IST-DASLab / M-FACLinks
Efficient reference implementations of the static & dynamic M-FAC algorithms (for pruning and optimization)
☆17Updated 3 years ago
Alternatives and similar repositories for M-FAC
Users that are interested in M-FAC are comparing it to the libraries listed below
Sorting:
- Practical low-rank gradient compression for distributed optimization: https://arxiv.org/abs/1905.13727☆149Updated last year
- ☆46Updated 5 years ago
- Code accompanying the NeurIPS 2020 paper: WoodFisher (Singh & Alistarh, 2020)☆53Updated 4 years ago
- ☆220Updated 2 years ago
- Accuracy 77%. Large batch deep learning optimizer LARS for ImageNet with PyTorch and ResNet, using Horovod for distribution. Optional acc…☆38Updated 4 years ago
- Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH☆105Updated 5 years ago
- Block Sparse movement pruning☆81Updated 4 years ago
- Implementation of (overlap) local SGD in Pytorch☆34Updated 5 years ago
- ☆43Updated 3 years ago
- ☆41Updated 4 years ago
- GRACE - GRAdient ComprEssion for distributed deep learning☆139Updated last year
- Parameter Efficient Transfer Learning with Diff Pruning☆74Updated 4 years ago
- Pytorch implementation of the paper "SNIP: Single-shot Network Pruning based on Connection Sensitivity" by Lee et al.☆111Updated 6 years ago
- Pytorch library for factorized L0-based pruning.☆45Updated 2 years ago
- ☆227Updated last year
- Sketched SGD☆28Updated 5 years ago
- Code for "Training Neural Networks with Fixed Sparse Masks" (NeurIPS 2021).☆59Updated 3 years ago
- [ICLR 2023] Eva: Practical Second-order Optimization with Kronecker-vectorized Approximation☆12Updated 2 years ago
- ☆69Updated 5 years ago
- Implementation of Continuous Sparsification, a method for pruning and ticket search in deep networks☆33Updated 3 years ago
- Stochastic Gradient Push for Distributed Deep Learning☆169Updated 2 years ago
- A PyTorch implementation of the paper "Decoupled Parallel Backpropagation with Convergence Guarantee"☆29Updated 7 years ago
- Soft Threshold Weight Reparameterization for Learnable Sparsity☆90Updated 2 years ago
- SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY☆116Updated 6 years ago
- This pytorch package implements PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance (ICML 2022).☆46Updated 3 years ago
- PyTorch implementation of LAMB for ImageNet/ResNet-50 training☆13Updated 4 years ago
- Block-sparse primitives for PyTorch☆160Updated 4 years ago
- ☆195Updated 4 years ago
- ☆143Updated 2 years ago
- [ICML 2021] "Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training" by Shiwei Liu, Lu Yin, De…☆45Updated 2 years ago