Koopman Operator Identification of Model Parameter Trajectories for Temporal Domain Generalization (KOMET)

📅 2026-03-27
📈 Citations: 0
Influential: 0
📄 PDF

career value

184K/year
🤖 AI Summary
This work addresses the performance degradation of machine learning models in non-stationary environments caused by temporal domain drift by proposing a model-agnostic, zero-retraining adaptive framework. The approach models the sequence of model parameters as a trajectory of a nonlinear dynamical system and identifies its linear Koopman operator using extended dynamic mode decomposition (EDMD) with a Fourier-augmented observation dictionary. Leveraging a warm-start training protocol, the framework autonomously predicts future parameter trajectories without requiring future labels, enabling efficient adaptation. Moreover, it uncovers an interpretable dynamical structure underlying decision boundary drift. Evaluated across six datasets, the method achieves average accuracies between 0.981 and 1.000 over 100 future timesteps, demonstrating robustness and effectiveness under diverse distribution shift scenarios.

Technology Category

Application Category

📝 Abstract
Parametric models deployed in non-stationary environments degrade as the underlying data distribution evolves over time (a phenomenon known as temporal domain drift). In the current work, we present KOMET (Koopman Operator identification of Model parameter Evolution under Temporal drift), a model-agnostic, data-driven framework that treats the sequence of trained parameter vectors as the trajectory of a nonlinear dynamical system and identifies its governing linear operator via Extended Dynamic Mode Decomposition (EDMD). A warm-start sequential training protocol enforces parameter-trajectory smoothness, and a Fourier-augmented observable dictionary exploits the periodic structure inherent in many real-world distribution drifts. Once identified, KOMET's Koopman operator predicts future parameter trajectories autonomously, without access to future labeled data, enabling zero-retraining adaptation at deployment. Evaluated on six datasets spanning rotating, oscillating, and expanding distribution geometries, KOMET achieves mean autonomous-rollout accuracies between 0.981 and 1.000 over 100 held-out time steps. Spectral and coupling analyses further reveal interpretable dynamical structure consistent with the geometry of the drifting decision boundary.
Problem

Research questions and friction points this paper is trying to address.

temporal domain drift
non-stationary environments
model degradation
distribution shift
parameter evolution
Innovation

Methods, ideas, or system contributions that make the work stand out.

Koopman operator
temporal domain generalization
Extended Dynamic Mode Decomposition
parameter trajectory prediction
zero-retraining adaptation
🔎 Similar Papers
No similar papers found.
R
Randy C. Hoover
Department of Electrical Engineering and Computer Science (EECS), South Dakota Mines, Rapid City, SD 57702, USA
J
Jacob James
Data Science and Engineering Program within EECS, South Dakota Mines, Rapid City, SD 57702, USA
P
Paul May
Department of Electrical Engineering and Computer Science (EECS), South Dakota Mines, Rapid City, SD 57702, USA
K
Kyle Caudle
Department of Mathematics, South Dakota Mines, Rapid City, SD 57702, USA