Kipok / understanding-momentum
Code for the paper "Understanding the Role of Momentum in Stochastic Gradient Methods"
☆15Updated 5 years ago
Alternatives and similar repositories for understanding-momentum:
Users that are interested in understanding-momentum are comparing it to the libraries listed below
- Partially Adaptive Momentum Estimation method in the paper "Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep …☆39Updated last year
- ☆13Updated 7 years ago
- SSL using PyTorch☆49Updated 5 years ago
- "Learning Rate Dropout" in PyTorch☆34Updated 5 years ago
- Colab notebooks for d2l-book☆11Updated 5 years ago
- A simple middleware to improving GPU utilization then speedup online inference.☆19Updated 4 years ago
- ☆23Updated 4 years ago
- (Batched) advanced indexing for PyTorch.☆53Updated 2 months ago
- Exploiting Uncertainty of Loss Landscape for Stochastic Optimization☆15Updated 5 years ago
- Implementation for <Neural Similarity Learning> in NeurIPS'19.☆33Updated 4 years ago
- Easy Multiprocessing for Python☆43Updated 4 years ago
- Code for BlockSwap (ICLR 2020).☆33Updated 3 years ago
- Filter Response Normalization tested on better ImageNet baselines.☆35Updated 4 years ago
- Successfully training approximations to full-rank matrices for efficiency in deep learning.☆16Updated 4 years ago
- Implementation of the LOSSGRAD optimization algorithm☆15Updated 5 years ago
- Reversible Recurrent Neural Network Pytorch Implementation☆21Updated 7 years ago
- Tensors and Dynamic neural networks in Python with strong GPU acceleration☆17Updated last year
- Repository for the code of the paper "Neural Networks Regularization Through Class-wise Invariant Representation Learning".☆12Updated 7 years ago
- Implementation of Spectral Leakage and Rethinking the Kernel Size in CNNs in Pytorch☆14Updated 4 years ago
- Implementation for NATv2.☆23Updated 4 years ago
- ☆23Updated 6 years ago
- ☆25Updated 3 years ago
- Various implementations and experimentation for deep neural network model compression☆24Updated 6 years ago
- A disciplined approach to neural network parameters - Reviewing the approach for setting Hyper parameters by Leslie Smith☆11Updated 6 years ago
- Yet Another Neural Network Library 🤔☆26Updated 2 months ago
- Implementation for <Regularizing Neural Networks via Minimizing Hyperspherical Energy> in CVPR'20.☆23Updated 4 years ago
- Codes for DATA: Differentiable ArchiTecture Approximation.☆11Updated 3 years ago
- Code for our paper: "Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layers".☆21Updated 3 years ago
- Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks☆18Updated 5 years ago
- ICML2019 Accepted Paper. Overcoming Multi-Model Forgetting☆13Updated 5 years ago