Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kam, Chon-Fai, Cadet, Xavier, Bessafi, Miloud, Cadet, Frederic
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.11557
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910211132882944
author Kam, Chon-Fai
Cadet, Xavier
Bessafi, Miloud
Cadet, Frederic
author_facet Kam, Chon-Fai
Cadet, Xavier
Bessafi, Miloud
Cadet, Frederic
contents While world models learn compact representations of complex environments, they lack a physics-grounded metric to assess the structural fidelity of their latent spaces. We identify the wavelet scaling exponent $α$ as a critical diagnostic, proposing optimal representations satisfy variance equipartition ($α\approx 1/2$) -- mirroring Kolmogorov's inertial range. We establish $α= 1/2$ as a sharp transition boundary for the classical simulability of amplitude-encoded quantum kernels. Using tensor-network theory, we prove latents with $α> 1/2$ reside in an area-law phase admitting efficient classical emulation, while $α< 1/2$ triggers a volume-law phase where the Matrix Product State bond dimension $χ$ grows exponentially with qubit count $n$. Analyzing pre-trained VideoMAE latents reveals a dichotomy: spatial tokens approach the equipartition limit ($α\approx 0.423$), but permutation-invariant feature channels exhibit unstructured disorder ($α\approx -0.123$). This forces real-world latents deep into the volume-law phase, providing a data-driven necessary condition for simulation hardness. Finally, we apply Weingarten calculus to derive the exact variance of the scrambled transition probability under a 2-design ensemble. We prove this variance scales strictly as $\Var[X] = Θ(d^{-2})$. We confirm this numerically with a log-log slope of $-1.881$ ($R^2 = 0.999$), identifying a formidable shot-noise wall demanding a measurement budget of $M = Ω(d^2)$ that constrains quantum machine learning scalability.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11557
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Wavelet Variance Equipartition as a Threshold for World-Model Quality and Quantum Kernel TN-Simulability
Kam, Chon-Fai
Cadet, Xavier
Bessafi, Miloud
Cadet, Frederic
Quantum Physics
While world models learn compact representations of complex environments, they lack a physics-grounded metric to assess the structural fidelity of their latent spaces. We identify the wavelet scaling exponent $α$ as a critical diagnostic, proposing optimal representations satisfy variance equipartition ($α\approx 1/2$) -- mirroring Kolmogorov's inertial range. We establish $α= 1/2$ as a sharp transition boundary for the classical simulability of amplitude-encoded quantum kernels. Using tensor-network theory, we prove latents with $α> 1/2$ reside in an area-law phase admitting efficient classical emulation, while $α< 1/2$ triggers a volume-law phase where the Matrix Product State bond dimension $χ$ grows exponentially with qubit count $n$. Analyzing pre-trained VideoMAE latents reveals a dichotomy: spatial tokens approach the equipartition limit ($α\approx 0.423$), but permutation-invariant feature channels exhibit unstructured disorder ($α\approx -0.123$). This forces real-world latents deep into the volume-law phase, providing a data-driven necessary condition for simulation hardness. Finally, we apply Weingarten calculus to derive the exact variance of the scrambled transition probability under a 2-design ensemble. We prove this variance scales strictly as $\Var[X] = Θ(d^{-2})$. We confirm this numerically with a log-log slope of $-1.881$ ($R^2 = 0.999$), identifying a formidable shot-noise wall demanding a measurement budget of $M = Ω(d^2)$ that constrains quantum machine learning scalability.
title Wavelet Variance Equipartition as a Threshold for World-Model Quality and Quantum Kernel TN-Simulability
topic Quantum Physics
url https://arxiv.org/abs/2605.11557