动力学感知的过去-未来信息瓶颈
Dynamics Aware Past-Future Information Bottleneck
Wooyoung Chung, Stas Tiomkin
AI 速读 基于摘要
作者提出将PF-IB目标约束在分块Hankel矩阵构成的李群流形上，使压缩后的线性动力系统表示具备可实现性，从而可直接用于估计与控制。
cs.IT · eess.SY
查看原文摘要
The simplification of complex dynamical systems is essential for efficient estimation and control. A principled approach to this task is through the lens of information-theoretic compression. The Past-Future Information Bottleneck (PF-IB) provides a theoretical framework for compressing linear dynamical systems. However, the standard formulation often lacks structural consistency, yielding representations that are not realizable as dynamical systems. By constraining the objective to a specific manifold of block Hankel matrices, which we prove is a Lie group, we bridge the gap between PF-IB and realization theory. Our approach ensures that the resulting compressed dynamics are realizable, thereby enabling its direct application to estimation and control. We demonstrate our approach in numerical simulations.