Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks

arXiv2006.10581MaRDI QIDQ6343216

Author name not available (Why is that?)

Publication date: 16 June 2020

Abstract: Transfer learning has emerged as a powerful technique for improving the performance of machine learning models on new domains where labeled training data may be scarce. In this approach a model trained for a source task, where plenty of labeled training data is available, is used as a starting point for training a model on a related target task with only few labeled training data. Despite recent empirical success of transfer learning approaches, the benefits and fundamental limits of transfer learning are poorly understood. In this paper we develop a statistical minimax framework to characterize the fundamental limits of transfer learning in the context of regression with linear and one-hidden layer neural network models. Specifically, we derive a lower-bound for the target generalization error achievable by any algorithm as a function of the number of labeled source and target data as well as appropriate notions of similarity between the source and target tasks. Our lower bound provides new insights into the benefits and limitations of transfer learning. We further corroborate our theoretical finding with various experiments.

Has companion code repository: https://github.com/z-fabian/transfer_lowerbounds_arXiv

This page was built for publication: Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6343216)