Research map / Learning theory and algorithms / Prediction and decision losses
Power and limitations of single-qubit native quantum neural networks
Zhan Yu, Hongshun Yao, Mujin Li, 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 the number of layers (ablation) | Single-qubit native QNN · Damping function f(x)=sin(5x)/(5x) | approximation error | Improved |
| Use 45 layers with complex trainable blocks | Single-qubit native QNN U^WZW · Square wave function | approximation quality | Improved |
| Increase the number of layers (ablation) | Single-qubit native QNN · Bivariate function f(x,y) | training loss | No clear effect |
| Use a two-qubit Parallel-Entanglement model instead of a single-qubit model | Native QNN · Bivariate function f(x,y) | approximation quality | Improved |
| Replace the trainable blocks with universal trainable blocks (ablation) | Two-qubit QNN · Bivariate function f(x,y) | approximation quality | Improved |
Closest papers by meaning
- Exponential Hardness of Optimization from the Locality in Quantum Neural Networks (AAAI 2024 · similarity 0.91)
- Exploring channel distinguishability in local neighborhoods of the model space in quantum neural networks (ICLR 2025 · similarity 0.88)
- Non-asymptotic Approximation Error Bounds of Parameterized Quantum Circuits (NeurIPS 2024 · similarity 0.88)
- ATP: Adaptive Threshold Pruning for Efficient Data Encoding in Quantum Neural Networks (CVPR 2025 · similarity 0.88)
- Quantum Positional Encodings for Graph Neural Networks (ICML 2024 · similarity 0.86)
- Characterizing Trainability of Instantaneous Quantum Polynomial Circuit Born Machine (NeurIPS 2026 · 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.
