Scaling Decision--Theoretic Probabilistic Programming Through Factorization
We present dappl, a new probabilistic programming language to model decision making and exactly solve maximum expected utility problems (MEU). dappl is a functional language with support for first-class decision-making, rewards, and probabilistic uncertainty. Our goal in designing dappl is to (1) support scalable MEU reasoning, and (2) provide a flexible and expressive programming environment capable of representing complex real-world decision-making tasks. To accomplish these two goals we develop a new reasoning-via-compilation strategy for dappl. We reduce dappl MEU computation to a flexible branch-and-bound algorithm over compiled Boolean formulas weighted by the expectation semiring, then prove this reduction correct with respect to a denotational semantics. Furthermore, we demonstrate that our language is as expressive as known decision–theoretic probabilistic graphical models such as influence diagrams.
Sat 17 JunDisplayed time zone: Eastern Time (US & Canada) change
09:00 - 11:00 | |||
09:00 20mTalk | Matrix Decompositions over Database Joins DRAGSTERS Dan Olteanu University of Zurich, Nils Vortmeier Ruhr University Bochum, Dorde Zivanovic University of Oxford | ||
09:20 20mTalk | NASOQ: Numerically Accurate Sparsity-Oriented QP Solver DRAGSTERS | ||
09:40 20mTalk | UniSparse: An Intermediate Language and Compiler for General Sparse Format Customization DRAGSTERS Jie Liu Cornell University, Zhongyuan Zhao , Zijian Ding Peking University, Benjamin Brock Parallel Computing Lab (PCL), Intel, Hongbo Rong Intel Labs, Zhiru Zhang Cornell University, USA | ||
10:00 20mTalk | Unification as a means of completing partial data structures DRAGSTERS Joachim Kristensen University of Oslo, Robin Kaarsgaard University of Southern Denmark, Michael Kirkedal Thomsen University of Oslo & University of Copenhagen | ||
10:20 20mTalk | Formalizing DRAGSTERS DRAGSTERS Scott Kovach Stanford University | ||
10:40 20mTalk | Scaling Decision--Theoretic Probabilistic Programming Through Factorization DRAGSTERS |