# Memorized Sparse Backpropagation

arXiv: https://arxiv.org/abs/1905.10194 · HTML: https://mlsanity.com/paper/1905.10194/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2019.

## Built on by (most cited first, 4 of 4)

- [Towards Accurate Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2303.14341/) (2023)
- [SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks](https://mlsanity.com/paper/2302.04852/) (2023)
- [Compressing the Backward Pass of Large-Scale Neural Architectures by Structured Activation Pruning](https://mlsanity.com/paper/2311.16883/) (2023)
- [ssProp: Energy-Efficient Training for Convolutional Neural Networks with Scheduled Sparse Back Propagation](https://mlsanity.com/paper/2408.12561/) (2024)

## Abstract (arXiv)

Neural network learning is usually time-consuming since backpropagation needs to compute full gradients and backpropagate them across multiple layers. Despite its success of existing works in accelerating propagation through sparseness, the relevant theoretical characteristics remain under-researched and empirical studies found that they suffer from the loss of information contained in unpropagated gradients. To tackle these problems, this paper presents a unified sparse backpropagation framework and provides a detailed analysis of its theoretical characteristics. Analysis reveals that when applied to a multilayer perceptron, our framework essentially performs gradient descent using an estimated gradient similar enough to the true gradient, resulting in convergence in probability under certain conditions. Furthermore, a simple yet effective algorithm named memorized sparse backpropagation (MSBP) is proposed to remedy the problem of information loss by storing unpropagated gradients in memory for learning in the next steps. Experimental results demonstrate that the proposed MSBP is effective to alleviate the information loss in traditional sparse backpropagation while achieving comparable acceleration.