SOURCE-LINKED INTELLIGENCE

Sparse Koopman Autoencoders Identify Local Dynamical Regimes in Multibasin Systems

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Koopman autoencoders (KAEs) seek a higher-dimensional latent representation in which nonlinear dynamics evolve linearly. However, many interesting systems have multiple basins of attraction, and both theoretical and empirical work has shown these multibasin systems cannot generally admit a single finite-dimensional global Koopman embedding under standard assumptions. We posit that encoders with a sparsity-inducing objective encouraging few active latent coefficients will provide latent supports as an inspectable basin-modeling principle for Koopman autoencoders. We use these encoders producing

Read original source ↗ Open in workspace

recordType

paper

region

Global