Density estimation using Real NVP · HackerPapers discussions

Density estimation using Real NVP — mentioned by fvncc

Sun, 05 Apr 2020 06:42:59 GMT

Another example is RealNVP, which has the same structure to enable inversion (partition, process half, then use the result to mutate the other half in an invertible way). Sadly, I gather the computational performance Is pretty bad .. https://arxiv.org/abs/1605.08803

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

Density estimation using Real NVP — mentioned by cs702

Fri, 18 Jan 2019 17:53:05 GMT

Nice work. I can think of only two things that are missing: * Normalizing flows - e.g., https://arxiv.org/abs/1605.08803 , https://arxiv.org/abs/1807.03039 , among many others * ODEnets and continous normalizing flows - https://arxiv.org/abs/1806.07366

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

Density estimation using Real NVP — mentioned by cs702

Fri, 12 Oct 2018 01:45:45 GMT

These guys have done what looks like an impressive amount of work... but I was disappointed to see there's no mention of generative language modeling at all and only a very brief mention of key advances in image generation over the past few years. Examples of generative language modeling ignored by this paper (not even mentioned): * Unsupervised Transformer - https://blog.openai.com/language-unsupervised/ * ELMo - https://arxiv.org/abs/1802.05365 * ULMFit - https://arxiv.org/abs/1801.06146 Examples of generative image modeling ignored by this paper (some are mentioned only in passing): * Glow…

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

Density estimation using Real NVP — mentioned by kastnerkyle

Fri, 03 Jun 2016 08:43:53 GMT

Yes, although the particular technique used here (variational autoencoder, or VAE) doesn't benefit from increasing the code space due to a particular penalty (KL divergence against a fixed N(0, 1) Gaussian prior) during training. So even by making it go to 1000 digits in the code space, the model will probably still only choose to use 5 or 10 dimensions unless the KL penalty is relaxed, making it closer to a standard autoencoder. An autoencoder with a much larger code space could be an improvement, or some newer works such as Adversarially Learned Inference / Adversarial Feature Learning [0…

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