AI Paper Atlas

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

NeurIPS 2022 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel regression under shift · 16 citations (OpenAlex)

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 changedWhereMeasuredEffect
use reduced-rank regression (RRR) instead of principal component regression (PCR)rank-3 Koopman estimator · Noisy logistic maptest error: 0.18 -> 0.13Improved
use RRR instead of PCRrank-3 Koopman estimator · Noisy logistic mapeigenvalue lambda_2,3 relative error: 0.85 -> 0.16Improved
use RRR instead of KRRKoopman estimator · Noisy logistic maptest error: 0.13 -> 0.13No clear effect
use RRR instead of KRRKoopman estimator · Noisy logistic maptraining error: 0.032 -> 0.13Hurt
use RRR instead of KRRKoopman estimator · Noisy logistic mapeigenvalue lambda_2,3 relative error: 0.48 -> 0.16Improved
use RRR instead of KRRKoopman estimator · Noisy logistic mapeigenvalue 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 RRRrank-10 RRR · MNIST digit sequence forecastingforecast quality (qualitative)Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy