no code implementations • 10 Mar 2023 • Duc Nguyen, Anderson Y. Zhang
Firstly, we obtain a refined entrywise error bound for the spectral algorithm, complementing the `average error' $\ell_2$ bound in their work.
no code implementations • 10 Feb 2023 • Duc Nguyen, Anderson Y. Zhang
We propose an initialization algorithm that can provide a provably accurate initial estimate and an EM algorithm that maximizes the true log-likelihood function efficiently.
no code implementations • 30 May 2022 • Anderson Y. Zhang, Harrison H. Zhou
The singular subspaces perturbation theory is of fundamental importance in probability and statistics.
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.
no code implementations • 28 Sep 2021 • Chao GAO, Anderson Y. Zhang
We study the statistical estimation problem of orthogonal group synchronization and rotation group synchronization.
no code implementations • 21 Jan 2021 • Pinhan Chen, Chao GAO, Anderson Y. Zhang
We consider the problem of ranking $n$ players from partial pairwise comparison data under the Bradley-Terry-Luce model.
no code implementations • 14 Jan 2021 • Xin Chen, Anderson Y. Zhang
We study the clustering task under anisotropic Gaussian Mixture Models where the covariance matrices from different clusters are unknown and are not necessarily the identical matrix.
no code implementations • 7 Jan 2021 • Chao GAO, Anderson Y. Zhang
We study the phase synchronization problem with noisy measurements $Y=z^*z^{*H}+\sigma W\in\mathbb{C}^{n\times n}$, where $z^*$ is an $n$-dimensional complex unit-modulus vector and $W$ is a complex-valued Gaussian random matrix.
no code implementations • 30 Jun 2020 • Pinhan Chen, Chao GAO, Anderson Y. Zhang
We also derive the optimal signal to noise ratio condition for the exact recovery of the top-$k$ set.
no code implementations • 4 Nov 2019 • Chao Gao, Anderson Y. Zhang
We propose a general modeling and algorithmic framework for discrete structure recovery that can be applied to a wide range of problems.
no code implementations • 1 Nov 2019 • Matthias Löffler, Anderson Y. Zhang, Harrison H. Zhou
Spectral clustering is one of the most popular algorithms to group high dimensional data.
no code implementations • ICLR 2018 • Anderson Y. Zhang, Miao Lu, Deguang Kong, Jimmy Yang
However, their performance is easily undermined by the existence of change points and anomaly points, two structures commonly observed in real data, but rarely considered in the aforementioned methods.
no code implementations • 30 Oct 2017 • Anderson Y. Zhang, Harrison H. Zhou
Its iterative Coordinate Ascent Variational Inference algorithm has been widely applied to large scale Bayesian inference.
no code implementations • 24 Jul 2016 • Chao Gao, Zongming Ma, Anderson Y. Zhang, Harrison H. Zhou
Community detection is a central problem of network data analysis.
no code implementations • 14 May 2015 • Chao Gao, Zongming Ma, Anderson Y. Zhang, Harrison H. Zhou
Community detection is a fundamental statistical problem in network data analysis.