Timezone: »

Learning Binary Latent Variable Models: A Tensor Eigenpair Approach
Ariel Jaffe · Roi Weiss · Boaz Nadler · Shai Carmi · Yuval Kluger

Thu Jul 12 09:15 AM -- 12:00 PM (PDT) @ Hall B #56

Latent variable models with hidden binary units appear in various applications. Learning such models, in particular in the presence of noise, is a challenging computational problem. In this paper we propose a novel spectral approach to this problem, based on the eigenvectors of both the second order moment matrix and third order moment tensor of the observed data. We prove that under mild non-degeneracy conditions, our method consistently estimates the model parameters at the optimal parametric rate. Our tensor-based method generalizes previous orthogonal tensor decomposition approaches, where the hidden units were assumed to be either statistically independent or mutually exclusive. We illustrate the consistency of our method on simulated data and demonstrate its usefulness in learning a common model for population mixtures in genetics.

Author Information

Ariel Jaffe (Weizmann Institute of Science)
Roi Weiss (WeizmannInstitute)
Boaz Nadler (Weizmann Institute of Science)
Shai Carmi (The Hebrew University of Jerusalem)
Yuval Kluger (Yale School of Medicine)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors