High-dimensional robust regression under heavy-tailed data: Asymptotics and Universality
U Adomaityte, L Defilippis, B Loureiro… - arXiv preprint arXiv …, 2023 - arxiv.org
We investigate the high-dimensional properties of robust regression estimators in the
presence of heavy-tailed contamination of both the covariates and response functions. In …
presence of heavy-tailed contamination of both the covariates and response functions. In …
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 …
Gaussian universality for approximately polynomial functions of high-dimensional data
We establish an invariance principle for polynomial functions of $ n $ independent high-
dimensional random vectors, and also show that the obtained rates are nearly optimal. Both …
dimensional random vectors, and also show that the obtained rates are nearly optimal. Both …
Classification of heavy-tailed features in high dimensions: a superstatistical approach
We characterise the learning of a mixture of two clouds of data points with generic centroids
via empirical risk minimisation in the high dimensional regime, under the assumptions of …
via empirical risk minimisation in the high dimensional regime, under the assumptions of …
Fitting an ellipsoid to random points: predictions using the replica method
A Maillard, D Kunisky - IEEE Transactions on Information …, 2024 - ieeexplore.ieee.org
We consider the problem of fitting a centered ellipsoid to n standard Gaussian random
vectors in R d, as n, d→∞ with n/d 2→ α> 0. It has been conjectured that this problem is, with …
vectors in R d, as n, d→∞ with n/d 2→ α> 0. It has been conjectured that this problem is, with …
Finite-size correction and variance of the mutual information of random linear estimation with non-Gaussian priors: A replica calculation
TG Tsironis, AL Moustakas - Physical Review E, 2024 - APS
Random linear vector channels have been known to increase the transmission of
information in several communications systems. For Gaussian priors, the statistics of a key …
information in several communications systems. For Gaussian priors, the statistics of a key …
Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers
Deep linear networks have been extensively studied, as they provide simplified models of
deep learning. However, little is known in the case of finite-width architectures with multiple …
deep learning. However, little is known in the case of finite-width architectures with multiple …
Generalized Penalized Constrained Regression: Sharp Guarantees in High Dimensions with Noisy Features
The generalized penalized constrained regression (G-PCR) is a penalized model for high-
dimensional linear inverse problems with structured features. This paper presents a sharp …
dimensional linear inverse problems with structured features. This paper presents a sharp …
Storage Capacity Evaluation of the Quantum Perceptron using the Replica Method
M Urushibata, M Ohzeki - arXiv preprint arXiv:2404.14785, 2024 - arxiv.org
We investigate a quantum perceptron implemented on a quantum circuit using a repeat until
method. We evaluate this from the perspective of capacity, one of the performance …
method. We evaluate this from the perspective of capacity, one of the performance …
Slow rates of approximation of U-statistics and V-statistics by quadratic forms of Gaussians
We construct examples of degree-two U-and V-statistics of $ n $ iid~ heavy-tailed random
vectors in $\mathbb {R}^{d (n)} $, whose $\nu $-th moments exist for ${\nu> 2} $, and provide …
vectors in $\mathbb {R}^{d (n)} $, whose $\nu $-th moments exist for ${\nu> 2} $, and provide …