A Gradient Descent Trust Region Optimizer
Please use this identifier to cite or link to this publication: http://hdl.handle.net/10380/3310
New: Prefer using the following doi: https://doi.org/10.54294/f5gzka
This document describes a new simple gradient descent optimizer which is a potential replacement or supplement for RegularStepGradientDescentOptimizer. The optimizer requires only the gradient of the parameters and uses a simple linear model internally. However, it follows the theoretical basis of a trust-region algorithm and is able to achieve greater efficiency on certain image registration cases.