yashkant / padam-tensorflow
Reproducing the paper "PADAM: Closing The Generalization Gap of Adaptive Gradient Methods In Training Deep Neural Networks" for the ICLR 2019 Reproducibility Challenge
☆51Updated 5 years ago
Related projects: ⓘ
- Mathematical consequences of orthogonal weights initialization and regularization in deep learning. Experiments with gain-adjusted orthog…☆17Updated 4 years ago
- A PyTorch implement of Dilated RNN☆12Updated 6 years ago
- Code for our paper: "Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layers".☆21Updated 2 years ago
- A pytorch implementation for the LSTM experiments in the paper: Why Gradient Clipping Accelerates Training: A Theoretical Justification f…☆44Updated 4 years ago
- Reproducible code for Augmentation paper☆18Updated 5 years ago
- Deep neural architecture research framework☆12Updated last year
- This repository has moved to: https://github.com/tkipf/c-swm☆27Updated 4 years ago
- The implementation of paper ''Efficient Attention Network: Accelerate Attention by Searching Where to Plug''.☆20Updated last year
- Official code for NeurIPS paper "Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach".☆16Updated 2 years ago
- Code base for SRSGD.☆28Updated 4 years ago
- Anonymous Repository for ICML LRG Workshop: On Explainability Techniques for Graph Convolutional Networks☆23Updated 5 years ago
- Official PyTorch implementation of the paper : ProbAct: A Probabilistic Activation Function for Deep Neural Networks.☆13Updated 5 years ago
- ☆10Updated this week
- Repository for the code of the paper "Neural Networks Regularization Through Class-wise Invariant Representation Learning".☆12Updated 6 years ago
- Interpolation between Residual and Non-Residual Networks, ICML 2020. https://arxiv.org/abs/2006.05749☆26Updated 4 years ago
- Implementation of Kronecker Attention in Pytorch☆17Updated 4 years ago
- Delta Orthogonal Initialization for PyTorch☆18Updated 6 years ago
- ☆61Updated last year
- Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks☆13Updated 4 years ago
- Partially Adaptive Momentum Estimation method in the paper "Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep …☆39Updated last year
- Towards Visual Explanations for Convolutional Neural Networks via Input Resampling☆14Updated 7 years ago
- Reversible Recurrent Neural Network Pytorch Implementation☆21Updated 6 years ago
- Applied Sparse regularization (L1), Weight decay regularization (L2), ElasticNet, GroupLasso and GroupSparseLasso to Neuronal Network.☆38Updated 2 years ago
- Exploiting Uncertainty of Loss Landscape for Stochastic Optimization☆15Updated 5 years ago
- Computing the eigenvalues of Neural Tangent Kernel and Conjugate Kernel (aka NNGP kernel) over the boolean cube☆47Updated 5 years ago
- [NeurIPS'19] [PyTorch] Adaptive Regularization in NN☆67Updated 4 years ago
- SparseMax activation function implementation (ICML 2016) (PyTorch)☆26Updated 6 years ago
- ☆24Updated 4 months ago
- ☆24Updated 4 years ago
- A pytorch implementation of Information Bottleneck GAN☆28Updated 5 years ago