Pith. sign in

REVIEW 2 cited by

Spectral State Space Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.06837 v4 pith:R74JRSKX submitted 2023-12-11 cs.LG

classification cs.LG
keywords modelsspectralspacestatepredictiontasksdynamicalfiltering
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper studies sequence modeling for prediction tasks with long range dependencies. We propose a new formulation for state space models (SSMs) based on learning linear dynamical systems with the spectral filtering algorithm (Hazan et al. (2017)). This gives rise to a novel sequence prediction architecture we call a spectral state space model. Spectral state space models have two primary advantages. First, they have provable robustness properties as their performance depends on neither the spectrum of the underlying dynamics nor the dimensionality of the problem. Second, these models are constructed with fixed convolutional filters that do not require learning while still outperforming SSMs in both theory and practice. The resulting models are evaluated on synthetic dynamical systems and long-range prediction tasks of various modalities. These evaluations support the theoretical benefits of spectral filtering for tasks requiring very long range memory.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SFO: Learning PDE Operators via Spectral Filtering

    cs.LG 2026-01 conditional novelty 6.0 of 10

    A neural operator that expands PDE kernels in fixed Hilbert-matrix eigenmodes achieves state-of-the-art benchmark accuracy with substantially fewer parameters.

  2. A Spectral Filtering Approach to Regret Analysis of Distributed Online Control for Linear Dynamical Systems

    math.OC 2026-08 conditional novelty 5.0 of 10

    A distributed spectral-filter controller is claimed to achieve O~(n^{3/2} sqrt(T)/((1-beta) gamma^3)) individual regret for networked LTI systems with adversarial disturbances and convex costs.

Pith tools