collections of examples of gumbel softmax tricks in optimization & deep learning
-
Updated
Apr 16, 2024 - Python
collections of examples of gumbel softmax tricks in optimization & deep learning
deep models for small image classification datasets
Python library for the differentiable hypergeometric distribution
[Pytorch] Minimal implementation of a Variational Autoencoder (VAE) with Categorical Latent variables.
Jittor reimplementation of DiverseSampling (MM22)
The implementation of Gumbel softmax reparametrization trick for discrete VAE
Official project of DiverseSampling (ACMMM2022 Paper)
Black-box spike and slab variational inference, example with linear models
Implementation of the Gumbel-Sigmoid distribution in PyTorch.
Code for TACL 2022 paper on Data-to-text Generation with Variational Sequential Planning
De novo Drug Design via Binary Representations of SMILES for avoiding the Posterior Collapse Problem (BIBM 2021)
Keras, Tensorflow eager execution implementation of Categorical Variational Autoencoder
Code acompanying the paper Developmentally motivated emergence of compositional communication via template transfer
GAN-Based Text Generation
TensorFlow-based implementation of "Attend, Infer, Repeat" paper (Eslami et al., 2016, arXiv:1603.08575).
A Unified Deep Model of Learning from both Data and Queries for Cardinality Estimation
Implementation of NeurIPS 19 paper: Paraphrase Generation with Latent Bag of Words
An implementation of a Variational-Autoencoder using the Gumbel-Softmax reparametrization trick in TensorFlow (tested on r1.5 CPU and GPU) in ICLR 2017.
Source code for the NAACL 2019 paper "SEQ^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression"
Keras implementation of a Variational Auto Encoder with a Concrete Latent Distribution
Add a description, image, and links to the gumbel-softmax topic page so that developers can more easily learn about it.
To associate your repository with the gumbel-softmax topic, visit your repo's landing page and select "manage topics."