PulseAugur
LIVE 14:45:37
research · [3 sources] ·
0
research

Deep learning time series research explores synthetic data, benchmarks, and accuracy laws

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 3 sources

Two new arXiv papers explore advancements in deep learning for time series analysis. The first paper provides a comprehensive survey of deep time series models, introducing a benchmark library called TSLib that implements 41 models and supports 5 analysis tasks. The second paper empirically studies an "accuracy law" for deep time series forecasters, discovering a relationship between model error and the complexity of window-wise series patterns, and proposes a new training strategy. AI

Summary written by gemini-2.5-flash-lite from 3 sources. How we write summaries →

IMPACT These papers offer new benchmarks and insights into the performance limitations and training strategies for deep learning models applied to time series data.

RANK_REASON Two arXiv papers present new research and benchmarks in deep time series modeling and forecasting.

Read on arXiv cs.LG →

COVERAGE [3]

  1. arXiv cs.LG TIER_1 · Hugo Cazaux, Eyj\'olfur Ingi \'Asgeirsson, Hlynur Stef\'ansson ·

    Does Synthetic Data Help? Empirical Evidence from Deep Learning Time Series Forecasters

    arXiv:2605.06032v1 Announce Type: new Abstract: 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 synthe…

  2. arXiv cs.LG TIER_1 · Yuxuan Wang, Haixu Wu, Jiaxiang Dong, Yong Liu, Chen Wang, Mingsheng Long, Jianmin Wang ·

    Deep Time Series Models: A Comprehensive Survey and Benchmark

    arXiv:2407.13278v3 Announce Type: replace Abstract: Time series, characterized by a sequence of data points organized in a discrete-time order, are ubiquitous in real-world scenarios. Unlike other data modalities, time series present unique challenges in learning and modeling due…

  3. arXiv cs.LG TIER_1 · Yuxuan Wang, Haixu Wu, Yuezhou Ma, Yuchen Fang, Ziyi Zhang, Yong Liu, Shiyu Wang, Zhou Ye, Yang Xiang, Jianmin Wang, Mingsheng Long ·

    Exploring Accuracy Law for Deep Time Series Forecasters: An Empirical Study

    arXiv:2510.02729v2 Announce Type: replace Abstract: Deep time series forecasting has emerged as a rapidly growing field in recent years. Despite the exponential growth of community interests, progress on standard benchmarks is often limited to marginal improvements. A common cons…

RELATED ENTITIES

RELATED TOPICS