GQKAE uses quantum-inspired Kolmogorov-Arnold networks to reduce parameters by 66% in generative quantum eigensolvers while achieving chemical accuracy on H4, N2, LiH, and other molecules.
hub
Quantum circuit optimization with deep reinforcement learning
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
A structure-aware transformer trained on 3-14 qubit systems predicts Trotter orderings for 16-20 qubit 1D Heisenberg Hamiltonians with a mean fidelity gap of 0.00115 to the best of 24 candidates.
Treating the replay buffer as a central lever in RL for quantum circuit optimization yields 4-32x sample efficiency gains, up to 67.5% faster episodes, and 85-90% fewer steps to accuracy on noisy molecular and compilation tasks.
Generative optimization of quantum embedding circuits improves supervised classification on some datasets, with derived bounds showing performance saturation governed by Wasserstein distance of the classical input data.
P-GONE applies generative ML to optimize Trotter-Suzuki decompositions, reporting up to 19.4x circuit depth reduction at F >= 0.95 versus Qiskit baselines on structured Hamiltonians.
A hybrid policy with classical preprocessing and a parameterized quantum circuit learns effective multiqubit disentanglement scheduling from partial two-qubit reduced-state observations, with preprocessing dominating performance and wider circuits outperforming deeper ones.
DeepQuantum is a PyTorch platform that unifies quantum circuits, photonic quantum circuits, and measurement-based quantum computing in one open-source framework for hybrid models and variational algorithms.
Presents a quantum Hamiltonian whose ground state encodes equivalence classes of expressions, enabling verification, counting, and structural queries on instances far beyond classical reach.
QARMA applies transformer-augmented reinforcement learning to qubit allocation and reuse in modular quantum systems, reporting up to 86% average reduction in inter-core communications versus optimized Qiskit baselines.
FactorLibrary stores reusable subexpressions to help RL agents (especially PPO+MCTS top-down) find certified optimal arithmetic circuits for polynomials up to complexity 8 at 91.8% success rate.
Hybrid quantum-classical constant propagation reduces multi-qubit quantum operations by propagating constants between quantum and classical program states.
DDQN reinforcement learning automates VITE circuit design, producing circuits with ~37% fewer gates and ~43% less depth than hardware-efficient ansatze for Max-Cut while reaching Full-CI for H2 with shallower depth.
citing papers explorer
-
Generative Quantum-inspired Kolmogorov-Arnold Eigensolver
GQKAE uses quantum-inspired Kolmogorov-Arnold networks to reduce parameters by 66% in generative quantum eigensolvers while achieving chemical accuracy on H4, N2, LiH, and other molecules.
-
Structure-Aware Transformers for Learning Near-Optimal Trotter Orderings with System-Size Generalization in 1D Heisenberg Hamiltonians
A structure-aware transformer trained on 3-14 qubit systems predicts Trotter orderings for 16-20 qubit 1D Heisenberg Hamiltonians with a mean fidelity gap of 0.00115 to the best of 24 candidates.
-
Replay-buffer engineering for noise-robust quantum circuit optimization
Treating the replay buffer as a central lever in RL for quantum circuit optimization yields 4-32x sample efficiency gains, up to 67.5% faster episodes, and 85-90% fewer steps to accuracy on noisy molecular and compilation tasks.
-
Generative Quantum Data Embeddings for Supervised Learning
Generative optimization of quantum embedding circuits improves supervised classification on some datasets, with derived bounds showing performance saturation governed by Wasserstein distance of the classical input data.
-
Physics Guided Generative Optimization for Trotter Suzuki Decomposition
P-GONE applies generative ML to optimize Trotter-Suzuki decompositions, reporting up to 19.4x circuit depth reduction at F >= 0.95 versus Qiskit baselines on structured Hamiltonians.
-
Learning quantum disentanglement scheduling from reduced states via modular hybrid policies
A hybrid policy with classical preprocessing and a parameterized quantum circuit learns effective multiqubit disentanglement scheduling from partial two-qubit reduced-state observations, with preprocessing dominating performance and wider circuits outperforming deeper ones.
-
DeepQuantum: A PyTorch-based Software Platform for Quantum Machine Learning and Photonic Quantum Computing
DeepQuantum is a PyTorch platform that unifies quantum circuits, photonic quantum circuits, and measurement-based quantum computing in one open-source framework for hybrid models and variational algorithms.
-
Quantum algorithms for equational reasoning
Presents a quantum Hamiltonian whose ground state encodes equivalence classes of expressions, enabling verification, counting, and structural queries on instances far beyond classical reach.
-
Learning-Optimized Qubit Mapping and Reuse to Minimize Inter-Core Communication in Modular Quantum Architectures
QARMA applies transformer-augmented reinforcement learning to qubit allocation and reuse in modular quantum systems, reporting up to 86% average reduction in inter-core communications versus optimized Qiskit baselines.
-
FactorLibrary: From Polynomials to Circuits via Recursive Subgoals
FactorLibrary stores reusable subexpressions to help RL agents (especially PPO+MCTS top-down) find certified optimal arithmetic circuits for polynomials up to complexity 8 at 91.8% success rate.
-
Automatic De-Quantization of Quantum Programs Using Constant Propagation
Hybrid quantum-classical constant propagation reduces multi-qubit quantum operations by propagating constants between quantum and classical program states.
-
Investigation of Automated Design of Quantum Circuits for Imaginary Time Evolution Methods Using Deep Reinforcement Learning
DDQN reinforcement learning automates VITE circuit design, producing circuits with ~37% fewer gates and ~43% less depth than hardware-efficient ansatze for Max-Cut while reaching Full-CI for H2 with shallower depth.
- Noise tolerance via reinforcement in the quantum search problem