestarget test loss orderingMixed

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy