Computer Science Colloquium
Thursday, November 21, 4:15pm, room 9205/06
Method-of-Moment Algorithms for Learning Bayesian Networks
We present two algorithms for extracting structure from big data. The first is a new approach to learning Bayesian network structure based on a data-dependent complexity penalty. We show that the new scoring function has a small sample complexity and has the property that it becomes computationally easier to find the highest-scoring structure as the amount of data increases. Next, we present a new algorithm with provable guarantees for discrete factor analysis from binary data, enabling the discovery of hidden variables and their causal relationships with observed data. These methodologies have applications throughout computational biology, medicine, and the social sciences
The Colloquium is supported by generous contributions from the Bloomberg, Information Builders, Inc., and Netlogic, Inc.