Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models

2024-10-12 · Sathya Kamesh Bhethanabhotla, Omar Swelam, Julien Siems, David Salinas, Frank Hutter

This paper introduces Mamba4Cast, a zero-shot foundation model for time series forecasting. Based on the Mamba architecture and inspired by Prior-data Fitted Networks (PFNs), Mamba4Cast generalizes robustly across diverse time series tasks without the need for dataset specific fine-tuning. Mamba4Cast's key innovation lies in its ability to achieve strong zero-shot performance on real-world datasets while having much lower inference times than time series foundation models based on the transformer architecture. Trained solely on synthetic data, the model generates forecasts for entire horizons in a single pass, outpacing traditional auto-regressive approaches. Our experiments show that Mamba4Cast performs competitively against other state-of-the-art foundation models in various data sets while scaling significantly better with the prediction length. The source code can be accessed at https://github.com/automl/Mamba4Cast.

📄 PDF Abstract BibTeX arXiv:2410.09385

Code (1)

automl/mamba4cast 공식 구현 pytorch

Tasks

AutoMLMambaState Space ModelsTime SeriesTime Series Forecasting

Methods 이 논문이 사용한 방법론

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.…

A Mamba Foundation Model for Time Series Forecasting

2024-11-05 · Haoyu Ma, Yushu Chen, Wenlai Zhao, Jinzhe Yang 외

Time series foundation models have demonstrated strong performance in zero-shot learning, making them well-suited for predicting rapidly evolving patterns in real-world applications where relevant training data are scarc…

Mamba model Prediction Time Series+3

Mamba time series forecasting with uncertainty quantification

2025-03-13 · Pedro Pessoa, Paul Campitelli, Douglas P. Shepherd, S. Banu Ozkan 외

State space models, such as Mamba, have recently garnered attention in time series forecasting due to their ability to capture sequence patterns. However, in electricity consumption benchmarks, Mamba forecasts exhibit a …

Mamba Probabilistic Time Series Forecasting State Space Models Time Series+2

Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction

2024-02-12 · Cheng Feng, Long Huang, Denis Krompass

We present General Time Transformer (GTT), an encoder-only style foundation model for zero-shot multivariate time series forecasting. GTT is pretrained on a large dataset of 200M high-quality time series samples spanning…

Multivariate Time Series Forecasting Time Series Time Series Forecasting

SeqFusion: Sequential Fusion of Pre-Trained Models for Zero-Shot Time-Series Forecasting

2025-03-04 · Ting-Ji Huang, Xu-Yang Chen, Han-Jia Ye

Unlike traditional time-series forecasting methods that require extensive in-task data for training, zero-shot forecasting can directly predict future values given a target time series without additional training data. C…

Time Series Time Series Forecasting

Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting

2026-02-19 · Xinghong Fu, Yanhong Li, Georgios Papaioannou, Yoon Kim arxiv

Learning time series foundation models has been shown to be a promising approach for zero-shot time series forecasting across diverse time series domains. Insofar as scaling has been a critical driver of performance of f…

Time Series Forecasting Data Augmentation