Skip to Main content Skip to Navigation
Conference papers

Improved PAC-Bayesian Bounds for Linear Regression

Vera Shalaeva 1 Alireza Fakhrizadeh Esfahani 2, 3 Pascal Germain 1 Mihaly Petreczky 2, 3
1 MODAL - MOdel for Data Analysis and Learning
Inria Lille - Nord Europe, LPP - Laboratoire Paul Painlevé - UMR 8524, METRICS - Evaluation des technologies de santé et des pratiques médicales - ULR 2694, Polytech Lille - École polytechnique universitaire de Lille, Université de Lille, Sciences et Technologies
Abstract : In this paper, we improve the PAC-Bayesian error bound for linear regression derived in Germain et al. [10]. The improvements are twofold. First, the proposed error bound is tighter, and converges to the generalization loss with a well-chosen temperature parameter. Second, the error bound also holds for training data that are not independently sampled. In particular, the error bound applies to certain time series generated by well-known classes of dynamical models, such as ARX models.
Document type :
Conference papers
Complete list of metadata

Cited literature [26 references]  Display  Hide  Download

https://hal.inria.fr/hal-02396556
Contributor : Vera Shalaeva <>
Submitted on : Friday, December 6, 2019 - 9:41:57 AM
Last modification on : Friday, December 11, 2020 - 6:44:05 PM
Long-term archiving on: : Saturday, March 7, 2020 - 2:09:11 PM

Files

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02396556, version 1
  • ARXIV : 1912.03036

Citation

Vera Shalaeva, Alireza Fakhrizadeh Esfahani, Pascal Germain, Mihaly Petreczky. Improved PAC-Bayesian Bounds for Linear Regression. AAAI 2020 - Thirty-Fourth AAAI Conference on Artificial Intelligence, Feb 2020, New York, United States. ⟨hal-02396556⟩

Share

Metrics

Record views

139

Files downloads

615