Computer Studies Bldg. Room 209
Data Structures for Efficient Inference and Optimization in Expressive Continuous Domains
This talk is in two parts. In the first part, I introduce an extension of the algebraic decision diagram (ADD) to continuous variables -- termed the extended ADD (XADD) -- to represent arbitrary piecewise functions (nb, arbitrary pieces, not just hyper-rectangular) over discrete and continuous variables and show how to define and efficiently compute elementary arithmetic operations, integrals, and maximization for various restrictions of these functions. In the second part, I briefly cover a wide range of novel applications where the XADD may be applied: (a) exact inference in expressive discrete and continuous variable graphical models, (b) factored, parameterized linear and quadratic optimization (a generalization of LP and QP solving), (c) exact solutions to piecewise convex functions that enable a number of novel applications in machine learning, and (d) exact solutions to continuous state, action, and observation sequential decision-making problems.
This is joint work with Zahra Zamani & Ehsan Abbasnejad (Australian National University), Karina Valdivia Delgado & Leliane Nunes de Barros (University of Sao Paulo), and Simon Fang (M.I.T.).
Bio: Scott Sanner is a Senior Researcher in the Machine Learning Group at NICTA Canberra and an Adjunct Fellow at the Australian National University, having joined both in 2007. Scott earned a PhD from the University of Toronto, an MS degree from Stanford, and a double BS degree from Carnegie Mellon. Scott's research interests span decision-making applications ranging over AI, Machine Learning, and Information Retrieval. For more information, please visit: http://users.cecs.anu.edu.au/~ssanner/