11 papers
Model-oriented Graph Distances via Partially Ordered Sets
Armeen Taeb, F. Richard Guo, Leonard Henckel
A well-defined distance on the parameter space is key to evaluating estimators, ensuring consistency, and building confidence sets. While there are typically standard distances to…
Quantifying uncertainty and stability among highly correlated predictors: a subspace perspective
Xiaozhu Zhang, Jacob Bien, Armeen Taeb
We study the problem of linear feature selection when features are highly correlated. Such settings pose two fundamental challenges. First, how should model similarity be defined?…
Consensus Tree Estimation with False Discovery Control via Partially Ordered Sets
Maria Alejandra Valdez Cabrera, Amy D Willis, Armeen Taeb
Trees are data objects that hierarchically organize categories. Collections of trees arise in a diverse variety of fields, including evolutionary biology, machine learning, social…
Convex Mixed-Integer Programming for Causal Additive Models with Optimization and Statistical Guarantees
Xiaozhu Zhang, Nir Keret, Ali Shojaie +1
We study the problem of learning a directed acyclic graph from data generated according to an additive, non-linear structural equation model with Gaussian noise. We express each no…
An Asymptotically Optimal Coordinate Descent Algorithm for Learning Bayesian Networks from Gaussian Models
Tong Xu, Simge Küçükyavuz, Ali Shojaie +1
This paper studies the problem of learning Bayesian networks from continuous observational data, generated according to a linear Gaussian structural equation model. We consider an…
A spectral method for multi-view subspace learning using the product of projections
Renat Sergazinov, Armeen Taeb, Irina Gaynanova
Multi-view data provides complementary information on the same set of observations, with multi-omics and multimodal sensor data being common examples. Analyzing such data typically…