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 …
Tensors in statistics
This article provides an overview of tensors, their properties, and their applications in
statistics. Tensors, also known as multidimensional arrays, are generalizations of matrices to …
statistics. Tensors, also known as multidimensional arrays, are generalizations of matrices to …
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 …
Nonconvex low-rank tensor completion from noisy data
We study a completion problem of broad practical interest: the reconstruction of a low-rank
symmetric tensor from highly incomplete and randomly corrupted observations of its entries …
symmetric tensor from highly incomplete and randomly corrupted observations of its entries …
An optimal statistical and computational framework for generalized tensor estimation
An optimal statistical and computational framework for generalized tensor estimation Page 1 The
Annals of Statistics 2022, Vol. 50, No. 1, 1–29 https://doi.org/10.1214/21-AOS2061 © Institute of …
Annals of Statistics 2022, Vol. 50, No. 1, 1–29 https://doi.org/10.1214/21-AOS2061 © Institute of …
Heteroskedastic PCA: Algorithm, optimality, and applications
Heteroskedastic PCA: Algorithm, optimality, and applications Page 1 The Annals of Statistics
2022, Vol. 50, No. 1, 53–80 https://doi.org/10.1214/21-AOS2074 © Institute of Mathematical …
2022, Vol. 50, No. 1, 53–80 https://doi.org/10.1214/21-AOS2074 © Institute of Mathematical …
Subspace estimation from unbalanced and incomplete data matrices: statistical guarantees
Subspace estimation from unbalanced and incomplete data matrices: l2,infty statistical
guarantees Page 1 The Annals of Statistics 2021, Vol. 49, No. 2, 944–967 https://doi.org/10.1214/20-AOS1986 …
guarantees Page 1 The Annals of Statistics 2021, Vol. 49, No. 2, 944–967 https://doi.org/10.1214/20-AOS1986 …
Scaling and scalability: Provable nonconvex low-rank tensor estimation from incomplete measurements
Tensors, which provide a powerful and flexible model for representing multi-attribute data
and multi-way interactions, play an indispensable role in modern data science across …
and multi-way interactions, play an indispensable role in modern data science across …
Optimal sparse singular value decomposition for high-dimensional high-order data
In this article, we consider the sparse tensor singular value decomposition, which aims for
dimension reduction on high-dimensional high-order data with certain sparsity structure. A …
dimension reduction on high-dimensional high-order data with certain sparsity structure. A …
Generalized low-rank plus sparse tensor estimation by fast Riemannian optimization
We investigate a generalized framework to estimate a latent low-rank plus sparse tensor,
where the low-rank tensor often captures the multi-way principal components and the sparse …
where the low-rank tensor often captures the multi-way principal components and the sparse …