# Stochastic Markov Gradient Descent and Training Low-Bit Neural Networks

arXiv: https://arxiv.org/abs/2008.11117 · HTML: https://mlsanity.com/paper/2008.11117/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Aug 2020.

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

- [Approximation of functions with one-bit neural networks](https://mlsanity.com/paper/2112.09181/) (2021)
- [Beyond Discreteness: Sample Complexity Analysis of Straight-Through Estimator for 1-bit Quantization](https://mlsanity.com/paper/2505.18113/) (2025)
- [Approximability and Generalisation](https://mlsanity.com/paper/2203.07989/) (2022)

## Abstract (arXiv)

The massive size of modern neural networks has motivated substantial recent interest in neural network quantization. We introduce Stochastic Markov Gradient Descent (SMGD), a discrete optimization method applicable to training quantized neural networks. The SMGD algorithm is designed for settings where memory is highly constrained during training. We provide theoretical guarantees of algorithm performance as well as encouraging numerical results.