Electronic Resource

Orthogonality in Quantum-ProbabilisticMachine Learning: An Investigation onMultiqubit Encoding

---

The “black-box” nature of deep learning models fundamentally limits their reliability in critical applications.Tensor networks (TNs), drawing on their interpretable, quantum-probabilistic foundations, offer a promisingpathway toward more transparent machine learning (ML). However, a systematic understanding of theircapabilities and limitations remains an open challenge. Here, we establish a fundamental connectionbetween a core property of quantum systems, namely, the catastrophe of orthogonality (COO), and therepresentational power and generalization performance of quantum-probabilistic TN models. Taking theFashion Modified National Institute of Standards and Technology dataset, we propose 2 multiqubit dataencoding schemes and demonstrate that key hyperparameters, such as the number of qubits, featurecount, and mapping angle, modulate the onset of COO. This control mechanism directly dictates the model’scapacity, revealing that over-fitting can be interpreted as a specific regime of the quantum state space. Ourwork provides a theoretical lens, grounded in quantum many-body physics, for interpreting ML models.It positions TNs not merely as efficient computational tools but as a foundational framework for buildinginherently interpretable and reliable ML models

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

-

Penerbit

Beijing, China : Science Partner Journal., 2026

Deskripsi Fisik

10 hlm.

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

MACHINE LEARNING

Info Detail Spesifik

-

Pernyataan Tanggungjawab

Sheng-Chen Bai, Kun Zhang, and Shi-Ju Ran

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar