Improved PAC-Bayesian Bounds for Linear Regression
DOI:
https://doi.org/10.1609/aaai.v34i04.6020Abstract
In this paper, we improve the PAC-Bayesian error bound for linear regression derived in Germain et al. (2016). The improvements are two-fold. 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.
Downloads
Published
2020-04-03
How to Cite
Shalaeva, V., Fakhrizadeh Esfahani, A., Germain, P., & Petreczky, M. (2020). Improved PAC-Bayesian Bounds for Linear Regression. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 5660-5667. https://doi.org/10.1609/aaai.v34i04.6020
Issue
Section
AAAI Technical Track: Machine Learning