paper-with-me

홈 › Papers

Test Time Learning for Time Series Forecasting

2024-09-21 · Panayiotis Christou, Shichu Chen, Xupeng Chen, Parijat Dube

Time-series forecasting has seen significant advancements with the introduction of token prediction mechanisms such as multi-head attention. However, these methods often struggle to achieve the same performance as in language modeling, primarily due to the quadratic computational cost and the complexity of capturing long-range dependencies in time-series data. State-space models (SSMs), such as Mamba, have shown promise in addressing these challenges by offering efficient solutions with linear RNNs capable of modeling long sequences with larger context windows. However, there remains room for improvement in accuracy and scalability. We propose the use of Test-Time Training (TTT) modules in a parallel architecture to enhance performance in long-term time series forecasting. Through extensive experiments on standard benchmark datasets, we demonstrate that TTT modules consistently outperform state-of-the-art models, including the Mamba-based TimeMachine, particularly in scenarios involving extended sequence and prediction lengths. Our results show significant improvements in Mean Squared Error (MSE) and Mean Absolute Error (MAE), especially on larger datasets such as Electricity, Traffic, and Weather, underscoring the effectiveness of TTT in capturing long-range dependencies. Additionally, we explore various convolutional architectures within the TTT framework, showing that even simple configurations like 1D convolution with small filters can achieve competitive results. This work sets a new benchmark for time-series forecasting and lays the groundwork for future research in scalable, high-performance forecasting models.

📄 PDF Abstract BibTeX arXiv:2409.14012

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMambaState Space ModelsTime SeriesTime Series Forecasting

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Mamba Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.…

Similar Papers 제목 키워드 기반

TimeGym: Debugging for Time Series Modeling in Python

2021-05-04 · Diogo Seca

We introduce the TimeGym Forecasting Debugging Toolkit, a Python library for testing and debugging time series forecasting pipelines. TimeGym simplifies the testing forecasting pipeline by providing generic tests for for…

test driven developmentTime SeriesTime Series AnalysisTime Series Forecasting

Few-shot Learning for Time-series Forecasting

2020-09-30 · Tomoharu Iwata, Atsutoshi Kumagai

Time-series forecasting is important for many applications. Forecasting models are usually trained using time-series data in a specific target task. However, sufficient data in the target task might be unavailable, which…

Few-Shot LearningTime SeriesTime Series AnalysisTime Series Forecasting

Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series

2022-02-04 · Sercan O. Arik, Nathanael C. Yoder, Tomas Pfister

Real-world time-series datasets often violate the assumptions of standard supervised learning for forecasting -- their distributions evolve over time, rendering the conventional training and model selection procedures su…

DecoderModel SelectionSelf-Supervised LearningTime Series+2

Empowering Time Series Forecasting with LLM-Agents

2025-08-06 · Chin-Chia Michael Yeh, Vivian Lai, Uday Singh Saini, Xiran Fan 외 arxiv

Large Language Model (LLM) powered agents have emerged as effective planners for Automated Machine Learning (AutoML) systems. While most existing AutoML approaches focus on automating feature engineering and model archit…

Time Series ForecastingFeature Engineering

Correlated daily time series and forecasting in the M4 competition

2020-03-28 · Anti Ingel, Novin Shahroudi, Markus Kängsepp, Andre Tättar 외

We participated in the M4 competition for time series forecasting and describe here our methods for forecasting daily time series. We used an ensemble of five statistical forecasting methods and a method that we refer to…

Time SeriesTime Series AnalysisTime Series Forecasting