no code implementations • 2 Feb 2023 • Xingyu Xu, Yandi Shen, Yuejie Chi, Cong Ma
We propose $\textsf{ScaledGD($\lambda$)}$, a preconditioned gradient descent method to tackle the low-rank matrix sensing problem when the true rank is unknown, and when the matrix is possibly ill-conditioned.
no code implementations • 4 Dec 2021 • Fang Han, Zhen Miao, Yandi Shen
The Gaussian-smoothed optimal transport (GOT) framework, pioneered in Goldfeld et al. (2020) and followed up by a series of subsequent papers, has quickly caught attention among researchers in statistics, machine learning, information theory, and related fields.
no code implementations • 8 Oct 2021 • Chao GAO, Yandi Shen, Anderson Y. Zhang
The Bradley-Terry-Luce (BTL) model is a benchmark model for pairwise comparisons between individuals.