Nonconvex optimization meets low-rank matrix factorization: An overview
Substantial progress has been made recently on developing provably accurate and efficient
algorithms for low-rank matrix factorization via nonconvex optimization. While conventional …
algorithms for low-rank matrix factorization via nonconvex optimization. While conventional …
Spectral methods for data science: A statistical perspective
Spectral methods have emerged as a simple yet surprisingly effective approach for
extracting information from massive, noisy and incomplete data. In a nutshell, spectral …
extracting information from massive, noisy and incomplete data. In a nutshell, spectral …
Implicit regularization in nonconvex statistical estimation: Gradient descent converges linearly for phase retrieval and matrix completion
Recent years have seen a flurry of activities in designing provably efficient nonconvex
optimization procedures for solving statistical estimation problems. For various problems like …
optimization procedures for solving statistical estimation problems. For various problems like …
Gradient descent with random initialization: Fast global convergence for nonconvex phase retrieval
This paper considers the problem of solving systems of quadratic equations, namely,
recovering an object of interest x^ ♮ ∈ R^ nx♮∈ R n from m quadratic equations/samples …
recovering an object of interest x^ ♮ ∈ R^ nx♮∈ R n from m quadratic equations/samples …
Phasemax: Convex phase retrieval via basis pursuit
T Goldstein, C Studer - IEEE Transactions on Information …, 2018 - ieeexplore.ieee.org
We consider the recovery of a (real-or complex-valued) signal from magnitude-only
measurements, known as phase retrieval. We formulate phase retrieval as a convex …
measurements, known as phase retrieval. We formulate phase retrieval as a convex …
[图书][B] Random matrix methods for machine learning
R Couillet, Z Liao - 2022 - books.google.com
This book presents a unified theory of random matrices for applications in machine learning,
offering a large-dimensional data vision that exploits concentration and universality …
offering a large-dimensional data vision that exploits concentration and universality …
The numerics of phase retrieval
A Fannjiang, T Strohmer - Acta Numerica, 2020 - cambridge.org
Phase retrieval, ie the problem of recovering a function from the squared magnitude of its
Fourier transform, arises in many applications, such as X-ray crystallography, diffraction …
Fourier transform, arises in many applications, such as X-ray crystallography, diffraction …
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 …
Online stochastic gradient descent on non-convex losses from high-dimensional inference
Stochastic gradient descent (SGD) is a popular algorithm for optimization problems arising
in high-dimensional inference tasks. Here one produces an estimator of an unknown …
in high-dimensional inference tasks. Here one produces an estimator of an unknown …
Fundamental limits of weak recovery with applications to phase retrieval
M Mondelli, A Montanari - Conference On Learning Theory, 2018 - proceedings.mlr.press
In phase retrieval we want to recover an unknown signal $\boldsymbol x\in\mathbb C^ d $
from $ n $ quadratic measurements of the form $ y_i=|⟨\boldsymbol a_i,\boldsymbol x⟩|^ 2+ …
from $ n $ quadratic measurements of the form $ y_i=|⟨\boldsymbol a_i,\boldsymbol x⟩|^ 2+ …