rahulkidambi / AccSGDLinks
Implements pytorch code for the Accelerated SGD algorithm.
☆215Updated 7 years ago
Alternatives and similar repositories for AccSGD
Users that are interested in AccSGD are comparing it to the libraries listed below
Sorting:
- Code used to generate the results appearing in "Train longer, generalize better: closing the generalization gap in large batch training o…☆149Updated 8 years ago
- Code to reproduce some of the figures in the paper "On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima"☆144Updated 8 years ago
- Implementation of "Learning with Random Learning Rates" in PyTorch.☆102Updated 5 years ago
- Code for "EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis" https://arxiv.org/abs/1905.05934☆113Updated 5 years ago
- ☆219Updated 7 years ago
- ☆252Updated 8 years ago
- An implementation of shampoo☆75Updated 7 years ago
- Example code for the paper "Understanding deep learning requires rethinking generalization"☆178Updated 5 years ago
- Snapshot Ensembles in Torch (Snapshot Ensembles: Train 1, Get M for Free)☆189Updated 8 years ago
- A tutorial on "Bayesian Compression for Deep Learning" published at NIPS (2017).☆206Updated 6 years ago
- a lightweight and simple logger for Machine Learning☆127Updated 4 years ago
- This repository is no longer maintained. Check☆81Updated 5 years ago
- Second-order optimiser for deep networks☆76Updated 6 years ago
- Efficient Architecture Search by Network Transformation, in AAAI 2018☆169Updated 6 years ago
- meProp: Sparsified Back Propagation for Accelerated Deep Learning (ICML 2017)☆110Updated 3 years ago
- A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.☆83Updated 6 years ago
- Sparse Variational Dropout, ICML 2017☆313Updated 5 years ago
- ☆133Updated 7 years ago
- repo that holds code for improving on dropout using Stochastic Delta Rule☆142Updated 6 years ago
- Structured Bayesian Pruning, NIPS 2017☆74Updated 5 years ago
- Files to create the figures in the paper "Super-Convergence: Very Fast Training of Residual Networks Using Large Learning Rates"☆191Updated 7 years ago
- Implementation of soft parameter sharing for neural networks☆70Updated 4 years ago
- Decoupled Weight Decay Regularization (ICLR 2019)☆277Updated 6 years ago
- Pytorch Implementation of recent visual attribution methods for model interpretability☆146Updated 5 years ago
- ☆79Updated 7 years ago
- Examples of C extensions for PyTorch☆256Updated 2 years ago
- A plug-in replacement for DataLoader to load Imagenet disk-sequentially in PyTorch.☆239Updated 3 years ago
- A tutorial on 'Soft weight-sharing for Neural Network compression' published at ICLR2017☆145Updated 8 years ago
- visualization of CNN in PyTorch☆155Updated last year
- ☆46Updated 7 years ago