wenwei202 / smoothout
SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning
☆23Updated 5 years ago
Related projects: ⓘ
- Code for "On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length", ICLR 2019☆11Updated last year
- ☆13Updated 6 years ago
- Computing various norms/measures on over-parametrized neural networks☆48Updated 5 years ago
- [JMLR] TRADES + random smoothing for certifiable robustness☆14Updated 4 years ago
- This repo contains the code used for NeurIPS 2019 paper "Asymmetric Valleys: Beyond Sharp and Flat Local Minima".☆14Updated 4 years ago
- ☆44Updated 6 years ago
- Lua implementation of Entropy-SGD☆79Updated 6 years ago
- Official PyTorch code release for Implicit Gradient Transport, NeurIPS'19☆21Updated 5 years ago
- Implementation of the Deep Frank-Wolfe Algorithm -- Pytorch☆61Updated 3 years ago
- Net2Net implementation on PyTorch for any possible vision layers.☆38Updated 6 years ago
- Implementation of the paper "Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory", Ron Amit and Ron Meir, ICML 2018☆22Updated 4 years ago
- SGD and Ordered SGD codes for deep learning, SVM, and logistic regression☆34Updated 4 years ago
- Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent☆13Updated 4 years ago
- ☆29Updated 4 years ago
- Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)☆33Updated 4 years ago
- ☆34Updated 5 years ago
- Code for Stochastic Hyperparameter Optimization through Hypernetworks☆23Updated 6 years ago
- Implementation of Information Dropout☆39Updated 7 years ago
- Compressing Neural Networks using the Variational Information Bottleneck☆63Updated 2 years ago
- ICLR2020 Downloader & Search Tool☆18Updated 4 years ago
- Low-variance, efficient and unbiased gradient estimation for optimizing models with binary latent variables. (ICLR 2019)☆28Updated 5 years ago
- ☆72Updated 5 years ago
- ☆26Updated 5 years ago
- This project is the Torch implementation of our accepted AAAI 2018 paper : orthogonal weight normalization method for solving orthogonali…☆56Updated 4 years ago
- Low-variance and unbiased gradient for backpropagation through categorical random variables, with application in variational auto-encoder…☆17Updated 4 years ago
- Code for Self-Tuning Networks (ICLR 2019) https://arxiv.org/abs/1903.03088☆53Updated 5 years ago
- Recurrent Back Propagation, Back Propagation Through Optimization, ICML 2018☆39Updated 5 years ago
- Codes for the paper "Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex"☆20Updated 4 years ago
- [ICLR 2019] ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees☆31Updated 4 years ago
- Provable Robustness of ReLU networks via Maximization of Linear Regions [AISTATS 2019]☆31Updated 4 years ago