Browsing by Author "Fortgang, Shlomo T."
Now showing 1 - 1 of 1
- Results Per Page
- Sort Options
SpectraLDS: Distilling Spectral Filters into Constant-Time Recurrent Models
(2025-04-10) Fortgang, Shlomo T.; Hazan, EladWe introduce the first provable method for learning a symmetric linear dynamical system of arbitrarily high effective memory. This allows us to distill the convolutional layers in a leading hybrid state space model, FlashSTU, into O(1) linear dynamical systems, merging Transformer and RNN architectures in a manner suitable for scaling and with application to language modeling and other sequential processing tasks.