Adaptive directional gradients for parameterized quantum circuits
Researchers have developed an LLM-driven system for autonomously designing quantum circuits, integrating knowledge acquisition, code generation, and experimental feedback. This framework has shown success in constructing quantum feature maps for machine learning and ansatz for variational quantum eigensolvers in quantum chemistry, outperforming classical methods in benchmarks. Separately, a new framework for forward gradient estimators in parameterised quantum circuits has been proposed, significantly improving training efficiency and reducing measurement costs compared to existing methods, enabling training on larger quantum neural networks. AI
IMPACT LLMs are being applied to complex scientific optimization problems, while new gradient estimation techniques promise more efficient training of quantum machine learning models.
- parameter-shift rule
- Quantum Approximate Optimisation Algorithm (QAOA)
- Variational Quantum Eigensolver (VQE)
- gCANS
- ECG5000 dataset
- Parameterised Quantum Circuits (PQCs)
- MNIST
- QUIVER
- random coordinate descent
- variational quantum eigensolver
- quantum approximate optimisation algorithm
- ECG5000
- parameterised quantum circuits
- LLM
- arXiv
- quantum physics
- quantum chemistry
- Quantum Machine Learning
- Hugging Face