Preprint Mathematics
Mixed-state escape bounds and proper agnostic learning of stabilizer states in odd-prime dimensions
- Manuscript
- Archived
- Edition
- 1 · Permanent link
Overview
Abstract
We prove mixed-input escape bounds for weighted Weyl measurements in every odd-prime local dimension. A purity-sensitive single-system inequality supplies the mixed-state estimate. Combined with stabilizer bootstrapping, coherent conditioning and bounded rejection sampling, it yields a proper additive agnostic learner with explicit resource bounds. For each fixed prime and a lower bound on stabilizer overlap, the resource dependence on inverse overlap is quasipolynomial.
Keywords stabilizer states · agnostic learning · quantum learning · mixed states · odd-prime dimensions
Scope of the work
Arbitrary mixed inputs in odd-prime dimension, in an exact Clifford and coherent-measurement model. The stated copy counts and resource bounds are sufficient. The qutrit case is included in this consolidated paper.
Reproduction notes
Corrected October 18, 2026 version. The complete package contains the manuscript, analytic proofs, verification programs, numerical diagnostics and checksum manifest. Reproduction instructions are in README.txt. Finite diagnostics supplement the analytic proofs.
The manuscript
Read the paper
The complete manuscript, as published in this edition.
If the reader is unavailable on your device, open or download the PDF directly.
A stable scholarly record
Cite this edition
Scott Schubr. (2026). Mixed-state escape bounds and proper agnostic learning of stabilizer states in odd-prime dimensions (Version 1). Luminary Research Archive. https://luminaryoddities.com/researcharchive/mixed-state-escape-bounds-proper-agnostic-learning-stabilizer-states-odd-prime-dimensions/v/1
BibTeX
@techreport{luminary_mixed_state_escape_bounds_proper_agnostic_learning_stabilizer_states_odd_prime_dimensions_v1,
title = {Mixed-state escape bounds and proper agnostic learning of stabilizer states in odd-prime dimensions},
author = {Scott Schubr},
year = {2026},
institution = {Luminary Research Archive},
type = {Preprint},
note = {Version 1},
url = {https://luminaryoddities.com/researcharchive/mixed-state-escape-bounds-proper-agnostic-learning-stabilizer-states-odd-prime-dimensions/v/1}
}Reader correspondence
Share feedback
Questions, observations, and corrections are welcome. Your message goes privately to the research team and refers to edition 1.
Sign in to Luminary