Complexity and precision in quantum associative retrieval
arXiv:2611.21941 · doi:10.1007/s44464-026-00051-7
Abstract
We show that efficient and high-precision quantum associative retrieval is possible with an exponential complexity advantage with respect to the classical brute force approach and with a polynomial capacity advantage with respect to classical neural network implementations for any number of patterns scaling polynomially in the number of qubits. Both classical neural and quantum associative memories store the patterns in a Hamiltonian; in the classical case the dynamics is irreversible relaxation toward attractors, in the quantum case it is unitary transformations generating an effective thermal distribution, followed by a measurement.
References in corpus (12)
- Quantum Machine Learning
- Quantum Mechanics helps in searching for a needle in a haystack
- Quantum Amplitude Amplification and Estimation
- Quantum Hopfield neural network
- Probabilistic Quantum Memories
- Pattern recognition on a quantum computer
- Quantum Template Matching
- Phase Transitions in Quantum Pattern Recognition
- Quantum Pattern Retrieval by Qubit Networks with Hebb Interactions
- Parametric Probabilistic Quantum Memory
- EP-PQM: Efficient Parametric Probabilistic Quantum Memory with Fewer Qubits and Gates
- Five Proofs of Chernoff's Bound with Applications