arXiv Machine Learning
Quantile-Guided Diffusion for Probabilistic Time-Series Forecasting
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 15
Learning-based Probabilistic Load Forecasting with Post-hoc and In-model Uncertainty
arXiv:2607. 12730v1 Announce Type: cross Abstract: Smart-building load forecasters are often trained offline on dense, multivariate, high-frequency data, but deployment may provide only hourly, feature-limited inputs.
arXiv Machine Learning
Oct 8
DiTS: Multimodal Diffusion Transformers Are Time Series Forecasters
DiTS introduces a Multimodal Diffusion Transformer designed for time‑series forecasting that incorporates heterogeneous exogenous covariates. The model treats endogenous targets and exogenous covariates as separate modalities, jointly conditioning future generation on target history and available covariates. By employing flow matching and Time‑aligned Modulation, DiTS achieves strong deterministic and probabilistic forecasting performance across diverse covariate‑aware tasks.
arXiv Machine Learning
23h ago
PathFM: Fast Generative Forecasting of Multivariate Trajectories
arXiv:2610.22358v1 Announce Type: new Abstract: Time series foundation models are becoming increasingly popular for general-purpose forecasting. However, most leading models predict marginal quantile...
arXiv Machine Learning
Jul 30
Crossing-Free Probabilistic K-Line Forecasts Without Retraining
arXiv:2607. 26792v1 Announce Type: cross Abstract: Probabilistic K-line forecasting describes uncertainty in four complementary prices, namely open--high--low--close (OHLC).
arXiv Machine Learning
Sep 29
Aurora-X: Built for Extreme Time Series Forecasting
Aurora‑X is a billion‑parameter time‑series foundation model designed for extreme forecasting tasks. It employs a progressive curriculum that starts with channel‑independent pretraining, then adds cross‑variable dependencies, variable context and horizon lengths, and optional future covariates during mid‑training. A variable‑resolution post‑training stage allows adjustable temporal spans per token at inference, while a pattern‑guided mixture‑of‑experts expands capacity through sparse activation and expert specialization. An implicit quantile network head predicts arbitrary quantiles, enhancing probabilistic forecasting flexibility. Experiments on GIFT‑Eval, TIME, FEV‑Bench, TFB, and DAG‑Bench show state‑of‑the‑art performance against both pretrained TSFMs and task‑specific supervised models.
arXiv Machine Learning
Sep 22
Monotone-Constrained Diffusion Models for Long-Horizon Production Forecasting
The paper introduces Physics‑SIMS‑TS, a conditional diffusion model designed for long‑horizon oil and gas production forecasting. It enforces monotone decline through negative guidance, decline‑curve constraints, and isotonic projection during sampling, and incorporates spatial training augmentation and an ensembled stochastic sampler to produce calibrated predictive distributions. Evaluated on over 35,000 wells across three jurisdictions, Physics‑SIMS‑TS achieves the highest accuracy among diffusion forecasters and matches transformer ensembles, with only a 0.5% increase in mean squared error for monotonicity.