Multiple Descent: Design Your Own Generalization Curve

Lin Chen, Yifei Min, Misha Belkin, amin karbasi

Keywords: generalization, double descent, multiple descent

TL;DR: We show that the generalization curve can have multiple descents, and the locations can be explicitly controlled.

Abstract:

This paper explores the generalization loss of linear regression in variably parameterized families of models, both under-parameterized and over-parameterized. We show that the generalization curve can have an arbitrary number of peaks, and moreover, the locations of those peaks can be explicitly controlled. Our results highlight the fact that both the classical U-shaped generalization curve and the recently observed double descent curve are not intrinsic properties of the model family.
Instead, their emergence is due to the interaction between the properties of the data and the inductive biases of learning algorithms.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.