Research map / Learning theory and algorithms / Kernels and regression theory
Sharp Spectral Rates for Koopman Operator Learning
Vladimir R Kostic, Karim Lounici, Pietro Novelli, 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 RRR instead of PCR with the bad kernel | Koopman eigenvalue estimation · Ornstein-Uhlenbeck, bad kernel | eigenvalue estimate concentration | Improved |
| use the bad kernel with PCR | PCR estimator · Ornstein-Uhlenbeck | eigenvalue estimate concentration | Hurt |
| use the ugly kernel with large singular value ratio | PCR and RRR · Ornstein-Uhlenbeck | eigenvalue estimate concentration | Hurt |
| use RRR instead of PCR for eigenfunctions | Koopman estimator · Langevin dynamics | eigenfunction estimation error | Improved |
| select kernel by smallest empirical spectral bias | RRR estimators · Alanine Dipeptide | forecasting RMSE | Improved |
Closest papers by meaning
- ResKoopNet: Learning Koopman Representations for Complex Dynamics with Spectral Residuals (ICML 2025 · similarity 0.90)
- Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems (NeurIPS 2025 · similarity 0.89)
- Deep-Koopman-KANDy: Dictionary Discovery for Deep-Koopman Operators with Kolmogorov-Arnold Networks for Dynamics (NeurIPS 2026 · similarity 0.88)
- From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach (NeurIPS 2024 · similarity 0.87)
- Finding Koopman Invariant Subspaces via Personalized PageRank (NeurIPS 2026 · similarity 0.86)
- Revisiting Orbital Minimization Method for Neural Operator Decomposition (NeurIPS 2025 · similarity 0.86)
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.
