Research map / Learning theory and algorithms / Kernels and regression theory
A Convex Parametrization of a New Class of Universal Kernel Functions
Brendon K. Colbert, Matthew M. Peet
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 |
|---|---|---|---|
| replace SimpleMKL Gaussian/polynomial library with Tessellated Kernel SDP | SimpleMKL · UCI Liver | test set accuracy: 65.51 -> 72.32 | Improved |
| replace SimpleMKL library with Tessellated Kernel SDP | SimpleMKL · UCI Cancer | test set accuracy: 96.55 -> 97.18 | Improved |
| replace SimpleMKL library with Tessellated Kernel SDP | SimpleMKL · UCI Heart | test set accuracy: 83.70 -> 83.46 | No clear effect |
| replace SimpleMKL library with Tessellated Kernel SDP | SimpleMKL · UCI Ionosphere | test set accuracy: 92.16 -> 93.24 | Improved |
| use random PSD TK matrices as SimpleMKL library | SimpleMKL · UCI Ionosphere | test set accuracy: 92.16 -> 87.65 | Hurt |
| use random PSD TK matrices as SimpleMKL library | SimpleMKL · UCI Heart | test set accuracy: 83.70 -> 84.38 | Improved |
| use random PSD TK matrices as SimpleMKL library | SimpleMKL · UCI Pima | test set accuracy: 76.00 -> 76.75 | Improved |
| use TK SDP instead of neural net | 3-layer neural net · UCI Liver | test set accuracy: 66.32 -> 72.32 | Improved |
| use TK SDP instead of SimpleMKL | SimpleMKL · UCI Liver | training time: 2.61 -> 95.75 | Hurt |
| use random TK library instead of TK SDP | TK SDP · UCI Pima | training time: 1211.66 -> 34.65 | Improved |
| increase training set size on noisy spiral (1400 points, sigma .1) | TK vs SimpleMKL · Noisy spiral | test set accuracy | Improved |
Closest papers by meaning
- Infinite Kernel Learning: Generalization Bounds and Algorithms (AAAI 2017 · similarity 0.88)
- The optimality of kernel classifiers in Sobolev space (ICLR 2024 · similarity 0.86)
- On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity (NeurIPS 2024 · similarity 0.86)
- Faster Algorithms for Structured Linear and Kernel Support Vector Machines (ICLR 2025 · similarity 0.85)
- Joker: Joint Optimization Framework for Lightweight Kernel Machines (ICML 2025 · similarity 0.85)
- Inverse M-Kernels for Linear Universal Approximators of Non-Negative Functions (NeurIPS 2024 · 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.
