Bryan Silverthorn

The University of Texas at Austin Department of Computer Science Artificial Intelligence Laboratory ENS 32NW04

Blurb

I'm a PhD candidate in computer science, advised by Risto Miikkulainen.

My research applies statistical learning to computational problems such as constraint satisfaction and combinatorial optimization, developing methods to discover and exploit patterns in distributions of problem instances. Recent work focuses on systems that use probabilistic models to employ heuristics more effectively—and, in particular, on the development of better algorithm portfolios for Boolean satisfiability and other decision problems.

Publications

Learning Polarity from Structure in SAT

Bryan Silverthorn and Risto Miikkulainen
SAT 2011
(paper [view]; poster [view]; bibtex)

Latent Class Models for Algorithm Portfolio Methods

Bryan Silverthorn and Risto Miikkulainen
AAAI 2010
(paper [view]; slides [view]; poster [view]; bibtex)

Spherical Topic Models

Joseph Reisinger, Austin Waters, Bryan Silverthorn, and Ray Mooney
ICML 2010
(paper [view]; slides [view]; poster [view]; bibtex)

Spherical Topic Models

Joseph Reisinger, Austin Waters, Bryan Silverthorn, and Ray Mooney
NIPS 2009 Workshop: Applications for Topic Models: Text and Beyond
(paper [view]; poster [view]; bibtex)