paper-with-me

홈 › Papers

Improved Batching Strategy For Irregular Time-Series ODE

2022-07-12 · Ting Fung Lam, Yony Bresler, Ahmed Khorshid, Nathan Perlmutter

Irregular time series data are prevalent in the real world and are challenging to model with a simple recurrent neural network (RNN). Hence, a model that combines the use of ordinary differential equations (ODE) and RNN was proposed (ODE-RNN) to model irregular time series with higher accuracy, but it suffers from high computational costs. In this paper, we propose an improvement in the runtime on ODE-RNNs by using a different efficient batching strategy. Our experiments show that the new models reduce the runtime of ODE-RNN significantly ranging from 2 times up to 49 times depending on the irregularity of the data while maintaining comparable accuracy. Hence, our model can scale favorably for modeling larger irregular data sets.

📄 PDF Abstract BibTeX arXiv:2207.05708

Code (0)

등록된 구현이 없습니다.

Tasks

Irregular Time SeriesTime SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

Static Batching of Irregular Workloads on GPUs: Framework and Application to Efficient MoE Model Inference

2025-01-27 · Yinghan Li, Yifei Li, Jiejing Zhang, Bujiao Chen 외

It has long been a problem to arrange and execute irregular workloads on massively parallel devices. We propose a general framework for statically batching irregular workloads into a single kernel with a runtime task map…

GPUMixture-of-Experts

Rethinking Large Language Models For Irregular Time Series Classification In Critical Care

2026-01-23 · Feixiang Zheng, Yu Wu, Cecilia Mascolo, Ting Dang arxiv

Time series data from the Intensive Care Unit (ICU) provides critical information for patient monitoring. While recent advancements in applying Large Language Models (LLMs) to time series modeling (TSM) have shown great …

Time Series ClassificationFew-Shot Learning

PAITS: Pretraining and Augmentation for Irregularly-Sampled Time Series

2023-08-25 · Nicasia Beebe-Wang, Sayna Ebrahimi, Jinsung Yoon, Sercan O. Arik 외

Real-world time series data that commonly reflect sequential human behavior are often uniquely irregularly sampled and sparse, with highly nonuniform sampling over time and entities. Yet, commonly-used pretraining and au…

Time Series

Continuous Time Evidential Distributions for Irregular Time Series

2023-07-25 · Taylor W. Killian, Haoran Zhang, Thomas Hartvigsen, Ava P. Amini

Prevalent in many real-world settings such as healthcare, irregular time series are challenging to formulate predictions from. It is difficult to infer the value of a feature at any given time when observations are spora…

Irregular Time SeriesTime SeriesTime Series Classification

VariViT: A Vision Transformer for Variable Image Sizes

2026-02-16 · Aswathi Varma, Suprosanna Shit, Chinmay Prabhakar, Daniel Scholz 외 arxiv

Vision Transformers (ViTs) have emerged as the state-of-the-art architecture in representation learning, leveraging self-attention mechanisms to excel in various tasks. ViTs split images into fixed-size patches, constrai…

Brain Tumor ClassificationRepresentation Learning