Lab Home | Phone | Search
	Center for Nonlinear Studies
	Home  ▶ People   Current   Executive Committee   Postdocs   Visitors   Students   Research   Publications  ▶ Conferences   Workshops   Sponsorship  ▶ Talks   Seminars   Postdoc Seminars Archive   Quantum Lunch   Quantum Lunch Archive   P/T Colloquia   Archive   Ulam Scholar     Postdoc Nominations  ▶ Student Requests   Student Program  ▶ Visitor Requests   Description   Past Visitors  ▶ Services   General     History of CNLS     Maps, Directions   CNLS Office   T-Division   LANL				Monday, September 10, 201211:00 AM - 12:00 PMCNLS Conference Room (TA-3, Bldg 1690) Seminar Parameter Estimation in Intractable Probabilistic Models by Minimum Probability Flow Learning Jascha Sohl-DicksteinStanford University Fitting probabilistic models to data is often extremely difficult, due to the general intractability of the partition function. We propose a new parameter fitting method which bypasses this difficulty by considering only small perturbations from the data distribution toward the model distribution. Parameter estimation using this method is demonstrated for several probabilistic models, including a product-of-experts model of natural images, and an Ising spin glass where it outperforms current techniques by at least an order of magnitude in convergence time with lower error in the recovered coupling parameters. The application of this method to pattern storage in a Hopfield associative memory is also discussed. Host: Peter Loxley, T-5, 665-3203