DeepAI AI Chat
Log In Sign Up

Effective dimension of machine learning models

by   Amira Abbas, et al.

Making statements about the performance of trained models on tasks involving new data is one of the primary goals of machine learning, i.e., to understand the generalization power of a model. Various capacity measures try to capture this ability, but usually fall short in explaining important characteristics of models that we observe in practice. In this study, we propose the local effective dimension as a capacity measure which seems to correlate well with generalization error on standard data sets. Importantly, we prove that the local effective dimension bounds the generalization error and discuss the aptness of this capacity measure for machine learning models.


page 1

page 2

page 3

page 4


Fractal Dimension Generalization Measure

Developing a robust generalization measure for the performance of machin...

Information-Theoretic Bounds on the Moments of the Generalization Error of Learning Algorithms

Generalization error bounds are critical to understanding the performanc...

A Note on High-Probability versus In-Expectation Guarantees of Generalization Bounds in Machine Learning

Statistical machine learning theory often tries to give generalization g...

The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization

Training with an emphasis on "hard-to-learn" components of the data has ...

Estimated VC dimension for risk bounds

Vapnik-Chervonenkis (VC) dimension is a fundamental measure of the gener...

Modeling Generalization in Machine Learning: A Methodological and Computational Study

As machine learning becomes more and more available to the general publi...

Robustness to Augmentations as a Generalization metric

Generalization is the ability of a model to predict on unseen domains an...