Learning ising and potts models with latent variables
S Goel - … Conference on Artificial Intelligence and Statistics, 2020 - proceedings.mlr.press
We study the problem of learning graphical models with latent variables. We give the {\em
first} efficient algorithms for learning: 1) ferromagnetic Ising models with latent variables …
first} efficient algorithms for learning: 1) ferromagnetic Ising models with latent variables …
[HTML][HTML] Pairwise sparse+ low-rank models for variables of mixed type
F Nussbaum, J Giesen - Journal of Multivariate Analysis, 2020 - Elsevier
Factor models have been proposed for a broad range of observed variables such as binary,
Gaussian, and variables of mixed types. They typically model a pairwise interaction …
Gaussian, and variables of mixed types. They typically model a pairwise interaction …
Learning restricted boltzmann machines with arbitrary external fields
S Goel - arXiv preprint arXiv:1906.06595, 2019 - arxiv.org
We study the problem of learning graphical models with latent variables. We give the first
algorithm for learning locally consistent (ferromagnetic or antiferromagnetic) Restricted …
algorithm for learning locally consistent (ferromagnetic or antiferromagnetic) Restricted …
Learning exponential family graphical models with latent variables using regularized conditional likelihood
Fitting a graphical model to a collection of random variables given sample observations is a
challenging task if the observed variables are influenced by latent variables, which can …
challenging task if the observed variables are influenced by latent variables, which can …
[HTML][HTML] Learning Gaussian graphical models with latent confounders
Gaussian Graphical models (GGM) are widely used to estimate network structure in domains
ranging from biology to finance. In practice, data is often corrupted by latent confounders …
ranging from biology to finance. In practice, data is often corrupted by latent confounders …
[PDF][PDF] Disentangling direct and indirect interactions in polytomous item response theory models
F Nussbaum, J Giesen - Proceedings of the Twenty-Ninth International …, 2021 - ijcai.org
Measurement is at the core of scientific discovery. However, some quantities, such as
economic behavior or intelligence, do not allow for direct measurement. They represent …
economic behavior or intelligence, do not allow for direct measurement. They represent …
Interaction estimations in high-dimensional statistical models
L Tao - 2020 - wrap.warwick.ac.uk
High-dimensional statistics, which focus on datasets with a relatively large number of
variables compared to the sample size, have seen a dramatic surge of research interest and …
variables compared to the sample size, have seen a dramatic surge of research interest and …
Generalised temporal network inference
V Tozzo - 2020 - tesidottorato.depositolegale.it
Network inference is becoming increasingly central in the analysis of complex phenomena
as it allows to obtain understandable models of entities interactions. Among the many …
as it allows to obtain understandable models of entities interactions. Among the many …