Quantum
Symmetry Discovery in Quantum Learning: Observable-Level and Task-Level Inference from Finite Measurements
Publication: quant-ph updates on arXiv.org
Author: Zeyu Chen
Source published: 02/10/2026, 04:00:00 UTC
Briefing created: 02/10/2026, 04:20:42 UTC
Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 02/10/2026, 04:13:24 UTC.
Briefings
This research establishes a finite-measurement theory for inferring symmetry groups in quantum learning models. The central finding is that observable-invisible transformations correspond to the stabilizer of a projected state when the probe span is invariant. The study introduces an unbiased shadow statistic to distinguish zero from positive squared expectation discrepancies, improving inverse-square-gap estimation rates. It also provides a commuting qubit lower bound proving gap dependence is optimal at fixed snapshot scales, alongside data-dependent tolerances for simultaneous intervals. Task validation uses either a characteristic kernel or encoded mean discrepancy to test joint distributions, while an exact group-average identity links these to task-breaking mass. The work determines which symmetry measurements support and provides the statistical basis for future release decisions.
Key points
- The central structural result identifies observable-invisible transformations with the stabilizer of a projected state whenever the probe span is invariant.
- An unbiased shadow statistic distinguishes zero from positive squared expectation discrepancies with an inverse-gap measurement rate, improving the inverse-square-gap rate of uniform discrepancy estimation.
Context and limitations
The study relies on finite dictionaries and assumes an invariant pure-state backbone. Results are based on Ising-chain calculations and are subject to uncertainty regarding continuous invisible spaces and label-dependent symmetry constraints.
Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 02/10/2026, 04:20:42 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.
View archived briefing on IPFS
bafybeic6n2mnrjbg3z6kvuuwei32zlbb5tjkscu7a42lqqefldmhy2q46e