Learning under Distribution Mismatch and Model Misspecification

10 Feb 2021  ·  Mohammad Saeed Masiha, Amin Gohari, Mohammad Hossein Yassaee, Mohammad Reza Aref ·

We study learning algorithms when there is a mismatch between the distributions of the training and test datasets of a learning algorithm. The effect of this mismatch on the generalization error and model misspecification are quantified... Moreover, we provide a connection between the generalization error and the rate-distortion theory, which allows one to utilize bounds from the rate-distortion theory to derive new bounds on the generalization error and vice versa. In particular, the rate-distortion based bound strictly improves over the earlier bound by Xu and Raginsky even when there is no mismatch. We also discuss how "auxiliary loss functions" can be utilized to obtain upper bounds on the generalization error. read more

PDF Abstract
No code implementations yet. Submit your code now

Categories


Information Theory Information Theory

Datasets


  Add Datasets introduced or used in this paper