Matrix product state pre-training for quantum machine learning
Hybrid quantum–classical algorithms are a promising candidate for develo** uses for
NISQ devices. In particular, parametrised quantum circuits (PQCs) paired with classical …
NISQ devices. In particular, parametrised quantum circuits (PQCs) paired with classical …
Quantum Fourier networks for solving parametric PDEs
Many real-world problems, like modelling environment dynamics, physical processes, time
series etc involve solving partial differential equations (PDEs) parameterised by problem …
series etc involve solving partial differential equations (PDEs) parameterised by problem …
Quantum angle generator for image generation
R Florian, V Sofia, G Michele, B Kerstin… - 2022 IEEE/ACM 7th …, 2022 - ieeexplore.ieee.org
The Quantum Angle Generator (QAG) is a new generative model for quantum computers. It
consists of a parameterized quantum circuit trained with an objective function. The QAG …
consists of a parameterized quantum circuit trained with an objective function. The QAG …
Fast batch gradient descent in quantum neural networks
JY Shim, J Kim - Electronics Letters, 2025 - Wiley Online Library
A novel batch gradient descent algorithm for parameterized quantum circuits that
significantly reduces the time complexity in terms of batch size for training quantum neural …
significantly reduces the time complexity in terms of batch size for training quantum neural …
Neural networks with complex-valued weights have no spurious local minima
X Liu - arxiv preprint arxiv:2103.07287, 2021 - arxiv.org
We study the benefits of complex-valued weights for neural networks. We prove that shallow
complex neural networks with quadratic activations have no spurious local minima. In …
complex neural networks with quadratic activations have no spurious local minima. In …