Quantum Causal Representations for Learning and Dimensional Reduction

Authors

Keywords:

quantum causality, information geometry, dimensionality reduction, quantum principal component analysis, machine learning

Abstract

This paper investigates the limitations of classical causal and statistical represen- tations when applied to complex information structures arising in quantum systems and advanced learning frameworks. Classical approaches, including correlation-based linear algebra and deterministic causal models, assume fixed causal order and linear in- formation flow, which become insufficient in the presence of quantum correlations and indefinite causal structures. The objective of this study is to develop a unified con- ceptual and mathematical framework integrating quantum information theory, causal modeling, and dimensionality reduction. Using a theoretical and analytical approach grounded in Hilbert space formalism and operator-based representations, the study in- troduces quantum causal matrices, quantum causal principal component analysis, and higher-order quantum causal tensors. The results show that quantum-enhanced repre- sentations provide a richer and more expressive description of structural dependencies beyond classical limits. This framework offers new perspectives on causal inference, learning representations, and information geometry. The main conclusion is that quan- tum informational principles enable a principled extension of classical models with significant implications for machine learning, artificial intelligence, and foundational studies of causality.

Keywords: quantum causality; information geometry; dimensionality reduction; quan- tum principal component analysis; machine learning

 

INTISARI

Makalah ini mengkaji keterbatasan representasi kausal dan statistik klasik ketika diterapkan pada struktur informasi yang kompleks, khususnya pada sistem kuantum dan kerangka pembelajaran lanjut. Pendekatan klasik, termasuk aljabar linear berbasis korelasi dan model kausal deterministik, umumnya mengasumsikan urutan kausal yang tetap serta aliran informasi yang linear, sehingga menjadi tidak memadai ketika berhadapan dengan korelasi kuantum dan struktur kausal yang tidak terdefinisi secara pasti. Tujuan penelitian ini adalah membangun suatu kerangka konseptual dan matematis terpadu yang mengintegrasikan teori informasi kuantum, pemodelan kausal, dan reduksi dimensi. Metode yang digunakan bersifat teoretis dan analitis dengan memanfaatkan formalisme ruang Hilbert dan representasi berbasis operator. Hasil kajian menunjukkan bahwa representasi kausal berbasis prinsip kuantum mampu memberikan deskripsi ketergantungan struktural yang lebih kaya dibandingkan pendekatan klasik. Kesimpulan utama dari penelitian ini adalah bahwa prinsip informasi kuantum menyediakan perluasan yang berlandaskan teori terhadap model-model klasik dengan implikasi penting bagi pembelajaran mesin, kecerdasan buatan, dan kajian fundamental kausalitas.

Kata Kunci: kausalitas kuantum; teori informasi; reduksi dimensi; QC-PCA; pembelajaran mesin

References

Bell, J. S. (1964). On the einstein podolsky rosen paradox. Physics Physique Fizika, 1 (3), 195–200. https://doi.org/10.1103/PhysicsPhysiqueFizika.1.195

Brukner, Cˇ. (2014). Quantum causality. Nature Physics, 10, 259–263. https://doi.org/10.1038/nphys2930

Chiribella, G., D’Ariano, G. M., Perinotti, P., & Valiron, B. (2013). Quantum computations with indefinite causal structure. Physical Review A, 88 (2), 022318. https://doi.org/ 10.1103/PhysRevA.88.022318

Choi, M.-D. (1975). Completely positive linear maps on complex matrices. Linear Algebra and Its Applications, 10, 285–290. https://doi.org/10.1016/0024-3795(75)90075-0

Ghojogh, B., & Crowley, M. (2019). Principal component analysis: A tutorial. https://arxiv. org/abs/1906.03148

Greenberger, D. M., Horne, M. A., & Zeilinger, A. (1990). Bell’s theorem without inequalities. American Journal of Physics, 58 (12), 1131–1143. https://doi.org/10.1119/1.16243

Horodecki, R., Horodecki, P., Horodecki, M., & Horodecki, K. (2009). Quantum entanglement. Reviews of Modern Physics, 81 (2), 865–942. https : //doi . org /10 . 1103 / RevModPhys.81.865

Jolliffe, I., & Cadima, J. (2016). Principal component analysis. Springer. https://doi.org/10.1007/978-1-4899-7545-2

Lloyd, S., Mohseni, M., & Rebentrost, P. (2014). Quantum principal component analysis. Nature Physics, 10, 631–633. https://doi.org/10.1038/nphys3029

Nielsen, M. A., & Chuang, I. L. (2010). Quantum computation and quantum information. Cambridge University Press. https://doi.org/10.1017/CBO9780511976667

Oreshkov, O., Costa, F., & Brukner, Cˇ. (2012). Quantum correlations with no causal order. Nature Communications, 3, 1092. https://doi.org/10.1038/ncomms2076

Oru´s, R. (2014). A practical introduction to tensor networks: Matrix product states and projected entangled pair states. Annals of Physics, 349, 117–158. https://doi.org/10. 1016/j.aop.2014.06.013

Pearl, J. (2009). Causality: Models, reasoning, and inference (2nd ed.). Cambridge University Press. https://doi.org/10.1017/CBO9780511803161

Petz, D. (2011). Introduction to quantum information theory. Springer. https://doi.org/10.1007/978-3-642-18263-2

Petz, D., & Suda´r, C. (1996). Monotone metrics on matrix spaces. Linear Algebra and its Applications, 244, 81–96. https://doi.org/10.1016/0024-3795(94)00211-8

Spirtes, P., Glymour, C., & Scheines, R. (2000). Causation, prediction, and search. MIT Press. https://mitpress.mit.edu/9780262194402

Downloads

Published

2026-01-01