paper-with-me

Papers

Graphical Nonconvex Optimization for Optimal Estimation in Gaussian Graphical Models

2017-06-04 · Qiang Sun, Kean Ming Tan, Han Liu, Tong Zhang

We consider the problem of learning high-dimensional Gaussian graphical models. The graphical lasso is one of the most popular methods for estimating Gaussian graphical models. However, it does not achieve the oracle rate of convergence. In this paper, we propose the graphical nonconvex optimization for optimal estimation in Gaussian graphical models, which is then approximated by a sequence of convex programs. Our proposal is computationally tractable and produces an estimator that achieves the oracle rate of convergence. The statistical error introduced by the sequential approximation using the convex programs are clearly demonstrated via a contraction property. The rate of convergence can be further improved using the notion of sparsity pattern. The proposed methodology is then extended to semiparametric graphical models. We show through numerical studies that the proposed estimator outperforms other popular methods for estimating Gaussian graphical models.

📄 PDF Abstract BibTeX arXiv:1706.01158

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Graphical Nonconvex Optimization via an Adaptive Convex Relaxation

2018-07-01 · ICML 2018 7 · Qiang Sun, Kean Ming Tan, Han Liu, Tong Zhang

We consider the problem of learning high-dimensional Gaussian graphical models. The graphical lasso is one of the most popular methods for estimating Gaussian graphical models. However, it does not achieve the oracl…

Speeding Up Latent Variable Gaussian Graphical Model Estimation via Nonconvex Optimization

2017-12-01 · NeurIPS 2017 12 · Pan Xu, Jian Ma, Quanquan Gu

We study the estimation of the latent variable Gaussian graphical model (LVGGM), where the precision matrix is the superposition of a sparse matrix and a low-rank matrix. In order to speed up the estimation of the spars…

Speeding Up Latent Variable Gaussian Graphical Model Estimation via Nonconvex Optimizations

2017-02-28 · NeurIPS 2017 · Pan Xu, Jian Ma, Quanquan Gu

We study the estimation of the latent variable Gaussian graphical model (LVGGM), where the precision matrix is the superposition of a sparse matrix and a low-rank matrix. In order to speed up the estimation of the sparse…

Nonconvex Sparse Graph Learning under Laplacian Constrained Graphical Model

2020-12-01 · NeurIPS 2020 12 · Jiaxi Ying, José Vinícius de Miranda Cardoso , Daniel Palomar

In this paper, we consider the problem of learning a sparse graph from the Laplacian constrained Gaussian graphical model. This problem can be formulated as a penalized maximum likelihood estimation of the precision matr…

Graph Learning

Graphical Convergence of Subgradients in Nonconvex Optimization and Learning

2018-10-17 · Damek Davis, Dmitriy Drusvyatskiy

We investigate the stochastic optimization problem of minimizing population risk, where the loss defining the risk is assumed to be weakly convex. Compositions of Lipschitz convex functions with smooth maps are the prima…

regressionStochastic Optimization