The reviewed record of science sign in
Pith

arxiv: 2505.17868 · v2 · pith:XNXKLTKU · submitted 2025-05-23 · cs.LG · math.OC

SpectraLDS: Provable Distillation for Linear Dynamical Systems

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:XNXKLTKUrecord.jsonopen to challenge →

classification cs.LG math.OC
keywords accuracysystemsdistillationdynamicalindependentinferencelinearmethod
0
0 comments X
read the original abstract

We present the first provable method for identifying symmetric linear dynamical systems (LDS) with accuracy guarantees that are independent of the systems' state dimension or effective memory. Our approach builds upon recent work that represents symmetric LDSs as convolutions learnable via fixed spectral transformations. We show how to invert this representation, thereby recovering an LDS model from its spectral transform and yielding an end-to-end convex optimization procedure. This distillation preserves predictive accuracy while enabling constant-time and constant-space inference per token, independent of sequence length. We evaluate our method, SpectraLDS, as a component in sequence prediction architectures and demonstrate that accuracy is preserved while inference efficiency is improved on tasks such as language modeling.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.