# Blind Descent: A Prequel to Gradient Descent

arXiv: https://arxiv.org/abs/2006.11505 · HTML: https://mlsanity.com/paper/2006.11505/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2020.

## Built on by (most cited first, 2 of 2)

- [Attempted Blind Constrained Descent Experiments](https://mlsanity.com/paper/2102.09643/) (2021)
- [An experimental comparative study of backpropagation and alternatives for training binary neural networks for image classification](https://mlsanity.com/paper/2408.04460/) (2024)

## Abstract (arXiv)

We describe an alternative learning method for neural networks, which we call Blind Descent. By design, Blind Descent does not face problems like exploding or vanishing gradients. In Blind Descent, gradients are not used to guide the learning process. In this paper, we present Blind Descent as a more fundamental learning process compared to gradient descent. We also show that gradient descent can be seen as a specific case of the Blind Descent algorithm. We also train two neural network architectures, a multilayer perceptron and a convolutional neural network, using the most general Blind Descent algorithm to demonstrate a proof of concept.