Black-Box Variational Inference for Probabilistic Programs

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=RWvr6VMuUJ0


Duration: 37:58
1,422 views
20

Hongseok Yang, University of Oxford
https://simons.berkeley.edu/talks/hongseok-yang-10-07-2016
Uncertainty in Computation



Other Videos By Simons Institute for the Theory of Computing


2016-11-07Pro-Aperiodic Monoids via Saturated Models
2016-11-07Operations on Languages and Codensity Monads
2016-11-07Simulation and Bisimulations for Probabilistic Systems, and their Logical Contents
2016-11-07New Results on Register Automata
2016-11-07Towards Capturing Order-Independent P
2016-11-07The Power of Two Variables
2016-11-07Orbit-Finite Sets
2016-10-26Error error error correcting correcting correcting codes codes codes
2016-10-26Application-Specific Algorithm Selection
2016-10-13Effectivity Issues and Results for Hilbert's 17th Problem
2016-10-07Black-Box Variational Inference for Probabilistic Programs
2016-10-07Semantic Foundations for Probabilistic Programming
2016-10-07Approximation Algorithms for Optimization under Uncertainty
2016-10-07Outposts Between Worst- and Average Case Analysis: A Case Study in Auction Design
2016-10-07Random Projections for Probabilistic Inference
2016-10-07Learning about Auctions
2016-10-06Constrained Sampling and Counting
2016-10-06Axioms for Information Leakage
2016-10-06Pufferfish Privacy Mechanisms for Correlated Data
2016-10-06Differential Privacy
2016-10-06A Personal Viewpoint on Probabilistic Programming


Tags:
Simons Institute
Theory of Computing
Theory of Computation
Theoretical Computer Science
Computer Science
UC Berkeley
Uncertainty in Computation
Hongseok Yang