paper-with-me

홈 › Papers

Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithm

2021-11-02 · Yuheng Bu, Gholamali Aminian, Laura Toni, Miguel Rodrigues, Gregory Wornell

We provide an information-theoretic analysis of the generalization ability of Gibbs-based transfer learning algorithms by focusing on two popular transfer learning approaches, $\alpha$-weighted-ERM and two-stage-ERM. Our key result is an exact characterization of the generalization behaviour using the conditional symmetrized KL information between the output hypothesis and the target training samples given the source samples. Our results can also be applied to provide novel distribution-free generalization error upper bounds on these two aforementioned Gibbs algorithms. Our approach is versatile, as it also characterizes the generalization errors and excess risks of these two Gibbs algorithms in the asymptotic regime, where they converge to the $\alpha$-weighted-ERM and two-stage-ERM, respectively. Based on our theoretical results, we show that the benefits of transfer learning can be viewed as a bias-variance trade-off, with the bias induced by the source distribution and the variance induced by the lack of target samples. We believe this viewpoint can guide the choice of transfer learning algorithms in practice.

📄 PDF Abstract BibTeX arXiv:2111.01635

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

Characterizing the Generalization Error of Gibbs Algorithm with Symmetrized KL information

2021-07-28 · Gholamali Aminian, Yuheng Bu, Laura Toni, Miguel R. D. Rodrigues 외

Bounding the generalization error of a supervised learning algorithm is one of the most important problems in learning theory, and various approaches have been developed. However, existing bounds are often loose and lack…

Learning Theory

Generalization Analysis of Machine Learning Algorithms via the Worst-Case Data-Generating Probability Measure

2023-12-19 · Xinying Zou, Samir M. Perlaza, Iñaki Esnaola, Eitan Altman

In this paper, the worst-case probability measure over the data is introduced as a tool for characterizing the generalization capabilities of machine learning algorithms. More specifically, the worst-case probability mea…

Sensitivity

An Exact Characterization of the Generalization Error for the Gibbs Algorithm

2021-12-01 · NeurIPS 2021 12 · Gholamali Aminian, Yuheng Bu, Laura Toni, Miguel Rodrigues 외

Various approaches have been developed to upper bound the generalization error of a supervised learning algorithm. However, existing bounds are often loose and lack of guarantees. As a result, they may fail to characteri…

On the Generalization Error of Meta Learning for the Gibbs Algorithm

2023-04-27 · Yuheng Bu, Harsha Vardhan Tetali, Gholamali Aminian, Miguel Rodrigues 외

We analyze the generalization ability of joint-training meta learning algorithms via the Gibbs algorithm. Our exact characterization of the expected meta generalization error for the meta Gibbs algorithm is based on symm…

Meta-Learning

Generalization of the Gibbs algorithm with high probability at low temperatures

2025-02-16 · Andreas Maurer

The paper gives a bound on the generalization error of the Gibbs algorithm, which recovers known data-independent bounds for the high temperature range and extends to the low-temperature range, where generalization depen…