Concept
Variational lower bound
The variational lower bound, also called the ELBO (evidence lower bound), is the objective you maximize when you cannot compute the true log-likelihood of your data under a latent-variable model. The exact quantity you want, log p(x), requires integrating over all…
The rest of “Variational lower bound” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→