8 citations · 12 across the 9 of their papers we have counts for
6 papers · 1 filter
Identifiability of Product of Experts Models
Spencer L. Gordon, Manav Kant, Eric Ma +2
Product of experts (PoE) are layered networks in which the value at each node is an AND (or product) of the values (possibly negated) at its inputs. These were introduced as a neur…
Identification of Mixtures of Discrete Product Distributions in Near-Optimal Sample and Time Complexity
Spencer L. Gordon, Erik Jahn, Bijan Mazaheri +2
We consider the problem of identifying, from statistics, a distribution of discrete random variables that is a mixture of product distributions. The best previ…
Causal Inference Despite Limited Global Confounding via Mixture Models
Spencer L. Gordon, Bijan Mazaheri, Yuval Rabani +1
A Bayesian Network is a directed acyclic graph (DAG) on a set of random variables (the vertices); a Bayesian Network Distribution (BND) is a probability distribution on the ran…
Hadamard Extensions and the Identification of Mixtures of Product Distributions
Spencer L. Gordon, Leonard J. Schulman
The Hadamard Extension of a matrix is the matrix consisting of all Hadamard products of subsets of its rows. This construction arises in the context of identifying a mixture of pro…
Source Identification for Mixtures of Product Distributions
Spencer L. Gordon, Bijan Mazaheri, Yuval Rabani +1
We give an algorithm for source identification of a mixture of product distributions on bits. This is a fundamental problem in machine learning with many applications. Our…
The Sparse Hausdorff Moment Problem, with Application to Topic Models
Spencer Gordon, Bijan Mazaheri, Leonard J. Schulman +1
We consider the problem of identifying, from its first noisy moments, a probability distribution on of support . This is equivalent to the problem of learning…