# Connections Between Adaptive Control and Optimization in Machine Learning

arXiv: https://arxiv.org/abs/1904.05856 · HTML: https://mlsanity.com/paper/1904.05856/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2019.

## Built on by (most cited first, 7 of 7)

- [Online Algorithms and Policies Using Adaptive and Machine Learning Approaches](https://mlsanity.com/paper/2105.06577/) (2021)
- [Computability, Complexity, Consistency and Controllability: A Four C's Framework for cross-disciplinary Ethical Algorithm Research](https://mlsanity.com/paper/2102.04234/) (2021)
- [Function Approximation with Randomly Initialized Neural Networks for Approximate Model Reference Adaptive Control](https://mlsanity.com/paper/2303.16251/) (2023)
- [On the stability of gradient descent with second order dynamics for time-varying cost functions](https://mlsanity.com/paper/2405.13765/) (2024)
- [Robust synchronization and policy adaptation for networked heterogeneous agents](https://mlsanity.com/paper/2409.03273/) (2024)
- [1 Modular Parallel Manipulator for Long-Term Soft Robotic Data Collection](https://mlsanity.com/paper/2409.03614/) (2024)
- [Regret Analysis: a control perspective](https://mlsanity.com/paper/2501.04572/) (2025)

## Abstract (arXiv)

This 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.