Data-conforming data-driven control: avoiding premature generalizations beyond data

TL;DR

This paper introduces a method to prevent premature generalization in data-driven control by enforcing data consistency and controlling distributional shifts, thereby improving safety and reliability.

Contribution

It proposes affine regularization and LMI constraints to ensure data-driven control systems do not overgeneralize beyond observed data, formulated as convex semi-definite programs.

Findings

Enhanced safety in data-driven control demonstrated through numerical example

Convex semi-definite programs efficiently solve the proposed regularization approach

Mitigates issues of distributional shift and premature generalization

Abstract

Data-driven and adaptive control approaches face the problem of introducing sudden distributional shifts beyond the distribution of data encountered during learning. Therefore, they are prone to invalidating the very assumptions used in their own construction. This is due to the linearity of the underlying system, inherently assumed and formulated in most data-driven control approaches, which may falsely generalize the behavior of the system beyond the behavior experienced in the data. This paper seeks to mitigate these problems by enforcing consistency of the newly designed closed-loop systems with data and slowing down any distributional shifts in the joint state-input space. This is achieved through incorporating affine regularization terms and linear matrix inequality constraints to data-driven approaches, resulting in convex semi-definite programs that can be efficiently solved by standard software packages. We discuss the optimality conditions of these programs and then conclude the paper with a numerical example that further highlights the problem of premature generalization beyond data and shows the effectiveness of our proposed approaches in enhancing the safety of data-driven control methods.