On the interplay between learning and memory in deep state space models
Keywords: state space models, long-term dependencies, sequence modeling, linear time-invariant systems, theory, memory
Abstract: Deep state-space models (SSMs) have emerged as a powerful deep learning architecture for sequence modeling, but the theory of how these models learn long-term dependencies lags the practice. To explain how parameterization and the number of layers affect a model's expressiveness, we study the properties of deep $\textit{linear}$ SSMs, i.e., linearly coupled stacks of linear time-invariant systems. We show that such systems share timescales across layers, and we provide novel analysis on the role of linear feedforward connections in regularizing these temporal dependencies. In practice, SSMs can struggle with an explosion of the hidden state variance when learning long-term dependencies. We expand our theoretical understanding of this problem for deep SSMs and provide new intuitions on how this problem may be resolved by increasing the number of layers. Finally, we confirm our theoretical results in a teacher-student framework and show the effects of model parameterization on learning convergence.
Primary Area: learning on time series and dynamical systems
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 13020
Loading