Research map / Reinforcement learning / Visual and representation RL
Learning to Optimize Variational Quantum Circuits to Solve Combinatorial Problems
Sami Khairy, Ruslan Shaydulin, Lukasz Cincio, Yuri Alexeev, Prasanna Balaprakash
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use a KDE model learned from high-quality training-instance parameters instead of Nelder-Mead | QAOA parameter optimization · Random graphs, p=1, p=2, and p=4 | median optimality gap reduction factor: 7.06; 8.07; 6.52 | Improved |
| Use a KDE model learned from high-quality training-instance parameters instead of Nelder-Mead | QAOA parameter optimization · Community graphs, p=1, p=2, and p=4 | median optimality gap reduction factor: 26.20; 14.15; 9.31 | Improved |
| Use a KDE model learned from high-quality training-instance parameters instead of Nelder-Mead | QAOA parameter optimization · Ladder graphs, p=1, p=2, and p=4 | median optimality gap reduction factor: 17.68; 30.15; 8.15 | Improved |
| Use an RL-learned policy instead of Nelder-Mead | QAOA parameter optimization · Random graphs, p=1, p=2, and p=4 | median optimality gap reduction factor: 3.07; 1.81; 1.37 | Improved |
| Use an RL-learned policy instead of Nelder-Mead | QAOA parameter optimization · Community graphs, p=1, p=2, and p=4 | median optimality gap reduction factor: 2.66; 1.47; 1.05 | Improved |
| Use an RL-learned policy instead of Nelder-Mead | QAOA parameter optimization · Ladder graphs, p=1, p=2, and p=4 | median optimality gap reduction factor: 5.59; 1.87; 1.12 | Improved |
| Increase QAOA circuit depth | QAOA · Test graphs, especially community and ladder graphs | approximation ratio | Improved |
Closest papers by meaning
- Curriculum reinforcement learning for quantum architecture search under hardware errors (ICLR 2024 · similarity 0.91)
- TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture search (NeurIPS 2025 · similarity 0.90)
- Training-Free Quantum Architecture Search (AAAI 2024 · similarity 0.89)
- MG-Net: Learn to Customize QAOA with Circuit Depth Awareness (NeurIPS 2024 · similarity 0.89)
- Q-MAML: Quantum Model-Agnostic Meta-Learning for Variational Quantum Algorithms (AAAI 2025 · similarity 0.89)
- Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithm (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
