Meta-learning and Data Augmentation for Stress Testing Forecasting Models

2024-06-24 · Ricardo Inácio, Vitor Cerqueira, Marília Barandas, Carlos Soares

The effectiveness of univariate forecasting models is often hampered by conditions that cause them stress. A model is considered to be under stress if it shows a negative behaviour, such as higher-than-usual errors or increased uncertainty. Understanding the factors that cause stress to forecasting models is important to improve their reliability, transparency, and utility. This paper addresses this problem by contributing with a novel framework called MAST (Meta-learning and data Augmentation for Stress Testing). The proposed approach aims to model and characterize stress in univariate time series forecasting models, focusing on conditions where they exhibit large errors. In particular, MAST is a meta-learning approach that predicts the probability that a given model will perform poorly on a given time series based on a set of statistical time series features. MAST also encompasses a novel data augmentation technique based on oversampling to improve the metadata concerning stress. We conducted experiments using three benchmark datasets that contain a total of 49.794 time series to validate the performance of MAST. The results suggest that the proposed approach is able to identify conditions that lead to large errors. The method and experiments are publicly available in a repository.

📄 PDF Abstract BibTeX arXiv:2406.17008

Code (1)

ricardoinaciopt/mast 공식 구현

Tasks

Data Augmentation Meta-LearningTime SeriesTime Series Forecasting Univariate Time Series Forecasting

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Stress-testing medical large language models reveals latent safety pathology beyond benchmark accuracy

2026-06-06 · Yuan Shen, Xiaojun Wu, Linghua Yu arxiv

Large language models (LLMs) are entering clinical practice based on benchmark accuracy that may fail to detect safety-relevant failure modes. Here we present AI-MASLD, a stress-audit framework that adapts the logic of m…

Information Extraction

Conditional Method Confidence Set

2025-05-27 · Lukas Bauer, Ekaterina Kazak

This paper proposes a Conditional Method Confidence Set (CMCS) which allows to select the best subset of forecasting methods with equal predictive ability conditional on a specific economic regime. The test resembles the…

Forecasting Market Prices using DL with Data Augmentation and Meta-learning: ARIMA still wins!

2021-10-19 · NeurIPS Workshop ICBINB 2021 12 · Vedant Shah, Gautam Shroff

Deep-learning techniques have been successfully used for time-series forecasting and have often shown superior performance on many standard benchmark datasets as compared to traditional techniques. Here we present a comp…

Data Augmentation Deep Learning Meta-Learning Time Series+2

Stress Testing of Meta-learning Approaches for Few-shot Learning

2021-01-21 · Aroof Aimen, Sahil Sidheekh, Vineet Madan, Narayanan C. Krishnan

Meta-learning (ML) has emerged as a promising learning method under resource constraints such as few-shot learning. ML approaches typically propose a methodology to learn generalizable models. In this work-in-progress pa…

Few-Shot Learning Meta-Learning

A Physics-Informed, Behavior-Aware Digital Twin for Robust Multimodal Forecasting of Core Body Temperature in Precision Livestock Farming

2026-04-05 · Riasad Alvi, Mohaimenul Azam Khan Raiaan, Sadia Sultana Chowa, Arefin Ittesafun Abian 외 arxiv

Precision livestock farming requires accurate and timely heat stress prediction to ensure animal welfare and optimize farm management. This study presents a physics-informed digital twin (DT) framework combined with an u…

Feature Engineering