paper-with-me

홈 › Papers

Enhancing Transformer-Based Foundation Models for Time Series Forecasting via Bagging, Boosting and Statistical Ensembles

2025-08-18 · Dhruv D. Modi, Rong Pan arxiv

Time series foundation models (TSFMs) such as Lag-Llama, TimeGPT, Chronos, MOMENT, UniTS, and TimesFM have shown strong generalization and zero-shot capabilities for time series forecasting, anomaly detection, classification, and imputation. Despite these advantages, their predictions still suffer from variance, domain-specific bias, and limited uncertainty quantification when deployed on real operational data. This paper investigates a suite of statistical and ensemble-based enhancement techniques, including bootstrap-based bagging, regression-based stacking, prediction interval construction, statistical residual modeling, and iterative error feedback, to improve robustness and accuracy. Using the Belgium Electricity Short-Term Load Forecasting dataset as a case study, we demonstrate that the proposed hybrids consistently outperform standalone foundation models across multiple horizons. Regression-based ensembles achieve the lowest mean squared error; bootstrap aggregation markedly reduces long-context errors; residual modeling corrects systematic bias; and the resulting prediction intervals achieve near nominal coverage with widths shrinking as context length increases. The results indicate that integrating statistical reasoning with modern foundation models yields measurable gains in accuracy, reliability, and interpretability for real-world time series applications.

📄 PDF Abstract BibTeX arXiv:2508.16641

Code (0)

등록된 구현이 없습니다.

Tasks

Time Series ForecastingAnomaly Detection

Similar Papers 제목 키워드 기반

QKCV Attention: Enhancing Time Series Forecasting with Static Categorical Embeddings for Both Lightweight and Pre-trained Foundation Models

2025-10-21 · Hao Wang, Baojun Ma arxiv

In real-world time series forecasting tasks, category information plays a pivotal role in capturing inherent data patterns. This paper introduces QKCV (Query-Key-Category-Value) attention, an extension of the traditional…

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 ForecastingData Augmentation

Toto: Time Series Optimized Transformer for Observability

2024-07-10 · Ben Cohen, Emaad Khwaja, Kan Wang, Charles Masson 외

This technical report describes the Time Series Optimized Transformer for Observability (Toto), a new state of the art foundation model for time series forecasting developed by Datadog. In addition to advancing the state…

Time SeriesTime Series Forecasting

TimeFound: A Foundation Model for Time Series Forecasting

2025-03-06 · Congxi Xiao, Jingbo Zhou, Yixiong Xiao, Xinjiang Lu 외

We present TimeFound, an encoder-decoder transformer-based time series foundation model for out-of-the-box zero-shot forecasting. To handle time series data from various domains, TimeFound employs a multi-resolution patc…

DecoderTime SeriesTime Series Forecasting

Unify and Anchor: A Context-Aware Transformer for Cross-Domain Time Series Forecasting

2025-03-03 · Xiaobin Hong, Jiawen Zhang, Wenzhong Li, Sanglu Lu 외

The rise of foundation models has revolutionized natural language processing and computer vision, yet their best practices to time series forecasting remains underexplored. Existing time series foundation models often ad…

Domain GeneralizationMixture-of-ExpertsTime SeriesTime Series Forecasting