Quantum Gaussian processes are defined via unitary quantum stochastic processes and proven scalable for matchgate evolutions, enabling regression, classification, and Bayesian optimization on quantum data.
The noisy kernel eK is assumed to exhibit independent and identically distributed (i.i.d.) noise in its (symmetric) entries as ˜kij = ˜kji = kij + εij with εij ∼ N (0, σ2 κ)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Provable and scalable quantum Gaussian processes for quantum learning
Quantum Gaussian processes are defined via unitary quantum stochastic processes and proven scalable for matchgate evolutions, enabling regression, classification, and Bayesian optimization on quantum data.