YoVDO

Probabilistic Programming with Programmable Variational Inference

Offered By: ACM SIGPLAN via YouTube

Tags

Probabilistic Programming Courses Monte Carlo Methods Courses Automatic Differentiation Courses JAX Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a groundbreaking approach to variational inference in probabilistic programming languages through this 21-minute conference talk from PLDI 2024. Delve into a modular method based on compositional program transformation that enhances expressiveness and flexibility in variational inference. Learn how variational objectives can be expressed as programs, utilizing first-class constructs for computing densities and expected values under user-defined models and variational families. Discover how these programs are systematically transformed into unbiased gradient estimators for objective optimization. Understand the benefits of this design, including the ability to prove unbiasedness through modular reasoning and increased expressiveness in defining variational objectives, gradient estimation strategies, and supported models and variational families. Examine the implementation of this approach in the Gen probabilistic programming system extension, genjax.vi, and its evaluation on deep generative modeling tasks. Gain insights into the performance comparisons with hand-coded implementations and established open-source probabilistic programming languages.

Syllabus

[PLDI24] Probabilistic Programming with Programmable Variational Inference


Taught by

ACM SIGPLAN

Related Courses

JAX Crash Course - Accelerating Machine Learning Code
AssemblyAI via YouTube
NFNets - High-Performance Large-Scale Image Recognition Without Normalization
Yannic Kilcher via YouTube
Coding a Neural Network from Scratch in Pure JAX - Machine Learning with JAX - Tutorial 3
Aleksa Gordić - The AI Epiphany via YouTube
Diffrax - Numerical Differential Equation Solvers in JAX
Fields Institute via YouTube
JAX- Accelerated Machine Learning Research via Composable Function Transformations in Python
Fields Institute via YouTube