lancopku / meProp
meProp: Sparsified Back Propagation for Accelerated Deep Learning (ICML 2017)
☆110Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for meProp
- ☆64Updated 7 years ago
- Implements pytorch code for the Accelerated SGD algorithm.☆215Updated 6 years ago
- Sparse and structured neural attention mechanisms☆223Updated 4 years ago
- Code used to generate the results appearing in "Train longer, generalize better: closing the generalization gap in large batch training o…☆148Updated 7 years ago
- Adaptive Softmax implementation for PyTorch☆79Updated 5 years ago
- ☆78Updated 6 years ago
- Implement Decoupled Neural Interfaces using Synthetic Gradients in Pytorch☆118Updated 7 years ago
- Pytorch implementation of bytenet from "Neural Machine Translation in Linear Time" paper☆47Updated 6 years ago
- Implementation of "Learning with Random Learning Rates" in PyTorch.☆102Updated 5 years ago
- A pytorch implementation of "Self-Normalizing Neural Networks" by Klambauer et al. (still beta)☆59Updated 7 years ago
- A new kind of pooling layer for faster and sharper convergence☆76Updated 7 years ago
- Dynamic evaluation for pytorch language models, now includes hyperparameter tuning☆105Updated 6 years ago
- ☆75Updated 7 years ago
- Cleaned original source code from my NIPS publication☆154Updated 6 years ago
- SparseMAP: differentiable sparse structure inference☆110Updated 5 years ago
- Codes for "Towards Binary-Valued Gates for Robust LSTM Training".☆76Updated 6 years ago
- Weight initialization schemes for PyTorch nn.Modules☆70Updated 7 years ago
- Source code for "Efficient Training of BERT by Progressively Stacking"☆112Updated 5 years ago
- ☆93Updated 7 years ago
- Structured Attentions for Visual Question Answering☆47Updated 6 years ago
- Code for SegTree Transformer (ICLR-RLGM 2019).☆27Updated 5 years ago
- Code for "EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis" https://arxiv.org/abs/1905.05934☆112Updated 4 years ago
- Path-Level Network Transformation for Efficient Architecture Search, in ICML 2018.☆113Updated 6 years ago
- Explore OpenReview papers for ICLR (with citation counts, acceptance status, and ratings)!☆86Updated 3 years ago
- (Beta Version!) Experiment Code for Paper ``CoT: Cooperative Training for Generative Modeling of Discrete Data''☆73Updated 5 years ago
- A PyTorch implementation of Recurrent Additive Networks by Lee et al. (2017)☆29Updated 7 years ago
- Efficient Architecture Search by Network Transformation, in AAAI 2018☆170Updated 5 years ago
- Reference implementation for Structured Prediction with Deep Value Networks☆55Updated 7 years ago
- Comparing Fixed and Adaptive Computation Time for Recurrent Neural Networks☆34Updated 6 years ago