Research map / Probabilistic and scientific modeling / Dynamical systems
ShadowNet for Data-Centric Quantum System Learning
Yuxuan Du, Yibo Yang, Tongliang Liu, Zhouchen Lin, David A. Clifton, Bernard Ghanem, Dacheng Tao
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| increase training set size from 8 to 200 (ablation) | attention ShadowNet · TFIM QST | test ground energy estimation error: 0.94 -> 0.02 | Improved |
| increase training set size from 8 to 200 (ablation) | attention ShadowNet · TFIM QST | test fidelity: 0.81 -> 1 | Improved |
| increase training set size from 100 to 800 (M=500) (ablation) | attention ShadowNet · TFIM+XXZ QST | test fidelity: 0.878 -> 0.995 | Improved |
| increase training set size from 100 to 800 (M=500) (ablation) | attention ShadowNet · TFIM+XXZ QST | ground energy estimation error: 1.361 -> 0.044 | Improved |
| increase shot number from 500 to 2000 at n=100 (ablation) | attention ShadowNet · TFIM+XXZ QST | test fidelity: 0.878 -> 0.933 | Improved |
| increase shot number from 500 to 2000 at n=800 (ablation) | attention ShadowNet · TFIM+XXZ QST | test fidelity: 0.995 -> 0.996 | No clear effect |
| use ShadowNet instead of classical shadows (n=800, M=500) | ShadowNet · TFIM+XXZ QST | ground energy estimation error: 0.477 -> 0.044 | Improved |
| use ShadowNet instead of classical shadows (n=800, M=2000) | ShadowNet · TFIM+XXZ QST | ground energy estimation error: 0.204 -> 0.038 | Improved |
| use attention instead of convolution (n=100) (ablation) | ShadowNet · TFIM+XXZ QST | train fidelity: 0.706 -> near 1 | Improved |
| use attention instead of convolution (n=800) (ablation) | ShadowNet · TFIM+XXZ QST | train fidelity: 0.914 -> near 1 | Improved |
| add classical shadows to noise-parameter features (ablation) | attention ShadowNet · noisy GHZ DFE (N=60) | test loss: 0.0147 -> 0.00013 | Improved |
| add noise parameters to classical shadow features (ablation) | attention ShadowNet · noisy GHZ DFE (N=60) | test loss: 0.0196 -> 0.00013 | Improved |
Closest papers by meaning
- Rethink the Role of Deep Learning towards Large-scale Quantum Systems (ICML 2025 · similarity 0.88)
- TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture search (NeurIPS 2025 · similarity 0.85)
- ATP: Adaptive Threshold Pruning for Efficient Data Encoding in Quantum Neural Networks (CVPR 2025 · similarity 0.85)
- One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective (NeurIPS 2026 · similarity 0.85)
- Reinforced Learning Explicit Circuit Representations for Quantum State Characterization from Local Measurements (ICML 2025 · similarity 0.85)
- Online Learning of Pure States is as Hard as Mixed States (NeurIPS 2025 · similarity 0.85)
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.
