AI and the World's Hard Problems · Quantum physics & quantum computing · arXiv · 2026-10-20
Supervised Learning with Quantum Hamiltonian Embeddings
The authors propose quantum Hamiltonian embeddings, a supervised learning framework that encodes a classical training dataset into a single parameterized Hamiltonian whose approximate ground state defines the classification rule. They establish efficient gradient estimation and prove generalization guarantees. They also demonstrate the framework on IBM Heron processors using a standard benchmark dataset.