Research map / Learning theory and algorithms / Kernels and regression theory
Deep learning with kernels through RKHM and the Perron-Frobenius operator
Yuka Hashimoto, 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 deep RKHM (operator-norm loss) instead of deep vvRKHS with Hilbert-Schmidt norm | autoencoder · synthetic d=10, n=10 | generalization error | Improved |
| Add Perron-Frobenius operator term (lambda1=100 vs 0) to loss (ablation) | deep RKHM · synthetic d=10, n=1000 | generalization error | Improved |
| Use deep RKHM instead of CNN with 7x7 and 4x4 filters | MNIST classifier with 2 dense layers · MNIST, n=20 | test accuracy | Improved |
| Add Perron-Frobenius operator term (lambda1=1 vs 0) (ablation) | deep RKHM · MNIST, n=20 | test accuracy | Improved |
| Use deep RKHM instead of CNN with equal parameter count | MNIST classifier · MNIST, n=20 | test accuracy | Improved |
| Add Perron-Frobenius operator term (lambda1=1 vs 0) (ablation) | deep RKHM · MNIST | test loss | Improved |
Closest papers by meaning
- Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs (ICLR 2026 · similarity 0.88)
- Reproducing kernel Hilbert C*-module and kernel mean embeddings (JMLR 2021 · similarity 0.88)
- A Representer Theorem for Deep Kernel Learning (JMLR 2019 · similarity 0.87)
- Hierarchical Kernels in Deep Kernel Learning (JMLR 2023 · similarity 0.86)
- A Kernel Perspective for Regularizing Deep Neural Networks (ICML 2019 · similarity 0.86)
- Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines (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.
