mrahtz / humble-gumbelLinks
Jupyter notebook on Gumbel-max and Gumbel-softmax tricks
☆41Updated 2 years ago
Alternatives and similar repositories for humble-gumbel
Users that are interested in humble-gumbel are comparing it to the libraries listed below
Sorting:
- ZForcing Repo☆40Updated 7 years ago
- An implementation of a Variational-Autoencoder using the Gumbel-Softmax reparametrization trick in TensorFlow (tested on r1.5 CPU and GPU…☆72Updated 7 years ago
- SparseMAP: differentiable sparse structure inference☆112Updated 6 years ago
- Pytorch Implementation of paper "Noisy Natural Gradient as Variational Inference"☆121Updated 7 years ago
- Computing various norms/measures on over-parametrized neural networks☆50Updated 6 years ago
- Code for "Systematic Generalization: What Is Required and Can It Be Learned"☆37Updated 6 years ago
- PyTorch code for meta seq2seq learning☆43Updated 5 years ago
- Implementation of REBAR in PyTorch☆17Updated 7 years ago
- Understanding Short-Horizon Bias in Stochastic Meta-Optimization☆37Updated 7 years ago
- Experiments with binary LSTM using gumbel-sigmoid☆31Updated 5 years ago
- Implementation of Conditionally Shifted Neurons by Munkhdalai et al. (https://arxiv.org/pdf/1712.09926.pdf)☆28Updated 7 years ago
- ☆152Updated 7 years ago
- Policy based Active Learning with DQN (EMNLP-2017)☆90Updated 7 years ago
- Implementation of Stochastic Beam Search using Fairseq☆105Updated 6 years ago
- learning to search in pytorch☆110Updated 5 years ago
- Multiplicative Normalizing Flow (MNF) posteriors for variational Bayesian neural networks☆65Updated 5 years ago
- ☆14Updated 6 years ago
- Contains code relating to this arxiv paper https://arxiv.org/abs/1802.03761☆37Updated 7 years ago
- Repository of code for the experiments for the ICLR submission "An Empirical Investigation of Catastrophic Forgetting in Gradient-Based N…☆69Updated 11 years ago
- Open source implementation of SeaRNN (ICLR 2018, https://openreview.net/forum?id=HkUR_y-RZ)☆48Updated 7 years ago
- Comparing Fixed and Adaptive Computation Time for Recurrent Neural Networks☆35Updated 7 years ago
- A generic Monte Carlo method based on the Gumbel-Max trick.☆32Updated 9 years ago
- ☆24Updated 4 months ago
- Pytorch Implemetation for our NAACL2019 Paper "Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling" http…☆63Updated 5 years ago
- Adaptive Softmax implementation for PyTorch☆81Updated 6 years ago
- Unsupervised Learning by Predicting Noise☆90Updated 3 years ago
- a python implementation of various versions of the information bottleneck, including automated parameter searching☆128Updated 5 years ago
- Code for the paper Implicit Weight Uncertainty in Neural Networks☆65Updated 5 years ago
- Code for the publication Learning to Reason with Third-Order Tensor Products.☆41Updated 6 years ago
- Estimating Gradients for Discrete Random Variables by Sampling without Replacement☆40Updated 5 years ago