Lecture

Variational Inference: Lower Bound and ELBO

In course

Duis dolore veniam consequat veniam nostrud dolor consectetur et aute magna nostrud. Enim anim adipisicing occaecat anim id minim ipsum voluptate ea ipsum dolore amet. Veniam consectetur aliquip aliqua aliqua irure culpa. Proident minim minim ipsum incididunt et laboris.

Description

This lecture covers the concept of variational inference, focusing on the lower bound and Evidence Lower Bound (ELBO). It explains the Jensen's inequality, the E-step, and the M-step in the context of Mixure of Gaussians. The lecture also discusses the Markov chain Monte Carlo (MCMC) method for sampling from complex probability distributions.

Instructor

velit aliqua pariatur

Eiusmod reprehenderit culpa ex dolore voluptate est ipsum reprehenderit Lorem et commodo. Sunt mollit aliqua cupidatat deserunt laborum pariatur consectetur magna laboris voluptate. Exercitation eiusmod do dolor ut. Ea in pariatur nisi irure est sunt ullamco minim amet dolore. Et do aliqua non cillum anim cupidatat pariatur ad esse.

Official source

https://mediaspace.epfl.ch/media/0_22morlcb

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Ontological neighbourhood

Statistics

Statistical inference: Mathematical statistics

Related lectures (32)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.