 |
ML Newsnew | past | best | rss | submit | about |
| Connections Between Adaptive Control and Optimization in Machine Learning (arxiv.org) | |
| 3 points by gballan on Jun 1, 2019 | hide | past | pdf | discuss on HN | |
|
In plain words: Adaptive control and machine learning optimization turn out to use nearly the same update rules and ideas about stability and learning. Using that overlap, the paper solves a specific problem in higher-order learning by borrowing ideas from the other field. AbstractThis paper demonstrates many immediate connections between adaptive control and optimization methods commonly employed in machine learning. Starting from common output error formulations, similarities in update law modifications are examined. Concepts in stability, performance, and learning, common to both fields are then discussed. Building on the similarities in update laws and common concepts, new intersections and opportunities for improved algorithm analysis are provided. In particular, a specific problem related to higher order learning is solved through insights obtained from these intersections. | |
| add comment on HN |