ARM-gradient / ARSM
Low-variance and unbiased gradient for backpropagation through categorical random variables, with application in variational auto-encoder and reinforcement learning. ICML 2019
☆17Updated 4 years ago
Alternatives and similar repositories for ARSM:
Users that are interested in ARSM are comparing it to the libraries listed below
- Low-variance, efficient and unbiased gradient estimation for optimizing models with binary latent variables. (ICLR 2019)☆28Updated 6 years ago
- Estimating Gradients for Discrete Random Variables by Sampling without Replacement☆40Updated 5 years ago
- Pytorch Implemetation for our NAACL2019 Paper "Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling" http…☆62Updated 4 years ago
- [AAAI 2020 Oral] Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution☆37Updated 4 years ago
- Code for "Training Deep Energy-Based Models with f-Divergence Minimization" ICML 2020☆36Updated last year
- [ICLR 2020] FSPool: Learning Set Representations with Featurewise Sort Pooling☆42Updated last year
- Implementation of the paper "Direct Optimization through argmax for discrete Variational Auto-Encoder"☆14Updated 4 years ago
- Official PyTorch (Lightning) implementation of the NeurIPS 2020 paper "Efficient Marginalization of Discrete and Structured Latent Variab…☆28Updated 3 years ago
- ☆12Updated 4 years ago
- ☆20Updated 4 years ago
- Code for Reparameterizable Subset Sampling via Continuous Relaxations, IJCAI 2019.☆54Updated last year
- Toy datasets to evaluate algorithms for domain generalization and invariance learning.☆42Updated 3 years ago
- A variational inference method with accurate uncertainty estimation. It uses a new semi-implicit variational family built on neural netwo…☆53Updated 4 months ago
- ☆12Updated 5 years ago
- MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders☆23Updated 5 years ago
- Tensorflow implementation of "Meta Dropout: Learning to Perturb Latent Features for Generalization" (ICLR 2020)☆27Updated 4 years ago
- ☆14Updated 5 years ago
- ☆31Updated 4 years ago
- [NeurIPS'20] Code for the Paper Compositional Visual Generation and Inference with Energy Based Models☆44Updated last year
- Scalable Training of Inference Networks for Gaussian-Process Models, ICML 2019☆41Updated 2 years ago
- Learning To Stop While Learning To Predict☆34Updated 2 years ago
- This is a joint implementation of AdaShift optimizer, LGANs, and MaxGP.☆14Updated 4 years ago
- An implementation of DIP-VAE from the paper "Variational Inference of Disentangled Latent Concepts from Unlabelled Observations" by Kumar…☆24Updated 6 years ago
- ☆65Updated 7 months ago
- Code for "A Spectral Approach to Gradient Estimation for Implicit Distributions" (ICML'18)☆32Updated last year
- ☆49Updated 4 years ago
- Explaining a black-box using Deep Variational Information Bottleneck Approach☆46Updated 2 years ago
- GAN(TK)²: GAN Neural Tangent Kernel ToolKit☆13Updated 2 years ago
- Group-conditional DRO to alleviate spurious correlations☆15Updated 3 years ago
- Official Release of "Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling"☆49Updated 4 years ago