DeepAI AI Chat
Log In Sign Up

Learning under Distribution Mismatch and Model Misspecification

by   Mohammad Saeed Masiha, et al.

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.


page 1

page 2

page 3

page 4


Learning Algorithm Generalization Error Bounds via Auxiliary Distributions

Generalization error boundaries are essential for comprehending how well...

Supermodular f-divergences and bounds on lossy compression and generalization error with mutual f-information

In this paper, we introduce super-modular -divergences and provide three...

Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning

In this paper, we use tools from rate-distortion theory to establish new...

Spherical Regression under Mismatch Corruption with Application to Automated Knowledge Translation

Motivated by a series of applications in data integration, language tran...

PACMAN: PAC-style bounds accounting for the Mismatch between Accuracy and Negative log-loss

The ultimate performance of machine learning algorithms for classificati...

Compact Error-Resilient Self-Assembly of Recursively Defined Patterns

A limitation to molecular implementations of tile-based self-assembly sy...

Data-dependent Generalization Bounds via Variable-Size Compressibility

In this paper, we establish novel data-dependent upper bounds on the gen...