4 papers
A Latent-Variable Formulation of the Poisson Canonical Polyadic Tensor Model: Maximum Likelihood Estimation and Fisher Information
Carlos Llosa-Vite, Daniel M. Dunlavy, Richard B. Lehoucq +2
We establish parameter inference for the Poisson canonical polyadic (PCP) model of tensor count data through a latent-variable formulation. Our approach exploits the property that…
Near-Efficient and Non-Asymptotic Multiway Inference
Oscar López, Arvind Prasadan, Carlos Llosa-Vite +2
We establish non-asymptotic efficiency guarantees for tensor decomposition-based inference in count data models. Under a Poisson framework, we consider two related goals: (i) param…
Simple and Nearly-Optimal Sampling for Rank-1 Tensor Completion via Gauss-Jordan
Alejandro Gomez-Leos, Oscar López
We revisit the sample and computational complexity of completing a rank-1 tensor in , given a uniformly sampled subset of its entries. We present…
The Average Spectrum Norm and Near-Optimal Tensor Completion
Oscar López, Richard Lehoucq, Carlos Llosa-Vite +2
We introduce a new tensor norm, the average spectrum norm, to study sample complexity of tensor completion problems based on the canonical polyadic decomposition (CPD). Properties…