Research map / Learning theory and algorithms / Prediction and decision losses
Concentration of Data Encoding in Parameterized Quantum Circuits
Guangxi Li, Ruilin Ye, Xuanqiang Zhao, Xin Wang
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 encoding depth | Strongly entangling PQC encoding + QNN · Synthetic data set | test accuracy: eventually decay to 50\% or so | Hurt |
| Increase encoding depth | Strongly entangling PQC encoding + optimal POVM · Synthetic data set | maximum success probability: eventually decay to 50\% or so | Hurt |
| Increase encoding depth | Strongly entangling PQC encoding + QNN · Synthetic data set | training loss: about \ln 2 | Hurt |
| Increase encoding depth | Strongly entangling PQC encoding + QNN · MNIST (2 vs 9; 3 vs 6) | test accuracy | Hurt |
| Use higher-depth PQC encoding | Strongly entangling PQC encoding + QNN · MNIST (3 vs 6) | training loss: \ln 2 | Hurt |
| Increase encoding depth | PQC encoding · Synthetic data set | quantum divergence from the maximally mixed state: decrease exponentially | Hurt |
| Replace each U3 gate with U2 or U1 gates (ablation) | General PQC encoding · General PQC encoding | quantum divergence bound: a similar bound | No clear effect |
| Use only Ry rotations in each encoding layer (ablation) | General PQC encoding · General PQC encoding | quantum divergence bound: \log\lr{1+(2^n-1)\mathrm{e}^{-\lfloor\frac{D}{2}\rfloor \sigma^2}} | Mixed |
| Use two different kinds of rotation gates in each encoding layer (ablation) | General PQC encoding · General PQC encoding | quantum divergence bound: the same upper bound | No clear effect |
Closest papers by meaning
- Exponential Hardness of Optimization from the Locality in Quantum Neural Networks (AAAI 2024 · similarity 0.88)
- ATP: Adaptive Threshold Pruning for Efficient Data Encoding in Quantum Neural Networks (CVPR 2025 · similarity 0.87)
- Exponential Quantum Communication Advantage in Distributed Inference and Learning (NeurIPS 2024 · similarity 0.87)
- Exploring channel distinguishability in local neighborhoods of the model space in quantum neural networks (ICLR 2025 · similarity 0.87)
- Quantum Positional Encodings for Graph Neural Networks (ICML 2024 · similarity 0.86)
- Non-asymptotic Approximation Error Bounds of Parameterized Quantum Circuits (NeurIPS 2024 · similarity 0.86)
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.
