paper-with-me

홈 › Papers

Numerical Analysis of HiPPO-LegS ODE for Deep State Space Models

2024-12-11 · Jaesung R. Park, Jaewook J. Suh, Youngjoon Hong, Ernest K. Ryu

In deep learning, the recently introduced state space models utilize HiPPO (High-order Polynomial Projection Operators) memory units to approximate continuous-time trajectories of input functions using ordinary differential equations (ODEs), and these techniques have shown empirical success in capturing long-range dependencies in long input sequences. However, the mathematical foundations of these ODEs, particularly the singular HiPPO-LegS (Legendre Scaled) ODE, and their corresponding numerical discretizations remain unsettled. In this work, we fill this gap by establishing that HiPPO-LegS ODE is well-posed despite its singularity, albeit without the freedom of arbitrary initial conditions. Further, we establish convergence of the associated numerical discretization schemes for Riemann integrable input functions.

📄 PDF Abstract BibTeX arXiv:2412.08595

Code (0)

등록된 구현이 없습니다.

Tasks

State Space Models

Similar Papers 제목 키워드 기반

HiPPO: Recurrent Memory with Optimal Polynomial Projections

2020-08-17 · NeurIPS 2020 12 · Albert Gu, Tri Dao, Stefano Ermon, Atri Rudra 외

A central problem in learning from sequential data is representing cumulative history in an incremental fashion as more data is processed. We introduce a general framework (HiPPO) for the online compression of continuous…

Permuted-MNISTSequential Image ClassificationTime SeriesTime Series Analysis

UnHiPPO: Uncertainty-aware Initialization for State Space Models

2025-06-05 · Marten Lienen, Abdullah Saydemir, Stephan Günnemann

State space models are emerging as a dominant model class for sequence problems with many relying on the HiPPO framework to initialize their dynamics. However, HiPPO fundamentally assumes data to be noise-free; an assump…

State Space Models

Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Models

2020-05-02 · EMNLP 2020 11 · Bill Yuchen Lin, Seyeon Lee, Rahul Khanna, Xiang Ren

Recent works show that pre-trained language models (PTLMs), such as BERT, possess certain commonsense and factual knowledge. They suggest that it is promising to use PTLMs as "neural knowledge bases" via predicting maske…

Diagnostic

A Coupled Neural Field Model for the Standard Consolidation Theory

2024-04-03 · Lisa Blum Moyse, Hugues Berry

The standard consolidation theory states that short-term memories located in the hippocampus enable the consolidation of long-term memories in the neocortex. In other words, the neocortex slowly learns long-term memories…

HippocampusRetrieval

LegSegNet: A Public Deep Learning System for Lower Extremity CT Tissue Segmentation and Quantification

2026-05-29 · Yuwen Chen, Yaqian Chen, Roy Colglazier, Haoyu Dong 외 arxiv

Lower extremity computed tomography (CT) contains clinically relevant information for body composition analysis, sarcopenia assessment, and musculoskeletal disease monitoring, but extracting these measurements at scale r…