WaLRUS: Wavelets for Long-range Representation Using SSMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Babaei, Hossein, White, Mel, Alemohammad, Sina, Baraniuk, Richard G.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909614902083584
author Babaei, Hossein
White, Mel
Alemohammad, Sina
Baraniuk, Richard G.
author_facet Babaei, Hossein
White, Mel
Alemohammad, Sina
Baraniuk, Richard G.
contents State-Space Models (SSMs) have proven to be powerful tools for modeling long-range dependencies in sequential data. While the recent method known as HiPPO has demonstrated strong performance, and formed the basis for machine learning models S4 and Mamba, it remains limited by its reliance on closed-form solutions for a few specific, well-behaved bases. The SaFARi framework generalized this approach, enabling the construction of SSMs from arbitrary frames, including non-orthogonal and redundant ones, thus allowing an infinite diversity of possible "species" within the SSM family. In this paper, we introduce WaLRUS (Wavelets for Long-range Representation Using SSMs), a new implementation of SaFARi built from Daubechies wavelets.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12161
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WaLRUS: Wavelets for Long-range Representation Using SSMs
Babaei, Hossein
White, Mel
Alemohammad, Sina
Baraniuk, Richard G.
Image and Video Processing
Machine Learning
Systems and Control
Audio and Speech Processing
Signal Processing
State-Space Models (SSMs) have proven to be powerful tools for modeling long-range dependencies in sequential data. While the recent method known as HiPPO has demonstrated strong performance, and formed the basis for machine learning models S4 and Mamba, it remains limited by its reliance on closed-form solutions for a few specific, well-behaved bases. The SaFARi framework generalized this approach, enabling the construction of SSMs from arbitrary frames, including non-orthogonal and redundant ones, thus allowing an infinite diversity of possible "species" within the SSM family. In this paper, we introduce WaLRUS (Wavelets for Long-range Representation Using SSMs), a new implementation of SaFARi built from Daubechies wavelets.
title WaLRUS: Wavelets for Long-range Representation Using SSMs
topic Image and Video Processing
Machine Learning
Systems and Control
Audio and Speech Processing
Signal Processing
url https://arxiv.org/abs/2505.12161