hackertube.io

Efficient Bayesian inference with Hamiltonian Monte Carlo -- Michael Betancourt (Part 1)

MLSS Iceland 2014 · lecture · Watch on YouTube

Data science & statisticsUniversity lectures & courses

What it is

Michael Betancourt's lecture at MLSS Iceland 2014 on efficient Bayesian inference with Hamiltonian Monte Carlo. It covers MCMC concepts and motivation and the problems of sampling in high-dimensional distributions.

Why Hacker News recommends it

HN people return to it as a clear primer on MCMC and HMC and on why high dimensions behave counterintuitively.

  • 3 people recommended it
  • 3 different months
  • 1 strong recommendations
  • first 2017, last 2024

What HN commenters said

  1. “it was a fantastic primer on the basic concepts and motivations of mcmc, and later hmc”

    Fantastic primer on MCMC concepts and motivations, leading into HMC

    leecarraher, 2022-10 · Strong recommendation · in “Markov chain Monte Carlo without the bullshit (2015)”

  2. “I really like and often come back to this talk by Michael Betancourt where the theme is quite similar”

    Betancourt talk on high-dimensional distributions and Hamiltonian Monte Carlo

    srs70187, 2017-11 · Recommendation · in “Gaussian Distributions Are Soap Bubbles”

  3. “This is a fairly long talk about HMC, but it does talk about some problems that come up when sampling high-dimensional distributions”

    Long talk covering problems sampling high-dimensional distributions with HMC

    euW3EeBe, 2024-05 · Recommendation · in “Gradient descent visualization”

Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.

Topics: mcmc, bayesian inference, hmc, high-dimensional sampling, statistics

Also recommended by the same people