English(EN)Rethinking Training & Inference for Forecasting: Linking Winner-Take-All back to GMMs
新AI方法解决时间序列预测和模型可解释性问题 · 追踪5个来源
作者PulseAugur 编辑部·[11 个来源]·
研究人员推出KARMA，一种通过构建马尔可夫代理模型来捕捉时间依赖性的新方法，用于解释时间序列预测模型。该方法识别预测充分性所需的最小历史长度，并估计一个马尔可夫转移核，提供一个五级全局解释层次结构。另外，一个名为The Simulacrum的框架使用决策理论预训练来开发基于神经网络的时间序列估计器，这些估计器可以近似最优决策规则并在真实基准上实现具有竞争力的预测精度。此外，一项关于时间序列基础模型灾难性遗忘的研究表明，虽然微调提高了准确性，但可能导致遗忘，尽管更大的模型显示出更强的鲁棒性，并且缓解技术可以帮助较小的模型匹配性能。
AI
arXiv:2607.01918v1 Announce Type: new Abstract: We present Zeus, a unified tuning-free Time Series Foundation Model (TSFM) that delivers superior performance across diverse analysis tasks without any task-specific fine-tuning. Unlike prior studies that primarily focus on zero-sho…
We present Zeus, a unified tuning-free Time Series Foundation Model (TSFM) that delivers superior performance across diverse analysis tasks without any task-specific fine-tuning. Unlike prior studies that primarily focus on zero-shot forecasting but require task-specific tuning f…
arXiv cs.LG
TIER_1English(EN)·Haroon Gharwi, Yue Dai, Kai Shu·
arXiv:2607.00197v1 Announce Type: new Abstract: Long-horizon multivariate time series forecasting (LTSF) remains challenging due to non-stationarity, regime shifts, and error accumulation. The Variability-Aware Recursive Neural Network (VARNN) is designed to track such variabilit…
arXiv:2606.28670v1 Announce Type: cross Abstract: We introduce MACROCAST, a lightweight Time Series Foundation Model (TSFM) for real-time macroeconomic forecasting. Existing TSFMs suffer from data leakage in two forms: temporal contamination, as the model may have seen the realiz…
arXiv cs.LG
TIER_1English(EN)·Oleksandr Shchur, Abdul Fatir Ansari, Caner Turkmen, Lorenzo Stella, Nick Erickson, Pablo Guerron, Michael Bohlke-Schneider, Yuyang Wang·
arXiv:2509.26468v3 Announce Type: replace Abstract: Benchmark quality is critical for meaningful evaluation and sustained progress in time series forecasting, particularly with the rise of pretrained models. Existing benchmarks often have limited domain coverage or overlook real-…
arXiv:2606.27711v1 Announce Type: cross Abstract: We introduce a neural network-based framework for learning time series estimators through a process we term decision-theoretic pretraining. Analysts specify a generative world, a distribution over data-generating processes, and a …
arXiv:2510.00809v3 Announce Type: replace Abstract: While Time Series Foundation Models (TSFMs) excel in zero-shot tasks, their behavior under continual fine tuning is poorly understood. We present the first systematic study of catastrophic forgetting in TSFMs (TimesFM-2.0, Chron…
arXiv:2606.27599v1 Announce Type: cross Abstract: While many explainable AI (XAI) methods have been proposed, most are not designed for time-series forecasting models and often rely on the implicit assumption that timestamp features are independent. This assumption ignores the fu…
We introduce a neural network-based framework for learning time series estimators through a process we term decision-theoretic pretraining. Analysts specify a generative world, a distribution over data-generating processes, and a target decision objective. A neural network traine…
arXiv cs.LG
TIER_1English(EN)·Qiyuan Wu, Katie Z Luo, Bharath Hariharan, Wei-Lun Chao, Mark Campbell·
arXiv:2606.26424v1 Announce Type: new Abstract: Trajectory forecasting for autonomous driving has advanced rapidly, yet representative models often produce uninformative posteriors over forecast modes, causing problems for mode pruning. We trace this to a modeling-training mismat…
arXiv:2412.19897v3 Announce Type: replace Abstract: We introduce a local surrogate approach for explainable time-series forecasting. An initially non-interpretable predictive model to improve the forecast of a classical time-series 'base model' is used. 'Explainability' of the co…
