The generalization error of random features regression: Precise asymptotics and double descent curve

by   Song Mei, et al.

Deep learning methods operate in regimes that defy the traditional statistical mindset. The neural network architectures often contain more parameters than training samples, and are so rich that they can interpolate the observed labels, even if the latter are replaced by pure noise. Despite their huge complexity, the same architectures achieve small generalization error on real data. This phenomenon has been rationalized in terms of a so-called `double descent' curve. As the model complexity increases, the generalization error follows the usual U-shaped curve at the beginning, first decreasing and then peaking around the interpolation threshold (when the model achieves vanishing training error). However, it descends again as model complexity exceeds this threshold. The global minimum of the generalization error is found in this overparametrized regime, often when the number of parameters is much larger than the number of samples. Far from being a peculiar property of deep neural networks, elements of this behavior have been demonstrated in much simpler settings, including linear regression with random covariates. In this paper we consider the problem of learning an unknown function over the d-dimensional sphere S^d-1, from n i.i.d. samples ( x_i, y_i) ∈ S^d-1× R, i < n. We perform ridge regression on N random features of the form σ( w_a^ T x), a < N. This can be equivalently described as a two-layers neural network with random first-layer weights. We compute the precise asymptotics of the generalization error, in the limit N, n, d →∞ with N/d and n/d fixed. This provides the first analytically tractable model that captures all the features of the double descent phenomenon.



There are no comments yet.


page 1

page 2

page 3

page 4


Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime

Deep neural networks can achieve remarkable generalization performances ...

The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization

Modern deep learning models employ considerably more parameters than req...

Surprises in High-Dimensional Ridgeless Least Squares Interpolation

Interpolators -- estimators that achieve zero training error -- have att...

The Interpolation Phase Transition in Neural Networks: Memorization and Generalization under Lazy Training

Modern neural networks are often operated in a strongly overparametrized...

Multiple Descent: Design Your Own Generalization Curve

This paper explores the generalization loss of linear regression in vari...

Beyond Occam's Razor in System Identification: Double-Descent when Modeling Dynamics

System identification aims to build models of dynamical systems from dat...

Generalisation error in learning with random features and the hidden manifold model

We study generalised linear regression and classification for a syntheti...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.