Research map / Learning theory and algorithms / Kernels and regression theory
Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces
Vladimir R Kostic, Pietro Novelli, Andreas Maurer, Carlo Ciliberto, Lorenzo Rosasco, Massimiliano Pontil
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 reduced-rank regression (RRR) instead of principal component regression (PCR) | rank-3 Koopman estimator · Noisy logistic map | test error: 0.18 -> 0.13 | Improved |
| use RRR instead of PCR | rank-3 Koopman estimator · Noisy logistic map | eigenvalue lambda_2,3 relative error: 0.85 -> 0.16 | Improved |
| use RRR instead of KRR | Koopman estimator · Noisy logistic map | test error: 0.13 -> 0.13 | No clear effect |
| use RRR instead of KRR | Koopman estimator · Noisy logistic map | training error: 0.032 -> 0.13 | Hurt |
| use RRR instead of KRR | Koopman estimator · Noisy logistic map | eigenvalue lambda_2,3 relative error: 0.48 -> 0.16 | Improved |
| use RRR instead of KRR | Koopman estimator · Noisy logistic map | eigenvalue lambda_1 relative error: 7.9 \cdot 10^{-7} -> 5.1 \cdot 10^{-6} | Hurt |
| use CNN feature kernel instead of linear or Gaussian kernel in RRR | rank-10 RRR · MNIST digit sequence forecasting | forecast quality (qualitative) | Improved |
Closest papers by meaning
- Deep-Koopman-KANDy: Dictionary Discovery for Deep-Koopman Operators with Kolmogorov-Arnold Networks for Dynamics (NeurIPS 2026 · similarity 0.89)
- ResKoopNet: Learning Koopman Representations for Complex Dynamics with Spectral Residuals (ICML 2025 · similarity 0.89)
- Learning invariant representations of time-homogeneous stochastic dynamical systems (ICLR 2024 · similarity 0.89)
- Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems (NeurIPS 2025 · similarity 0.89)
- SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting (ICML 2025 · similarity 0.88)
- Consistent Long-Term Forecasting of Ergodic Dynamical Systems (ICML 2024 · similarity 0.88)
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.
