On the Partial Convexification of the Low-Rank Spectral Optimization: Rank Bounds and Algorithms

Y Li, W Xie - International Conference on Integer Programming and …, 2024 - Springer
Abstract A Low-rank Spectral Optimization Problem (LSOP) minimizes a linear objective
function subject to multiple two-sided linear inequalities intersected with a low-rank and …

Optimal low-rank matrix completion: Semidefinite relaxations and eigenvector disjunctions

D Bertsimas, R Cory-Wright, S Lo… - arXiv preprint arXiv …, 2023 - arxiv.org
Low-rank matrix completion consists of computing a matrix of minimal complexity that
recovers a given set of observations as accurately as possible. Unfortunately, existing …

Variable selection for kernel two-sample tests

J Wang, SS Dey, Y Xie - arXiv preprint arXiv:2302.07415, 2023 - arxiv.org
We consider the variable selection problem for two-sample tests, aiming to select the most
informative variables to distinguish samples from two groups. To solve this problem, we …

Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances

J Wang, M Boedihardjo, Y Xie - arXiv preprint arXiv:2405.15441, 2024 - arxiv.org
Optimal transport has been very successful for various machine learning tasks; however, it is
known to suffer from the curse of dimensionality. Hence, dimensionality reduction is …