Research map / Learning theory and algorithms / Kernels and regression theory
Entangled Kernels - Beyond Separability
Riikka Huusari, Hachem Kadri
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 rank r (number of columns of Q) in EKL (ablation) | EKL · Simulated bilinear data (n=20, p=100) | mean squared error | Improved |
| increase the rank r in the scalar kernel extracted by partial trace (ablation) | ptrEKL · Simulated bilinear data (n=20, p=100) | mean squared error | No clear effect |
| use entangled kernel learning instead of separable kernel learning (OKL) or KRR when output count p is comparable to or larger than n | KRR/OKL · Simulated bilinear data, varying p and n | mean squared error | Improved |
| predict with the scalar kernel extracted by partial trace instead of the full entangled kernel | EKL · Simulated bilinear data, p larger than n | mean squared error | Improved |
Closest papers by meaning
- Optimal algorithmic complexity of inference in quantum kernel methods (NeurIPS 2026 · similarity 0.87)
- On the Trainability and Classical Simulability of Learning Matrix Product States Variationally (AAAI 2025 · similarity 0.85)
- Neural Auto-designer for Enhanced Quantum Kernels (ICLR 2024 · similarity 0.84)
- On the Relation between Trainability and Dequantization of Variational Quantum Learning Models (ICLR 2025 · similarity 0.83)
- Inverse M-Kernels for Linear Universal Approximators of Non-Negative Functions (NeurIPS 2024 · similarity 0.82)
- Locality Sensitive Hashing for p-Exponential Kernels with Applications to Density Estimation (NeurIPS 2026 · similarity 0.82)
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.
