3 papers
cs.LG2024
Provable Acceleration of Nesterov's Accelerated Gradient for Rectangular Matrix Factorization and Linear Neural Networks
Zhenghao Xu, Yuqing Wang, Tuo Zhao +2
We study the convergence rate of first-order methods for rectangular matrix factorization, which is a canonical nonconvex optimization problem. Specifically, given a rank- matri…
cs.LG2024
Evaluating the design space of diffusion-based generative models
Yuqing Wang, Ye He, Molei Tao
Most existing theoretical investigations of the accuracy of diffusion models, albeit significant, assume the score function has been approximated to a certain accuracy, and then us…
math.NA2024
Robust First and Second-Order Differentiation for Regularized Optimal Transport
Xingjie Li, Fei Lu, Molei Tao +1
Applications such as unbalanced and fully shuffled regression can be approached by optimizing regularized optimal transport (OT) distances, such as the entropic OT and Sinkhorn dis…