facebookresearch / qhoptim
Implementations of quasi-hyperbolic optimization algorithms.
☆100Updated 4 years ago
Related projects: ⓘ
- Pytorch implementation of Variational Dropout Sparsifies Deep Neural Networks☆83Updated 2 years ago
- Code for MSID, a Multi-Scale Intrinsic Distance for comparing generative models, studying neural networks, and more!☆49Updated 5 years ago
- Loss Patterns of Neural Networks☆82Updated 2 years ago
- Implementation of "Variational Dropout and the Local Reparameterization Trick" paper with Pytorch☆50Updated 6 years ago
- [NeurIPS'19] [PyTorch] Adaptive Regularization in NN☆67Updated 4 years ago
- ☆46Updated 3 years ago
- A supplementary code for Beyond Vector Spaces: Compact Data Representation as Differentiable Weighted Graphs.☆47Updated 4 years ago
- ☆61Updated last year
- MTAdam: Automatic Balancing of Multiple Training Loss Terms☆34Updated 3 years ago
- [ICLR 2019] Learning Representations of Sets through Optimized Permutations☆36Updated 5 years ago
- Implementation of "Learning with Random Learning Rates" in PyTorch.☆102Updated 4 years ago
- An implementation of shampoo☆73Updated 6 years ago
- Code for Self-Tuning Networks (ICLR 2019) https://arxiv.org/abs/1903.03088☆53Updated 5 years ago
- custom cuda kernel for {2, 3}d relative attention with pytorch wrapper☆43Updated 4 years ago
- 🧀 Pytorch code for the Fromage optimiser.☆120Updated 2 months ago
- The Deep Weight Prior, ICLR 2019☆44Updated 3 years ago
- Odds and Ends and Things I've implemented.☆78Updated 5 years ago
- Code to accompany the paper Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning☆33Updated 4 years ago
- Notes from NeurIPS 2019☆29Updated 4 years ago
- On disentangling the menagerie of disentanglement papers☆27Updated 4 years ago
- Computing various norms/measures on over-parametrized neural networks☆48Updated 5 years ago
- Recurrent Back Propagation, Back Propagation Through Optimization, ICML 2018☆39Updated 5 years ago
- ☆34Updated 5 years ago
- PyTorch implementation of the NIPS'17 paper Training Deep Networks without Learning Rates Through Coin Betting.☆38Updated 6 years ago
- [AAAI 2020 Oral] Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution☆36Updated 3 years ago
- Code for ICLR2018 paper: Improving GAN Training via Binarized Representation Entropy (BRE) Regularization - Y. Cao · W Ding · Y.C. Lui · …☆20Updated 6 years ago
- This repository provides the code for replicating the experiments in the paper "Building One-Shot Semi-supervised (BOSS) Learning up to F…☆36Updated 4 years ago
- Code for ICML 2018 paper on "Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam" by Khan, Nielsen, Tangkaratt, Lin, …☆109Updated 5 years ago
- Simple implementation of the LSUV initialization in PyTorch☆58Updated 8 months ago
- "Learning Rate Dropout" in PyTorch☆34Updated 4 years ago