English

Behavioral Heterogeneity as Quantum-Inspired Representation

Machine Learning 2026-03-25 v1 Multiagent Systems Methodology

Abstract

Driver heterogeneity is often reduced to labels or discrete regimes, compressing what is inherently dynamic into static categories. We introduce quantum-inspired representation that models each driver as an evolving latent state, presented as a density matrix with structured mathematical properties. Behavioral observations are embedded via non-linear Random Fourier Features, while state evolution blends temporal persistence of behavior with context-dependent profile activation. We evaluate our approach on empirical driving data, Third Generation Simulation Data (TGSIM), showing how driving profiles are extracted and analyzed.

Keywords

Cite

@article{arxiv.2603.22729,
  title  = {Behavioral Heterogeneity as Quantum-Inspired Representation},
  author = {Mohammad Elayan and Wissam Kontar},
  journal= {arXiv preprint arXiv:2603.22729},
  year   = {2026}
}
R2 v1 2026-07-01T11:34:42.233Z