Summary of Random Features Approximation For Control-affine Systems, by Kimia Kazemian et al.
Random Features Approximation for Control-Affine Systems
by Kimia Kazemian, Yahya Sattar, Sarah Dean
First submitted to arxiv on: 10 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Systems and Control (eess.SY); Optimization and Control (math.OC); Machine Learning (stat.ML)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed research introduces two novel classes of nonlinear feature representations that capture control-affine structure while allowing for arbitrary complexity in state dependence. The methods utilize random features approximations, inheriting the expressiveness of kernel methods at a lower computational cost. By formalizing the representational capabilities of these methods, it is shown that they are related to the Affine Dot Product (ADP) kernel and a novel Affine Dense (AD) kernel. A case study demonstrates the utility of these methods in data-driven optimization-based control using control certificate functions (CCF). Simulation experiments on a double pendulum empirically demonstrate the advantages of the proposed methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The research proposes new ways to understand complex systems that can be controlled. The methods use “random features” which are like shortcuts to find patterns in the data. This helps make the system easier to control and predict. It’s like having a map to navigate a complicated landscape. The researchers show how their methods work by comparing them to other techniques, and they test it on a double pendulum to see if it really works. |
Keywords
» Artificial intelligence » Dot product » Optimization
