ExplorerData ScienceMachine Learning
Research PaperResearchia:202603.10067

Quantum Diffusion Models: Score Reversal Is Not Free in Gaussian Dynamics

Ammar Fayad

Abstract

Diffusion-based generative modeling suggests reversing a noising semigroup by adding a score drift. For continuous-variable Gaussian Markov dynamics, complete positivity couples drift and diffusion at the generator level. For a quantum-limited attenuator with thermal parameter $ν$ and squeezing $r$, the fixed-diffusion Wigner-score (Bayes) reverse drift violates CP iff $\cosh(2r)>ν$. Any Gaussian CP repair must inject extra diffusion, implying $-2\ln F\ge c_{\text{geom}}(ν_{\min})I_{\mathrm{dec}...

Submitted: March 10, 2026Subjects: Machine Learning; Data Science

Description / Details

Diffusion-based generative modeling suggests reversing a noising semigroup by adding a score drift. For continuous-variable Gaussian Markov dynamics, complete positivity couples drift and diffusion at the generator level. For a quantum-limited attenuator with thermal parameter νν and squeezing rr, the fixed-diffusion Wigner-score (Bayes) reverse drift violates CP iff cosh(2r)>ν\cosh(2r)>ν. Any Gaussian CP repair must inject extra diffusion, implying 2lnFcgeom(νmin)Idecwc-2\ln F\ge c_{\text{geom}}(ν_{\min})I_{\mathrm{dec}}^{\mathrm{wc}}.


Source: arXiv:2603.06488v1 - http://arxiv.org/abs/2603.06488v1 PDF: https://arxiv.org/pdf/2603.06488v1 Original Link: http://arxiv.org/abs/2603.06488v1

Please sign in to join the discussion.

No comments yet. Be the first to share your thoughts!

Access Paper
View Source PDF
Submission Info
Date:
Mar 10, 2026
Topic:
Data Science
Area:
Machine Learning
Comments:
0
Bookmark