Phase retrieval: From computational imaging to machine learning: A tutorial
Phase retrieval consists in the recovery of a complex-valued signal from intensity-only
measurements. As it pervades a broad variety of applications, many researchers have …
measurements. As it pervades a broad variety of applications, many researchers have …
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 of approximate message passing with semirandom matrices
Universality of approximate message passing with semirandom matrices Page 1 The
Annals of Probability 2023, Vol. 51, No. 5, 1616–1683 https://doi.org/10.1214/23-AOP1628 …
Annals of Probability 2023, Vol. 51, No. 5, 1616–1683 https://doi.org/10.1214/23-AOP1628 …
Estimation in rotationally invariant generalized linear models via approximate message passing
R Venkataramanan, K Kögler… - … on Machine Learning, 2022 - proceedings.mlr.press
We consider the problem of signal estimation in generalized linear models defined via
rotationally invariant design matrices. Since these matrices can have an arbitrary spectral …
rotationally invariant design matrices. Since these matrices can have an arbitrary spectral …
Sharp global convergence guarantees for iterative nonconvex optimization with random data
KA Chandrasekher, A Pananjady… - The Annals of …, 2023 - projecteuclid.org
Sharp global convergence guarantees for iterative nonconvex optimization with random data
Page 1 The Annals of Statistics 2023, Vol. 51, No. 1, 179–210 https://doi.org/10.1214/22-AOS2246 …
Page 1 The Annals of Statistics 2023, Vol. 51, No. 1, 179–210 https://doi.org/10.1214/22-AOS2246 …
Approximate message passing with spectral initialization for generalized linear models
M Mondelli, R Venkataramanan - … Conference on Artificial …, 2021 - proceedings.mlr.press
We consider the problem of estimating a signal from measurements obtained via a
generalized linear model. We focus on estimators based on approximate message passing …
generalized linear model. We focus on estimators based on approximate message passing …
PCA initialization for approximate message passing in rotationally invariant models
M Mondelli, R Venkataramanan - Advances in Neural …, 2021 - proceedings.neurips.cc
We study the problem of estimating a rank-1 signal in the presence of rotationally invariant
noise--a class of perturbations more general than Gaussian noise. Principal Component …
noise--a class of perturbations more general than Gaussian noise. Principal Component …
Spectral universality of regularized linear regression with nearly deterministic sensing matrices
It has been observed that the performances of many high-dimensional estimation problems
are universal with respect to underlying sensing (or design) matrices. Specifically, matrices …
are universal with respect to underlying sensing (or design) matrices. Specifically, matrices …
On the cryptographic hardness of learning single periodic neurons
We show a simple reduction which demonstrates the cryptographic hardness of learning a
single periodic neuron over isotropic Gaussian distributions in the presence of noise. More …
single periodic neuron over isotropic Gaussian distributions in the presence of noise. More …
The price of ignorance: how much does it cost to forget noise structure in low-rank matrix estimation?
We consider the problem of estimating a rank-$1 $ signal corrupted by structured rotationally
invariant noise, and address the following question:\emph {how well do inference algorithms …
invariant noise, and address the following question:\emph {how well do inference algorithms …