# Speedup deep learning models on GPU by taking advantage of efficient unstructured pruning and bit-width reduction

arXiv: https://arxiv.org/abs/2112.15445 · HTML: https://mlsanity.com/paper/2112.15445/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 44 references that are in the map.
- First posted on arXiv 28 Dec 2021.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [Movement Pruning: Adaptive Sparsity by Fine-Tuning](https://mlsanity.com/paper/2005.07683/) (2020)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Variational Dropout Sparsifies Deep Neural Networks](https://mlsanity.com/paper/1701.05369/) (2017)
- [cuDNN: Efficient Primitives for Deep Learning](https://mlsanity.com/paper/1410.0759/) (2014)
- [Discrimination-aware Channel Pruning for Deep Neural Networks](https://mlsanity.com/paper/1810.11809/) (2018)
- [Fixed Point Quantization of Deep Convolutional Networks](https://mlsanity.com/paper/1511.06393/) (2015)
- [Fast Algorithms for Convolutional Neural Networks](https://mlsanity.com/paper/1509.09308/) (2015)
- [Comparative Study of CNN and RNN for Natural Language Processing](https://mlsanity.com/paper/1702.01923/) (2017)
- [Going Deeper with Contextual CNN for Hyperspectral Image Classification](https://mlsanity.com/paper/1604.03519/) (2016)
- [ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multipliers](https://mlsanity.com/paper/1812.11677/) (2018)
- [Faster CNNs with Direct Sparse Convolutions and Guided Pruning](https://mlsanity.com/paper/1608.01409/) (2016)
- [Structured Bayesian Pruning via Log-Normal Multiplicative Noise](https://mlsanity.com/paper/1705.07283/) (2017)
- [Stabilizing the Lottery Ticket Hypothesis](https://mlsanity.com/paper/1903.01611/) (2019)
- [Learning to Prune Filters in Convolutional Neural Networks](https://mlsanity.com/paper/1801.07365/) (2018)
- [Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs](https://mlsanity.com/paper/1802.10280/) (2018)
- [A novel channel pruning method for deep neural network compression](https://mlsanity.com/paper/1805.11394/) (2018)
- [Ensemble neuroevolution based approach for multivariate time series anomaly detection](https://mlsanity.com/paper/2108.03585/) (2021)
- [Ristretto: Hardware-Oriented Approximation of Convolutional Neural Networks](https://mlsanity.com/paper/1605.06402/) (2016)
- [Retrain or not retrain? -- efficient pruning methods of deep CNN networks](https://mlsanity.com/paper/2002.07051/) (2020)
- [Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural Networks](https://mlsanity.com/paper/2002.09958/) (2020)
- [Reliable Identification of Redundant Kernels for Convolutional Neural Network Compression](https://mlsanity.com/paper/1812.03608/) (2018)
- [GPU Fast Convolution via the Overlap-and-Save Method in Shared Memory](https://mlsanity.com/paper/1910.01972/) (2019)

## Built on by (most cited first, 3 of 3)

- [Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective](https://mlsanity.com/paper/2607.03784/) (2026)
- [Towards efficient deep autoencoders for multivariate time series anomaly detection](https://mlsanity.com/paper/2403.02429/) (2024)
- [Evolutionary fine tuning of quantized convolution-based deep learning models](https://mlsanity.com/paper/2605.05228/) (2026)

## Abstract (arXiv)

This work is focused on the pruning of some convolutional neural networks (CNNs) and improving theirs efficiency on graphic processing units (GPU) by using a direct sparse algorithm. The Nvidia deep neural network (cuDnn) library is the most effective implementations of deep learning (DL) algorithms for GPUs. GPUs are the most commonly used accelerators for deep learning computations. One of the most common techniques for improving the efficiency of CNN models is weight pruning and quantization. There are two main types of pruning: structural and non-structural. The first enables much easier acceleration on many type of accelerators, but with this type it is difficult to achieve a sparsity level and accuracy as high as that obtained with the second type. Non-structural pruning with retraining can generate a weight tensors up to 90% or more of sparsity in some deep CNN models. In this article the pruning algorithm is presented which makes it possible to achieve high sparsity levels without accuracy drop. In the next stage the linear and non-linear quantization is adapted for further time and footprint reduction. This paper is an extended of previously published paper concerning effective pruning techniques and present real models pruned with high sparsities and reduced precision which can achieve better performance than the CuDnn library.