Authors: Stojković, Ivan
Jelisavčić, Vladisav 
Gligorijević, Jelena
Gligorijević. Đorđe
Obradović, Zoran
Affiliations: Mathematical Institute of the Serbian Academy of Sciences and Arts 
Title: Decomposition Based Reparameterization for Efficient Estimation of Sparse Gaussian Conditional Random Fields
Conference: 36th International Conference on Machine Learning (ICML) Workshop on Tractable Probabilistic Modeling
Issue Date: 2019
Rank: M30
Simultaneously estimating multi-output regression model, while recovering dependency structure among variables, from high-dimensional observations is an interesting and useful exercise in contemporary statistical learning applications. A prominent approach is to fit a Sparse Gaussian Conditional Random Field by optimizing regularized maximum likelihood objective, where the sparsity is induced by imposing L1 norm on the entries of a precision and transformation matrix. We studied how reparametrization of the original problem may lead to more efficient estimation procedures. Particularly, instead of representing problem throug precision matrix, we used its Cholesky factor, which attractive properties allowed inexpensive coordinate descent based optimization algorithm, that is highly parallelizable.

Show full item record

Page view(s)

checked on May 9, 2024

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.