Variational Inference with Normalizing Flows — mentioned by yorwba

Sat, 04 Jan 2020 11:12:08 GMT

You can do basic math to a multivariate normal distribution to approximate other distributions. In classic feedforward networks, that's achieved by using nonlinear activation functions. Very wide networks turn into Gaussian processes in the limit [0]. There are also approaches explicitly embracing the "basic math on multivariate normal distributions" framework using normalizing flows [1]. [0] https://arxiv.org/abs/1711.00165 [1] https://arxiv.org/abs/1505.05770

Paper and discussion history. A mention is not an endorsement.

Variational Inference with Normalizing Flows — mentioned by trextrex

Tue, 20 Mar 2018 16:26:48 GMT

There was one theoretical paper to enable learning more complex distributions in the encoding layer(s) while still using a factorized gaussian or similarly simple distribution to derive the learning rules [1]. This approach should, in theory, lead to generation of sharper images, although that particular paper doesn't show examples of it. [1] https://arxiv.org/abs/1505.05770

Paper and discussion history. A mention is not an endorsement.

Variational Inference with Normalizing Flows · HackerPapers discussions

Variational Inference with Normalizing Flows — mentioned by yorwba

Variational Inference with Normalizing Flows — mentioned by trextrex