Quantum Fourier generative models are trained classically at over 1000-qubit scale using log-likelihood loss from Parseval's identity and deployed on superconducting hardware for fast sampling that preserves multi-modal structure.
Available: https://arxiv.org/abs/2602.11042
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
fields
quant-ph 7years
2026 7representative citing papers
Spectral Born machines are Fourier-phase quantum generative models over Z_d^n that train classically via graph-spectral MMD and show reduced parameters plus apparent overfitting resistance on integer data.
Analytical lower bounds and Lipschitz concentration results show when Gaussian-initialized IQP QCBMs avoid exponential gradient concentration under MMD training.
Develops an invariant-based framework connecting Pauli Lie algebras to transvection-generated Clifford subgroups for quantum reachability and dynamics analysis.
Sparse qubit connectivity inflates compiled circuit depth, pushing noisy IQP sampling implementations closer to the classically simulatable regime, whereas all-to-all architectures preserve a positive simulatability margin at current error rates.
Qudit extension of parameterized IQP circuits proposed for generative modeling of integer data, with loss function and covariance matrix, validated on electron shower energy deposits in CLIC electromagnetic calorimeter.
citing papers explorer
-
Quantum Fourier Generative Models Trainable at Large Scale
Quantum Fourier generative models are trained classically at over 1000-qubit scale using log-likelihood loss from Parseval's identity and deployed on superconducting hardware for fast sampling that preserves multi-modal structure.
-
Spectral Born machines: classically trainable quantum generative models for discrete data
Spectral Born machines are Fourier-phase quantum generative models over Z_d^n that train classically via graph-spectral MMD and show reduced parameters plus apparent overfitting resistance on integer data.
-
Trainability of IQP Quantum Circuit Born Machines Under Gaussian Initialization
Analytical lower bounds and Lipschitz concentration results show when Gaussian-initialized IQP QCBMs avoid exponential gradient concentration under MMD training.
-
From Pauli Strings to Quantum Dynamics: A Unified Characterization
Develops an invariant-based framework connecting Pauli Lie algebras to transvection-generated Clifford subgroups for quantum reachability and dynamics analysis.
-
The Impact of Qubit Connectivity on Quantum Advantage in Noisy IQP Circuits
Sparse qubit connectivity inflates compiled circuit depth, pushing noisy IQP sampling implementations closer to the classically simulatable regime, whereas all-to-all architectures preserve a positive simulatability margin at current error rates.
-
Qudit extension of parameterized IQP circuits: A generative quantum machine learning approach to integer data
Qudit extension of parameterized IQP circuits proposed for generative modeling of integer data, with loss function and covariance matrix, validated on electron shower energy deposits in CLIC electromagnetic calorimeter.
- An IQP Born Machine for Calorimeter Image Generation at 64 Qubits with Compiled-IQP Deployment