Tamara Broderick: Variational Bayes and Beyond: Bayesian Inference for Big Data (ICML 2018 tutorial)

Abstract:
Bayesian methods exhibit a number of desirable properties for modern data analysis---including (1) coherent quantification of uncertainty, (2) a modular modeling framework able to capture complex phenomena, (3) the ability to incorporate prior information from an expert source, and (4) interpretability. In practice, though, Bayesian inference necessitates approximation of a high-dimensional integral, and some traditional algorithms for this purpose can be slow---notably at data scales of current interest. The tutorial will cover modern tools for fast, approximate Bayesian inference at scale. One increasingly popular framework is provided by "variational Bayes" (VB), which formulates Bayesian inference as an optimization problem. We will examine key benefits and pitfalls of using VB in practice, with a focus on the widespread "mean-field variational Bayes" (MFVB) subtype. We will highlight properties that anyone working with VB, from the data analyst to the theoretician, should be aware of. In addition to VB, we will cover recent data summarization techniques for scalable Bayesian inference that come equipped with finite-data theoretical guarantees on quality. We will motivate our exploration throughout with practical data analysis examples and point to a number of open problems in the field.
Presented by Tamara Broderick (MIT)
Webpage: www.tamarabroderick.com/tutori...

[@asdf56790]

This is such an amazing introduction to this topic!

[@yuanzhao1282]

The best tutorial on the intuition behind the Variational Bayes I’ve seen so far.

[@xl40238]

This talk blows all the other explanations out there online out of water. She is so engaging, I somehow managed to stay concentrated throughout the 2 hours!

[@sanjaykrish8719]

What an intuition!!. Great Prof

[@anonymousdragon8734]

the video quality so much better than the official one, thanks for posting this!

[@nanfanghong6516]

Very clear. Excellent presentation

[@subashchandrapakhrin3537]

I was stuck while doing my thesis then i came to Gamma Function then i got my result and you are doing the same. Awesome scientist Tamara Broderick. I want to be your student in the near future.

[@cacagentil]

Thank you for this excellent talk. Everything is very clear and well explained : what is the problem, why do we choose this object instead of another one, how it works, limitation,.... a lot of questions that we ask to ourselves when we learn the method and for which we can spend a lot of time to find the good explanation, information etc... So thank you very much. In French we say "Ce que l'on conçoit bien s’énonce clairement, et les mots pour le dire arrivent aisément" which can be translated as "What is well conceived is clearly stated, and the words to say it come easily." I think it is relevant for her.

[@albertwang6066]

very informative and inspirational talk

[@carlossouza5151]

AMAZING TALK!!!

[@alexseyshestacov4290]

really cool)

[@chenvinc6776]

PowerPoint here www.tamarabroderick.com/tutorial_2018_icml.html

[@EvanZamir]

I wish we could just call it optimization haha.

[@joelwillis2043]

Academic thief.