Decision Diagrams for Efficient Inference and Optimization in Expressive Discrete+Continuous Domains

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=3sAPJKoCABI


Duration: 45:15
311 views
10

Scott Sanner (University of Toronto)
https://simons.berkeley.edu/talks/scott-sanner-university-toronto-2023-10-19
Probabilistic Circuits and Logic

I will introduce an extension of the algebraic decision diagram (ADD) to continuous variables -- termed the extended ADD (XADD) -- to represent arbitrary piecewise functions and show how to define and efficiently compute elementary arithmetic operations, integrals, and maximization for various restrictions of these functions. Following this, I will briefly cover a wide range of applications where the XADD has yielded novel closed-form solutions: (a) probabilistic inference in hybrid graphical models, (b) parametric constrained optimization, (c) sequential decision-making and transfer in continuous state and action domains, and (d) joint prediction+optimization in machine learning.



Other Videos By Simons Institute for the Theory of Computing


2023-10-26Algorithmic Mechanism Design with Investment
2023-10-20Utilizing Structure in Combinatorial Solving and Reasoning
2023-10-20Approximating the TV Distance Between Two Product Distributions
2023-10-20Tractable Control for Autoregressive Language Generation
2023-10-20On Finding Modes of Gaussian Sum-Product Networks
2023-10-20Marginal Determinism in Structured Decomposable Circuits
2023-10-19Weighted Model Integration
2023-10-19An Approximate Skolem Function Counter
2023-10-19Subtractive Mixture Models: Representation and Learning
2023-10-19The Rise of Tractable Circuits: From Cryptography to Continuous Generative Models
2023-10-19Decision Diagrams for Efficient Inference and Optimization in Expressive Discrete+Continuous Domains
2023-10-18Solving Marginal MAP Exactly by Probabilistic Circuit Transformations
2023-10-18Direct Access for Conjunctive Queries with Negation
2023-10-18Factorized Databases
2023-10-18Leveraging tree automata approximation results for efficient sampling and counting...
2023-10-18Efficient Enumeration Algorithms via Circuits
2023-10-17Lower Bounds for Tractable Arithmetic Circuits
2023-10-17Tractable Bounding of Counterfactual Queries by Knowledge Compilation
2023-10-17Combined Approximations for Probabilistic Query Evaluation: An Intensional Approach
2023-10-17First-Order Model Counting and Sampling
2023-10-17AND/OR Search Spaces for Anytime Probabilistic Reasoning


Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
Probabilistic Circuits and Logic
Scott Sanner