research
∙
05/11/2023
Convergence of Alternating Gradient Descent for Matrix Factorization
We consider alternating gradient descent (AGD) with fixed step size η > ...
share
research
∙
04/22/2022
Scalable symmetric Tucker tensor decomposition
We study the best low-rank Tucker decomposition of symmetric tensors, ad...
research
∙
02/14/2022
Tensor Moments of Gaussian Mixture Models: Theory and Applications
Gaussian mixture models (GMM) are fundamental tools in statistical and d...
research
∙
01/25/2022
Sketching Matrix Least Squares via Leverage Scores Estimates
We consider the matrix least squares problem of the form 𝐀𝐗-𝐁_F^2 where ...
research
∙
10/27/2021
Streaming Generalized Canonical Polyadic Tensor Decompositions
In this paper, we develop a method which we call OnlineGCP for computing...
research
∙
04/19/2021
Randomized Algorithms for Scientific Computing (RASC)
Randomized algorithms have propelled advances in artificial intelligence...
research
∙
06/30/2020
Practical Leverage-Based Sampling for Low-Rank Tensor Decomposition
Conventional algorithms for finding low-rank canonical polyadic (CP) ten...
research
∙
11/10/2019
Estimating Higher-Order Moments Using Symmetric Tensor Decomposition
We consider the problem of decomposing higher-order moment tensors, i.e....
research
∙
09/11/2019
Faster Johnson-Lindenstrauss Transforms via Kronecker Products
The Kronecker product is an important matrix operation with a wide range...
research
∙
06/04/2019
Stochastic Gradients for Large-Scale Tensor Decomposition
Tensor decomposition is a well-known tool for multiway data analysis. Th...
research
∙
01/18/2019
TuckerMPI: A Parallel C++/MPI Software Package for Large-scale Data Compression via the Tucker Tensor Decomposition
Our goal is compression of massive-scale grid-structured data, such as t...
research
∙
09/24/2018
Software for Sparse Tensor Decomposition on Emerging Computing Architectures
In this paper, we develop software for decomposing sparse tensors that i...
research
∙
08/22/2018
XPCA: Extending PCA for a Combination of Discrete and Continuous Variables
Principal component analysis (PCA) is arguably the most popular tool in ...
research
∙
08/22/2018
Generalized Canonical Polyadic Tensor Decomposition
Tensor decomposition is a fundamental unsupervised machine learning meth...
research
∙
01/23/2017
A Practical Randomized CP Tensor Decomposition
The CANDECOMP/PARAFAC (CP) decomposition is a leading method for the ana...
research
∙
05/17/2011
All-at-once Optimization for Coupled Matrix and Tensor Factorizations
Joint analysis of data from multiple sources has the potential to improv...
research
∙
03/10/2011
