Research map / Learning theory and algorithms / Kernels and regression theory
Spectral Truncation Kernels: Noncommutativity in C*-algebraic Kernel Machines
Yuka Hashimoto, Ayoub Hafid, Masahiro Ikeda, 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 |
|---|---|---|---|
| use finite truncation n=9 spectral truncation kernel instead of nonseparable vvRKHS kernel | kernel ridge regression · Synthetic regression | test error: 3.70 \times 10^{-4} -> 5.40\times 10^{-5} | Improved |
| use spectral truncation kernel instead of nonseparable vvRKHS kernel | kernel ridge regression · Synthetic regression | CPU time (s): 570.4 -> 149.3 | Improved |
| use finite truncation parameter n instead of n=infinity (commutative kernel) (ablation) | spectral truncation kernel · Synthetic regression | test error: best at n=32, worse for larger or smaller n | Improved |
| use finite truncation parameter n instead of n=infinity (ablation) | spectral truncation kernel · MNIST image recovery | test error: best at n=70 | Improved |
| use spectral truncation kernel ridge regression instead of two-layer CNN | MNIST image recovery · MNIST image recovery | test error | Improved |
Closest papers by meaning
- Learning with Operator-valued Kernels in Reproducing Kernel Krein Spaces (NeurIPS 2020 · similarity 0.87)
- Operator-valued Kernels for Learning from Functional Response Data (JMLR 2016 · similarity 0.85)
- Spectrally Transformed Kernel Regression (ICLR 2024 · similarity 0.84)
- Position: $C^*$-Algebraic Machine Learning $-$ Moving in a New Direction (ICML 2024 · similarity 0.84)
- On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity (NeurIPS 2024 · similarity 0.83)
- Inverse M-Kernels for Linear Universal Approximators of Non-Negative Functions (NeurIPS 2024 · similarity 0.83)
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.
