
Learning Gaussian Mixtures with Generalised Linear Models: Precise Asymptotics in Highdimensions
Generalised linear models for multiclass classification problems are on...
read it

The Gaussian equivalence of generative models for learning with shallow neural networks
Understanding the impact of data structure on the computational tractabi...
read it

Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime
In this manuscript we consider Kernel Ridge Regression (KRR) under the G...
read it

Capturing the learning curves of generic features maps for realistic data sets with a teacherstudent model
Teacherstudent models provide a powerful framework in which the typical...
read it

Phase retrieval in high dimensions: Statistical and computational phase transitions
We consider the phase retrieval problem of reconstructing a ndimensiona...
read it

Generalisation error in learning with random features and the hidden manifold model
We study generalised linear regression and classification for a syntheti...
read it

Exact asymptotics for phase retrieval and compressed sensing with random generative priors
We consider the problem of compressed sensing and of (realvalued) phase...
read it

The spiked matrix model with generative priors
Using a lowdimensional parametrization of signals is a generic and powe...
read it
Bruno Loureiro
verfied profile
Researcher @ the Information, Learning and Physics laboratory (IdePHICS) @ EPFL, working of the crossroads between Machine Learning and Statistical Physics.