# Learning by Directional Gradient Descent

International Conference on Learning Representations (ICLR)（2022）

摘要

How should state be constructed from a sequence of observations, so as to best achieve some objective? Most deep learning methods update the parameters of the state representation by gradient descent. However, no prior method for computing the gradient is fully satisfactory, for example consuming too much memory, introducing too much variance, or adding too much bias. In this work, we propose a new learning algorithm that addresses these limitations. The basic idea is to update the parameters of the representation by using the directional derivative along a candidate direction, a quantity that may be computed online with the same computational cost as the representation itself. We consider several different choices of candidate direction, including random selection and approximations to the true gradient, and investigate their performance on several synthetic tasks.

更多查看译文

关键词

credit assignment,directional derivative,recurrent networks

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要