English(EN)Prediction-powered inference for time series across space
arXiv发布新研究,介绍先进的时间序列预测技术 · 跟踪9个来源
作者PulseAugur 编辑部·[21 个来源]·
arXiv上发表的多篇研究论文介绍了改进时间序列预测的新方法。SteerCast通过使用过去数据的数据库来指导预测,而无需重新训练,从而增强了仅解码器模型。MIDAPN为数值和多模态时间序列数据提供了一个统一的骨干网络,集成了图适应和时间分析。CARE是一个轻量级模块,通过学习残差校正模式并提供不确定性估计来改进确定性预测器。SACQ通过使用交叉注意力和门控校正机制来优化长期预测,其性能优于标准的读出头。RideBench推出了一个大规模的网约车预测基准,突出了结合外部因素和长期预测的挑战。BEAT通过基于误差监控的自适应梯度调整来平衡预测中的频率分量。PulseBound专注于从光电容积描记数据进行生理结构化预测,确保因果信息的可访问性。最后,Temporal Predictive Multiplicity探讨了具有相似准确性的模型如何产生显著不同的预测轨迹,揭示了当前多重性研究中的一个空白。
AI
arXiv:2610.11165v1 Announce Type: new Abstract: Multivariate long-horizon forecasting is critical to electricity load scheduling and traffic flow management, and to financial risk control. Existing deterministic backbones output a single trajectory, masking heterogeneous predicti…
arXiv:2610.11924v1 Announce Type: cross Abstract: Media-bridged time series forecasting is expanding to encompass traditional "multivariate" and emerging "multimodal" (e.g., through textual assistance). Existing Time Series Forecasting (TSF) models still rely on paradigm-specific…
arXiv:2610.12232v1 Announce Type: new Abstract: Test-time adaptation (TTA) methods for time-series forecasting update a deployed model, or a small adapter around it, from incoming ground truth. But the label of an $H$-step forecast exists only $H$ steps later, and real data pipel…
arXiv cs.LG
TIER_1English(EN)·Van Dai Do, Huu Hiep Nguyen, Minh Hoang Nguyen, Hung Le·
arXiv:2610.11229v1 Announce Type: new Abstract: Time series forecasting aims to predict future values from historical observations and auxiliary features. We propose \textbf{SteerCast}, a retrieval-based latent steering method that improves decoder-only forecaster at inference ti…
arXiv:2610.11170v1 Announce Type: new Abstract: Long-term time series forecasting (LTSF) models predominantly employ patch-based encoders terminated by a flatten readout head that maps the entire encoded historical memory to all future steps through a single shared projection. Th…
arXiv:2610.12010v1 Announce Type: new Abstract: Predictive representation learning from photoplethysmography (PPG) can violate causal information access even with causal attention, as normalization, nonlocal transforms, or companion views may depend on withheld samples. We introd…
arXiv cs.AI
TIER_1English(EN)·Darahaas Nallagatla, Darryl Cherian Jacob, Pan He·
arXiv:2610.12240v1 Announce Type: cross Abstract: Time-series foundation models (TSFMs) have achieved strong forecasting performance across domains. However, most adaptation methods remain static. Existing all-in-one methods learn a single set of dataset-level parameter updates a…
arXiv:2501.19065v3 Announce Type: replace-cross Abstract: Long-term time-series forecasting supports a wide range of applications, including weather prediction and electricity demand planning. Frequency-domain methods address this task by decomposing observations into components …
arXiv:2610.11164v1 Announce Type: new Abstract: We release Ride-Hailing, a large-scale ride-hailing time series dataset synthesized from DiDi's marketplace data across 200 spatial areas. Ride-Hailing spans four consecutive years at half-hourly granularity and covers three represe…
arXiv:2602.06597v2 Announce Type: replace Abstract: While generative modeling facilitates probabilistic time series forecasting, incorporating heterogeneous exogenous information remains challenging. Diffusion Transformers (DiT) provide a scalable framework for conditional genera…
arXiv cs.LG
TIER_1English(EN)·Guilherme Afonso Galindo Padilha, Paulo Salgado Gomes de Mattos Neto, Rafael Menelau Oliveira e Cruz·
arXiv:2610.09096v1 Announce Type: new Abstract: While established literature underscores the pivotal role of preprocessing in forecasting accuracy, this stage remains largely overlooked in current research. Modern benchmarks typically resort to simple scaling, failing to account …
arXiv cs.LG
TIER_1English(EN)·Emanuele Albini, Francesca Toni, Saumitra Mishra, Francesco Leofante·
arXiv:2610.09994v1 Announce Type: new Abstract: Models with near-identical predictive performance can yield substantially different predictions, a phenomenon known as predictive multiplicity. Prior work has mostly studied this at the level of individual scalar outputs. In time-se…
arXiv:2610.10222v1 Announce Type: new Abstract: Differentially private time-series generators commonly produce fixed-length synthetic windows, whereas downstream forecasting models often require long continuous training sequences. How these windows are assembled after generation …
arXiv cs.LG
TIER_1English(EN)·Jakob Benjamin Wessel, Sam Allen·
arXiv:2610.10076v1 Announce Type: cross Abstract: Calibration is an essential requirement for probabilistic predictions to be useful for decision making. While state-of-the-art prediction methods often yield miscalibrated predictive distributions, several post-hoc recalibration s…
Multivariate long-horizon forecasting is critical to electricity load scheduling and traffic flow management, and to financial risk control. Existing deterministic backbones output a single trajectory, masking heterogeneous prediction difficulty across horizons and channels and p…
arXiv:2603.19899v2 Announce Type: replace-cross Abstract: Autocorrelation is a common property of time-series, where each observation is dependent on its predecessors. In deep time-series forecasting, it raises two central challenges: (1) designing backbone architectures to model…
arXiv:2610.07834v1 Announce Type: new Abstract: Retrieval-augmented time-series forecasting uses the continuations of historical segments similar to the current context as references for a forecaster. Most existing methods build the retrieval memory once from the training segment…
The following motif is common in spatiotemporal settings: we have a sequence of covariate and label pairs observed for a relatively short, recent time period. We have access to unlabeled covariates over a longer time period. Data is observed over many spatial locations. For insta…
arXiv cs.LG
TIER_1English(EN)·Jung Min Choi, Ngoc Son Le, Ibram Abdelmalak, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme·
arXiv:2610.03491v1 Announce Type: new Abstract: Most long-term time-series forecasting models map the look-back window directly to the full horizon in a single pass. While efficient, this design does not explicitly identify which historical states are most relevant to different f…
Real-world time series are frequently driven by exogenous events and structural shifts, rendering conventional forecasting based solely on historical numerical observations insufficient. While language models can retrieve external news, standard retrieval-augmented approaches str…
We present TimeBraid, a series of unified time-series and language models that align pretrained language models and pretrained time-series foundation models through interleaved global residual attention layers. Each model inherits knowledge, instruction following, and reasoning f…