English
Related papers

Related papers: Beyond Data Scarcity: A Frequency-Driven Framework…

200 papers

In applications of dynamical systems, situations can arise where it is desired to predict the onset of synchronization as it can lead to characteristic and significant changes in the system performance and behaviors, for better or worse. In…

Adaptation and Self-Organizing Systems · Physics 2021-06-30 Huawei Fan , Ling-Wei Kong , Ying-Cheng Lai , Xingang Wang

Recent research on time-series foundation models (TSFMs) has underscored the scarcity of real-world data, often supplemented with synthetic sources in existing datasets, whose generalizability remains however debated. As such, in this work,…

Artificial Intelligence · Computer Science 2025-12-01 Lujun Li , Lama Sleem , Yiqun Wang , Yangjie Xu , Niccolò Gentile , Radu State

While machine learning has emerged in recent years as a useful tool for rapid prediction of materials properties, generating sufficient data to reliably train models without overfitting is still impractical for many applications. Towards…

Materials Science · Physics 2022-07-29 Rees Chang , Yu-Xiong Wang , Elif Ertekin

Learning complex time series forecasting models usually requires a large amount of data, as each model is trained from scratch for each task/data set. Leveraging learning experience with similar datasets is a well-established technique for…

Machine Learning · Computer Science 2022-08-19 Lukas Brinkmeyer , Rafael Rego Drumond , Johannes Burchert , Lars Schmidt-Thieme

This paper addresses the challenge of overfitting in the learning of dynamical systems by introducing a novel approach for the generation of synthetic data, aimed at enhancing model generalization and robustness in scenarios characterized…

Machine Learning · Computer Science 2024-03-11 Dario Piga , Matteo Rufolo , Gabriele Maroni , Manas Mejari , Marco Forgione

Time series forecasting models have diverse real world applications (e.g., from electricity metrics to software workload). Latest foundational models trained for time series forecasting show strengths (e.g., for long sequences and in…

Machine Learning · Computer Science 2025-07-03 Keun Soo Yim

Time series foundation models (TSFMs) have recently gained significant attention due to their strong zero-shot capabilities and widespread real-world applications. Such models typically require a computationally costly pre-training on…

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 foundation models in…

Machine Learning · Computer Science 2026-02-20 Xinghong Fu , Yanhong Li , Georgios Papaioannou , Yoon Kim

Time series foundation models (FMs) have emerged as a popular paradigm for zero-shot multi-domain forecasting. These models are trained on numerous diverse datasets and claim to be effective forecasters across multiple different time series…

Risk Management · Quantitative Finance 2025-05-19 Anubha Goel , Puneet Pasricha , Martin Magris , Juho Kanniainen

The Transformer model has shown leading performance in time series forecasting. Nevertheless, in some complex scenarios, it tends to learn low-frequency features in the data and overlook high-frequency features, showing a frequency bias.…

Machine Learning · Computer Science 2024-07-04 Xihao Piao , Zheng Chen , Taichi Murayama , Yasuko Matsubara , Yasushi Sakurai

A time series represents a set of observations collected over time. Typically, these observations are captured with a uniform sampling frequency (e.g. daily). When data points are observed in uneven time intervals the time series is…

Machine Learning · Computer Science 2022-01-03 Pedro Costa , Vitor Cerqueira , João Vinagre

Synthetic datasets are a crucial ingredient for training stereo matching networks, but the question of what makes a stereo dataset effective remains underexplored. We investigate the design space of synthetic datasets by varying the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 David Yan , Alexander Raistrick , Jia Deng

We study, from an empirical standpoint, the efficacy of synthetic data in real-world scenarios. Leveraging synthetic data for training perception models has become a key strategy embraced by the community due to its efficiency, scalability,…

Machine Learning · Computer Science 2024-03-26 Che-Jui Chang , Danrui Li , Seonghyeon Moon , Mubbasir Kapadia

In recent years, deep learning models have resulted in a huge amount of progress in various areas, including computer vision. By nature, the supervised training of deep models requires a large amount of data to be available. This ideal case…

Computer Vision and Pattern Recognition · Computer Science 2019-07-17 Farzan Erlik Nowruzi , Prince Kapoor , Dhanvin Kolhatkar , Fahed Al Hassanat , Robert Laganiere , Julien Rebut

The rapid advancement of generative models, such as Stable Diffusion, raises a key question: how can synthetic data from these models enhance predictive modeling? While they can generate vast amounts of datasets, only a subset meaningfully…

Machine Learning · Statistics 2025-05-09 Jialong Jiang , Wenkang Hu , Jian Huang , Yuling Jiao , Xu Liu

Going beyond correlations, the understanding and identification of causal relationships in observational time series, an important subfield of Causal Discovery, poses a major challenge. The lack of access to a well-defined ground truth for…

Machine Learning · Statistics 2021-04-19 Andrew R. Lawrence , Marcus Kaiser , Rui Sampaio , Maksim Sipos

Synthetic data has transformed language model training, yet its role in time series forecasting remains poorly understood. We present a large-scale empirical study: nine experiment groups, 4,218 runs systematically evaluating synthetic time…

Machine Learning · Computer Science 2026-05-08 Hugo Cazaux , Eyjólfur Ingi Ásgeirsson , Hlynur Stefánsson

Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks frequently suffer from a simplicity-biased learning behavior…

Machine Learning · Computer Science 2024-10-22 Xilin He , Jingyu Hu , Qinliang Lin , Cheng Luo , Weicheng Xie , Siyang Song , Muhammad Haris Khan , Linlin Shen

Deep learning approaches are increasingly used to tackle forecasting tasks involving datasets with multiple univariate time series. A key factor in the successful application of these methods is a large enough training sample size, which is…

Machine Learning · Computer Science 2025-01-06 Vitor Cerqueira , Moisés Santos , Luis Roque , Yassine Baghoussi , Carlos Soares

Foundation models for zero-shot time series forecasting face challenges in efficient long-horizon prediction and reproducibility, with existing synthetic-only approaches underperforming on challenging benchmarks. This paper presents…

Machine Learning · Computer Science 2026-02-06 Vladyslav Moroshan , Julien Siems , Arber Zela , Timur Carstensen , Frank Hutter