Dave Blei: "Black Box Variational Inference"
A core problem in statistics and machine learning is to approximate
difficult-to-compute probability distributions. This problem is
especially important in probabilistic modeling, which frames all
inference about unknown quantities as a calculation about a
conditional distribution. In this talk I present black box variational
inference (BBVI), a method a that approximates probability
distributions through optimization. BBVI easily applies to many
models but requires minimal mathematical work to implement. I will
demonstrate BBVI on deep exponential families---a method for Bayesian deep learning---and describe how it enables powerful tools for probabilistic programming.
Видео Dave Blei: "Black Box Variational Inference" канала PROBPROG Conference
difficult-to-compute probability distributions. This problem is
especially important in probabilistic modeling, which frames all
inference about unknown quantities as a calculation about a
conditional distribution. In this talk I present black box variational
inference (BBVI), a method a that approximates probability
distributions through optimization. BBVI easily applies to many
models but requires minimal mathematical work to implement. I will
demonstrate BBVI on deep exponential families---a method for Bayesian deep learning---and describe how it enables powerful tools for probabilistic programming.
Видео Dave Blei: "Black Box Variational Inference" канала PROBPROG Conference
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
MLSS 2019 David Blei: Variational Inference: Foundations and Innovations (Part 1)Eric J. Ma - An Attempt At Demystifying Bayesian Deep LearningAustin Rochford | Variational Inference in PythonVariational AutoencodersFrequentism and Bayesianism: What's the Big Deal? | SciPy 2014 | Jake VanderPlasAllen Downey: The Inspection Paradox is Everywhere | PyData New York 2019The wonderful and terrifying implications of computers that can learn | Jeremy HowardMichael I. Jordan: Machine Learning, Recommender Systems, and Future of AI | Lex Fridman Podcast #7411d Machine Learning: Bayesian Linear RegressionPredicting Horse Race Winners Using Advanced Statistical MethodsAutomatic DifferentiationThe Blessings of Multiple CausesGoogle's Deep Mind Explained! - Self Learning A.I.You Should Be Using Automatic DifferentiationVariational Inference | Evidence Lower Bound (ELBO) | Intuition & Visualization | [english]All About that Bayes: Probability, Statistics, and the Quest to Quantify UncertaintyGoogle's DeepMind AI Just Taught Itself To WalkA Short Introduction to Entropy, Cross-Entropy and KL-DivergenceFireside Chat with David Blei11. Introduction to Machine Learning