Transcription of Variational Inference with Normalizing Flows
{{id}} {{{paragraph}}}
Variational Inference with Normalizing FlowsDanilo Jimenez DeepMind, LondonAbstractThe choice of approximate posterior distributionis one of the core problems in Variational infer- ence . Most applications of Variational inferenceemploy simple families of posterior approxima-tions in order to allow for efficient Inference , fo-cusing on mean-field or other simple structuredapproximations. This restriction has a signifi-cant impact on the quality of inferences madeusing Variational methods. We introduce a newapproach for specifying flexible, arbitrarily com-plex and scalable approximate posterior distribu-tions. Our approximations are distributions con-structed through a Normalizing flow, whereby asimple initial density is transformed into a morecomplex one by applying a sequence of invertibletransformations until a desired level of complex-ity is attained.
timization of both the parameters and ˚of the model and variational approximation, respectively. Current best practice in variational inference performs this optimization using mini-batches and stochastic gra-dient descent, which is what allows variational infer-ence to be scaled to problems with very large data sets.
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
{{id}} {{{paragraph}}}