Research map / Learning theory and algorithms / Kernels and regression theory
Estimating Koopman operators with sketching to provably learn large scale dynamical systems
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 exact PCR with Nystrom NysPCR (250 inducing points) | PCR Koopman estimator · Lorenz '63, increasing n | nRMSE | No clear effect |
| replace exact RRR with Nystrom NysRRR (250 inducing points) | RRR Koopman estimator · Lorenz '63, increasing n | nRMSE | No clear effect |
| replace exact estimators with Nystrom estimators as n grows | PCR/RRR · Lorenz '63, increasing n | running time | Helped |
| replace sKAF with NysPCR | PCR · Lorenz '63, forecast horizons | running time: approximately 10 times faster | Helped |
| replace sKAF with NysPCR | PCR · Lorenz '63, forecast horizons | nRMSE | No clear effect |
| use NysRRR instead of NysPCR | Nystrom estimators · Lorenz '63, forecast horizons | nRMSE vs running time | Mixed |
Closest papers by meaning
- Deep-Koopman-KANDy: Dictionary Discovery for Deep-Koopman Operators with Kolmogorov-Arnold Networks for Dynamics (NeurIPS 2026 · similarity 0.88)
- Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems (NeurIPS 2025 · similarity 0.88)
- ResKoopNet: Learning Koopman Representations for Complex Dynamics with Spectral Residuals (ICML 2025 · similarity 0.88)
- KoopSTD: Reliable Similarity Analysis between Dynamical Systems via Approximating Koopman Spectrum with Timescale Decoupling (ICML 2025 · similarity 0.85)
- Finding Koopman Invariant Subspaces via Personalized PageRank (NeurIPS 2026 · similarity 0.85)
- SKOLR: Structured Koopman Operator Linear RNN for Time-Series Forecasting (ICML 2025 · similarity 0.84)
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.