Open-source alternatives to Spdy

ICLR 2023 Pruning Deep Neural Networks from a Sparsity Perspective

This is the official repo for ICLR 2023 Paper "Bit-Pruning: A Sparse Multiplication-Less Dot-Product" Yusuke Sekikawa and Shingo Yashima

This repository contains the codes for the following NeurIPS-2019 paper

Codebase for the paper "A Gradient Flow Framework for Analyzing Network Pruning" \ICLR, 2021\.

This repository contains source code for the ICLR 2022 paper How many degrees of freedom do we need to train deep networks: a loss landscape perspective by Brett W. Larsen, Sanislav Fort, Nic Becker, and Surya Ganguli (arXiv version).

NeurIPS 2022 "Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing" by Yonggan Fu, Yang Zhang, Kaizhi Qian, Zhifan Ye, Zhongzhi Yu, Cheng-I Lai, Yingyan Lin

This codebase was developed by Jonathan Frankle and David Bieber at Google during the summer of 2018.

This framework implements key experiments on the sparse double descent phenomenon, as demonstrated in the following paper:

Repository with code to reproduce the results and checkpoints for compressed networks in our paper on novel pruning techniques with robust training. This repository supports all four robust training objectives: iterative adversarial training, randomized smoothing, MixTrain, and CROWN-IBP.

This code allows replicating the image experiments of AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks. This code allows for training compressed and decompressed WideResNet models for CIFAR-100, ResNet50 and MobileNet models for Imagenet (also for 2:4 sparsity), and…

Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".

Official implementation of the NeurIPS 2022 accepted paper "Robust Binary Models by Pruning Randomly-initialized Networks"

A PyTorch implementation of this paper.

This is the official implementation of the paper: "Layerwise Sparsity for Magnitude-based Pruning", ICLR 2021.

This repository contains the code for reproducing the results in the following paper:

Prune DNN using Alternating Direction Method of Multipliers (ADMM)

This repository is meant to provide a generic code base for neural network pruning, especially for pruning at initialization (PaI). (In preparation now, you may check our survey paper and paper collection below.)

This repository contains code for the paper SNIP: Single-shot Network Pruning based on Connection Sensitivity (ICLR 2019).

This is an PyTorch implement of the paper ``Prune Your Model Before Distill It''.

Francesco Croce\ (University of Tübingen), Maksym Andriushchenko\ (EPFL), Vikash Sehwag\ (Princeton University), Nicolas Flammarion (EPFL), Mung Chiang (Purdue University), Prateek Mittal (Princeton University), Matthias Hein (University of Tübingen)

RobustNets benchmark models and code

March 15, 2019: for our most updated work on model compression and acceleration, please reference:

Hattie Zhou, Janice Lan, Rosanne Liu, Jason Yosinski

Mukund Varma T 1 , Xuxi Chen 2 , Zhenyu Zhang 2 , Tianlong Chen 2 , Subhashini Venugopalan 3 , Zhangyang Wang 2

This repo includes codes for the official implementation of the paper The Elastic Lottery Ticket Hypothesis, by Xiaohan Chen, Yu Cheng, Shuohang Wang, Zhe Gan, Jingjing Liu, Zhangyang Wang.

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration Shiwei Liu,Tianlong Chen,Xiaohan Chen,Zahra Atashgahi,Lu Yin,Huanyu Kou,Li Shen,Mykola Pechenizkiy,Zhangyang Wang, Decebal Constantin Mocanu https://arxiv.org/abs/2106.10404