Improved PAC-Bayesian Bounds for Linear Regression
Vera Shalaeva, Esfahani, Alireza Fakhrizadeh, Pascal Germain, Mihály Petreczky · arXiv (Cornell University) · 2019
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.