Blind Descent: A Prequel to Gradient Descent
This addresses a fundamental issue in deep learning for researchers and practitioners, but appears incremental as it builds on existing optimization paradigms.
The paper tackles the problem of exploding or vanishing gradients in neural network training by introducing Blind Descent, an alternative learning method that does not use gradients, and demonstrates its feasibility by training a multilayer perceptron and a convolutional neural network as a proof of concept.
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.