クープマン表現の軌道修正
Course Correcting Koopman Representations
非線形力学系を潜在空間で線形化するクープマン表現の自己符号化器モデルを検討し、長期予測の課題を明らかにして周期的再符号化という推論時手法を提案した。
著者: Mahan Fathi, Clement Gehring, Jonathan Pilault, David Kanaa, Pierre-Luc Bacon, Ross Goroshin
分類: cs.LG, cs.AI, cs.RO, cs.SY, eess.SY
原文アブストラクト
Koopman representations aim to learn features of nonlinear dynamical systems (NLDS) which lead to linear dynamics in the latent space. Theoretically, such features can be used to simplify many problems in modeling and control of NLDS. In this work we study autoencoder formulations of this problem, and different ways they can be used to model dynamics, specifically for future state prediction over long horizons. We discover several limitations of predicting future states in the latent space and propose an inference-time mechanism, which we refer to as Periodic Reencoding, for faithfully capturing long term dynamics. We justify this method both analytically and empirically via experiments in low and high dimensional NLDS.
