Bayes-optimal learning of deep random networks of extensive-width
We consider the problem of learning a target function corresponding to a deep, extensive-
width, non-linear neural network with random Gaussian weights. We consider the asymptotic …
width, non-linear neural network with random Gaussian weights. We consider the asymptotic …
Universality laws for gaussian mixtures in generalized linear models
A recent line of work in high-dimensional statistics working under the Gaussian mixture
hypothesis has led to a number of results in the context of empirical risk minimization …
hypothesis has led to a number of results in the context of empirical risk minimization …
Spectral evolution and invariance in linear-width neural networks
We investigate the spectral properties of linear-width feed-forward neural networks, where
the sample size is asymptotically proportional to network width. Empirically, we show that the …
the sample size is asymptotically proportional to network width. Empirically, we show that the …
On double-descent in uncertainty quantification in overparametrized models
Uncertainty quantification is a central challenge in reliable and trustworthy machine
learning. Naive measures such as last-layer scores are well-known to yield overconfident …
learning. Naive measures such as last-layer scores are well-known to yield overconfident …
Asymptotics of feature learning in two-layer networks after one gradient-step
In this manuscript we investigate the problem of how two-layer neural networks learn
features from data, and improve over the kernel regime, after being trained with a single …
features from data, and improve over the kernel regime, after being trained with a single …
Nonlinear spiked covariance matrices and signal propagation in deep neural networks
Many recent works have studied the eigenvalue spectrum of the Conjugate Kernel (CK)
defined by the nonlinear feature map of a feedforward neural network. However, existing …
defined by the nonlinear feature map of a feedforward neural network. However, existing …
Local Kernel Renormalization as a mechanism for feature learning in overparametrized Convolutional Neural Networks
Feature learning, or the ability of deep neural networks to automatically learn relevant
features from raw data, underlies their exceptional capability to solve complex tasks …
features from raw data, underlies their exceptional capability to solve complex tasks …
Learning curves for deep structured Gaussian feature models
J Zavatone-Veth, C Pehlevan - Advances in Neural …, 2023 - proceedings.neurips.cc
In recent years, significant attention in deep learning theory has been devoted to analyzing
when models that interpolate their training data can still generalize well to unseen …
when models that interpolate their training data can still generalize well to unseen …
Universality of max-margin classifiers
Maximum margin binary classification is one of the most fundamental algorithms in machine
learning, yet the role of featurization maps and the high-dimensional asymptotics of the …
learning, yet the role of featurization maps and the high-dimensional asymptotics of the …
Asymptotics of Learning with Deep Structured (Random) Features
For a large class of feature maps we provide a tight asymptotic characterisation of the test
error associated with learning the readout layer, in the high-dimensional limit where the …
error associated with learning the readout layer, in the high-dimensional limit where the …