Verifiable Sampling for Delegated Generative Quantum Machine Learning

quant-ph, cs.LG

Submitted: 2026-10-09

Updated: 2026-10-09

Comments: 6 pages, 1 figure, 1 table. Accepted at the 2026 IEEE 2nd International Conference on Quantum Artificial Intelligence (QAI 2026). \c{opyright} 2026 IEEE

Code: https://github.com/qat-inria/veriphix

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• An unconditional distribution learning advantage with shallow quantum circuits
• Exponential separations between classical and quantum learners
• Generative quantum advantage for classical and quantum problems
• Generative modeling with Gaussian Boson Sampling: classically trainable Bosonic Born Machines
• The Born Ultimatum: Conditions for Classical Surrogation of Quantum Generative Models with Correlators
• Universal blind quantum computation
• Sample-based training of quantum generative models
• IQPopt: Fast optimization of instantaneous quantum polynomial circuits in JAX

Related papers

• Reconquering Bell sampling on qudits: stabilizer learning and testing, quantum pseudorandomness bounds, and more
• Encrypted clones can leak: Classification of informative subsets in Quantum Encrypted Cloning
• Polynomial-time classical and quantum simulation of quantum impurity models
• A quasiparticle-protected superconducting qubit
• Theory of quantum-enhanced interferometry with general Markovian light sources
• A convergent hierarchy of spectral gap certificates for qubit Hamiltonians