Abstract
The machine learning formulation of online learning is incomplete from a systems theoretic perspective. Typically, machine learning research emphasizes domains and tasks, and a problem solving worldview. It focuses on algorithm parameters, features, and samples, and neglects the perspective offered by considering system structure and system behavior or dynamics. Online learning is an active field of research and has been widely explored in terms of statistical theory and computational algorithms, however, in general, the literature still lacks formal system theoretical frameworks for modeling online learning systems and resolving systems-related concept drift issues. Furthermore, while the machine learning formulation serves to classify methods and literature, the systems theoretic formulation presented herein serves to provide a framework for the top-down design of online learning systems, including a novel definition of online learning and the identification of key design parameters. The framework is formulated in terms of input-output systems and is further divided into system structure and system behavior. Concept drift is a critical challenge faced in online learning, and this work formally approaches it as part of the system behavior characteristics. Healthcare provider fraud detection using machine learning is used as a case study throughout the paper to ground the discussion in a real-world online learning challenge.
Introduction
In the fast-paced world of machine learning, Online Learning (OL) is the go-to paradigm for dealing with data that arrives in a never-ending stream. However, most research in this area is "algorithm-centric," focusing on statistical bounds and parameter tuning. A recent paper by Anli du Preez, Peter Beling, and Tyler Cody argues that this view is incomplete. They propose a shift toward a "systems-centric" perspective, applying formal systems theory to provide a more robust foundation for designing and understanding online learning systems.
Traditional machine learning often assumes a "stationary" world where the data you train on looks exactly like the data you’ll see in production. Online learning was designed to break this assumption, allowing models to update incrementally. However, the current literature lacks a formal, top-down framework for modeling these systems. Most practitioners treat Concept Drift (CD)—when the underlying data distribution changes—as a statistical nuisance to be detected. This paper argues that CD is actually a fundamental characteristic of a system's behavior. Without a formal way to describe how a system’s structure (like its features) and behavior (its logic) evolve over time, we are essentially "building the plane while flying it" without a blueprint.
Methodology: Abstract Learning Systems Theory
The authors utilize Abstract Learning Systems Theory (ALST), a mathematical framework that views a system as a relation between input and output sets. By moving beyond purely statistical models, the authors provide a top-down design methodology that treats online learning as a dynamic interaction between system structure (sample spaces) and system behavior (probability distributions).
Formal Definitions of OL Systems
An OL system is defined as one that seeks to sequentially update its "knowledge" ($K_t$) to improve prediction performance at the next time step. This sequential process is visualized in Figure 3, where the system $S_t$ processes data $D_t$ and input $X_t$ to produce output $Y_t$ while updating its internal state $K_t$ for the next iteration.
The framework distinguishes between "trivial" systems (where the environment is stationary) and "non-trivial" systems, where either the input-output structure or the underlying probability distributions change over time.
Structural Flexibility and Homomorphisms
One of the most interesting additions is the use of homomorphisms. Most ML models break if you add a new feature or change the label set. By using homomorphic mappings, the authors provide a mathematical path for models to evolve their structure without needing to be retrained from scratch. This allows the system to map a model from one time step to another even if the "shape" of the data changes, such as moving from a binary classification task to a multi-class task as new types of fraud are discovered.
System Structure vs. Behavior
The framework separates the System Structure (the dimensions and types of inputs/outputs) from System Behavior (the joint probability distributions $P(X, Y)$). This decomposition allows for a more principled approach to "system health" monitoring. Rather than seeing Concept Drift as an external "error," the authors frame it as a change in the system's behavior ($P(Y|X)$ or $P(X)$). This perspective helps address the Stability-Plasticity Dilemma—how to learn new things without forgetting the old—as a formal trade-off within the system's knowledge-updating process.
Case Study: Healthcare Provider Fraud Detection
This theoretical paper uses Healthcare Provider Fraud Detection as a continuous, qualitative case study to ground its abstract mathematical definitions. In this domain, fraudsters constantly change their billing behavior (concept drift) and new types of claims data may appear (structural change). The ALST framework provides a way to formalize these changes, helping designers decide how complex the behavior they are trying to learn is and how variable that behavior is over time before choosing an algorithm.
Conclusion
The paper successfully bridges the gap between the "General Systems Theory" of the 1970s/80s and modern "Online Machine Learning." By identifying key design parameters like mapping functions between time steps, the authors provide a unified language for long-term system stability. Future work will focus on formalizing specific systems-theoretic measures for drift localization and translating these abstract homomorphisms into concrete code for popular architectures like neural networks or gradient-boosted trees.
Summary updated