-
For many bayesian scientists [and for one of my recent application domains] there's recently been a lot of hype around [this article](https://arxiv.org/abs/1611.01144) about how to learn categorical v…
-
Hi author, thanks for your work!
I want to ask you about the idea of the article, that is, why you should use Gumbel-softmax - if I understand correctly, the input in this article is not sampling.E…
ithok updated
2 years ago
-
Thanks for the code! I'm trying to learn Julia and Flux.jl but I'm having trouble finding an example of a VAE with gumbel-softmax trick. Chances are that you have already done this. Could you provide …
-
- https://arxiv.org/abs/1611.01144
- 2016
カテゴリー変数は、世界の離散的な構造を表現するための自然な選択です。
しかし、確率的ニューラルネットワークでは、サンプルをバックプロパゲートすることができないため、カテゴリー型の潜在変数を使用することはほとんどない。
本研究では、カテゴリー分布からの非微分サンプルを、新しいGumbel-Softmax分…
e4exp updated
3 years ago
-
-
# Categorical Reparameterization with Gumbel-Softmax - Reading Collections
[https://owen-liuyuxuan.github.io/papers_reading_sharing.github.io/Building_Blocks/GumbelSoftmax/](https://owen-liuyuxuan.…
-
## 一言でいうと
離散値の予測(=クラス分類など)を行う際の出力について。クラスの特定に使うargmaxなどは微分可能でないためうまく誤差伝搬できない。なので、連続/離散分布の特性を調整する変数を導入した方法を提案。その名はガンベル・ソフトMAX
### 論文リンク
http://blog.evjang.com/2016/11/tutorial-categorical-vari…
-
I played a little bit with the dev branch of redesign by GSOC author. It is a bit slower than AlphaGPU I think (pure performance wise) but with a few adjustement to Gumbel it works impressively well: …
-
Hi, @HEmile , I test the example in examples/vae/discrete_vae.py, but find the gumbel softmax performs much better than rebar, relax and reinforce (testing loss after 10 epochs: 98 for gumbel, 165 for…
-
Is it possible to use Gumbel softmax trick with a beam search decoder in the existing implementation of Texar. I want to differentiate through the generated beam search samples into the generator netw…