kudkudak / dnn_sharpest_directionsLinks
Code for "On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length", ICLR 2019
☆11Updated 2 years ago
Alternatives and similar repositories for dnn_sharpest_directions
Users that are interested in dnn_sharpest_directions are comparing it to the libraries listed below
Sorting:
- SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning☆23Updated 6 years ago
- [JMLR] TRADES + random smoothing for certifiable robustness☆14Updated 4 years ago
- Lua implementation of Entropy-SGD☆82Updated 7 years ago
- This repo contains the code used for NeurIPS 2019 paper "Asymmetric Valleys: Beyond Sharp and Flat Local Minima".☆14Updated 5 years ago
- Implementation of the Deep Frank-Wolfe Algorithm -- Pytorch☆62Updated 4 years ago
- Net2Net implementation on PyTorch for any possible vision layers.☆38Updated 7 years ago
- ☆33Updated 6 years ago
- Code base for SRSGD.☆28Updated 5 years ago
- Partially Adaptive Momentum Estimation method in the paper "Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep …☆39Updated 2 years ago
- Delta Orthogonal Initialization for PyTorch☆18Updated 6 years ago
- ☆13Updated 7 years ago
- Python implementation of the infomration bottleneck method (tishby et al, 1999)☆36Updated 7 years ago
- [ICLR 2019] ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees☆32Updated 5 years ago
- This project is the Torch implementation of our accepted AAAI 2018 paper : orthogonal weight normalization method for solving orthogonali…☆57Updated 5 years ago
- ☆34Updated 6 years ago
- ICML2019 Accepted Paper. Overcoming Multi-Model Forgetting☆13Updated 6 years ago
- A PyTorch implementation of the paper "Decoupled Parallel Backpropagation with Convergence Guarantee"☆29Updated 6 years ago
- Computing various norms/measures on over-parametrized neural networks☆49Updated 6 years ago
- An Implementation of "Small steps and giant leaps: Minimal Newton solvers for Deep Learning" In pytorch☆21Updated 6 years ago
- ☆46Updated 7 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 5 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
- Successfully training approximations to full-rank matrices for efficiency in deep learning.☆17Updated 4 years ago
- Codes for the paper "Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex"☆20Updated 4 years ago
- ☆23Updated 6 years ago
- Low-variance, efficient and unbiased gradient estimation for optimizing models with binary latent variables. (ICLR 2019)☆28Updated 6 years ago
- Understanding Short-Horizon Bias in Stochastic Meta-Optimization☆37Updated 7 years ago
- Learning To Stop While Learning To Predict☆34Updated 2 years ago
- Structured Bayesian Pruning, NIPS 2017☆74Updated 4 years ago
- Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)☆35Updated 4 years ago