DeepAI AI Chat
Log In Sign Up

Is My Model Flexible Enough? Information-Theoretic Model Check

by   Andreas Svensson, et al.
Uppsala universitet

The choice of model class is fundamental in statistical learning and system identification, no matter whether the class is derived from physical principles or is a generic black-box. We develop a method to evaluate the specified model class by assessing its capability of reproducing data that is similar to the observed data record. This model check is based on the information-theoretic properties of models viewed as data generators and is applicable to e.g. sequential data and nonlinear dynamical models. The method can be understood as a specific two-sided posterior predictive test. We apply the information-theoretic model check to both synthetic and real data and compare it with a classical whiteness test.


How consistent is my model with the data? Information-Theoretic Model Check

The choice of model class is fundamental in statistical learning and sys...

Information-theoretic generalization bounds for black-box learning algorithms

We derive information-theoretic generalization bounds for supervised lea...

Generic Bounds on the Maximum Deviations in Sequential Prediction: An Information-Theoretic Analysis

In this paper, we derive generic bounds on the maximum deviations in pre...

Fast Information-theoretic Bayesian Optimisation

Information-theoretic Bayesian optimisation techniques have demonstrated...

Information-Theoretic Visual Explanation for Black-Box Classifiers

In this work, we attempt to explain the prediction of any black-box clas...

Data Consistency Approach to Model Validation

In scientific inference problems, the underlying statistical modeling as...

Improving Supervised Phase Identification Through the Theory of Information Losses

This paper considers the problem of Phase Identification in power distri...

Code Repositories


Material for the research project on information-theoretic model check

view repo