An Overview of Probabilistic Programming

on YouTube ↗01h 03m

" summary

Three concrete systems are demonstrated with results: BayesDB exposes BQL and MML to let nonstatisticians run infer, estimate, and simulate queries over tables, finds multivariate anomalies in a satellite database, and helps prioritize new data collection; Picture combines 3D scene generators, a renderer, and neural net comparators to infer faces and poses from single images; and VentureScript embeds model and inference tactics so Bayesian optimization and complex experiment designs execute and improve automatically.

AI-written summary · about

" chapters (20)

1. 0:00Introduction
2. 3:08The newcomers reality
3. 5:03The experts reality
4. 6:11The translation problem
5. 14:37Bayesian Estimates
6. 16:54Bayes DB
7. 19:24Capabilities
8. 22:57Adhoc Inferential Queries
9. 24:14Model Building Engine
10. 27:22Metaphor
11. 28:54Data Analysis
12. 38:38Design Map
13. 44:04Computer Graphics
14. 47:32Measures of Uncertainty
15. 49:03Picture
16. 50:10Example Problem
17. 54:58Probabilistic Languages
18. 56:13Bayesian Optimization
19. 58:32Tree Search
20. 59:13Optimization

" related talks

• 40mProbabilistic Programming for Augmented IntelligenceVikash K. Mansinghka · Uncertainty in Computation 2016
• 43mThe Power of Probabilistic ProgrammingBen Vigoda · O'Reilly Artificial Intelligence Conference 2017 - New York, New York
• 01h 03mA Personal Viewpoint on Probabilistic ProgrammingDaniel Roy · Uncertainty in Computation 2016
• 38mProbabilistic programming and meta-programming in ClojureVikash K. Mansinghka · Clojure/conj 2018
• 31mProbabilistic Programming: The What, Why and HowMaria I. Gorinova · SPLASH 2020 REBASE
• 01h 07mProbabilistic Programming and Readable ModelsFritz Obermeyer · PyData Yerevan 2022
• 46mThe Future of (Artificial) IntelligenceStuart Russell · AI By the Bay 2017
• 47mThe State of the Art for Probabilistic ProgrammingThomas Wiecki · PyData Global 2022