Hugging Face Blog
Dec 1, 2022
Introducing Timestral
Introducing Timestral offers state‑of‑the‑art probabilistic forecasting across four model sizes ranging from 5 million to 209 million parameters. The models are designed to be CPU‑efficient and ready for zero‑shot use, enabling rapid deployment without extensive fine‑tuning.
Related stories
arXiv AI
Aug 18
TinyCast: Probabilistic Zero-Shot Forecasting with Computed Periodicity
arXiv:2608. 15767v1 Announce Type: cross Abstract: We introduce TinyCast, an attention-free zero-shot forecaster that emits a predictive distribution from 146,505 parameters, on the premise that at this size the periodic structure of a context is worth computing rather than learning.
Hugging Face Trending Papers
Oct 27
Timestral
Timestral is a family of four time‑series foundation models (5M, 28M, 123M, and 209M parameters) that achieve state‑of‑the‑art results on GIFT‑Eval, TIME, and fev‑bench, with the 209M and 123M variants topping every metric. The models use Decoupled Horizon Forecasting to separate prediction tokens from context, a covariate framework for known‑future inputs, and a two‑stage training pipeline that first pre‑trains on synthetic data and then post‑trains on a mix of real and synthetic data with extended context. All four models and inference code are publicly available on Hugging Face and GitHub.
arXiv Machine Learning
Aug 12
TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting
arXiv:2511. 18539v3 Announce Type: replace Abstract: We propose TimePre, a simple framework that unifies the efficiency of Multilayer Perceptron (MLP)-based models with the distributional flexibility of Multiple Choice Learning (MCL) for Probabilistic Time-Series Forecasting (PTSF).
arXiv AI
Oct 28
Timestral
Timestral is a family of four time‑series foundation models (5M, 28M, 123M, and 209M parameters) designed for probabilistic forecasting. It achieves state‑of‑the‑art results on GIFT‑Eval, TIME, and fev‑bench, with the 209M and 123M variants topping every metric. The approach relies on Decoupled Horizon Forecasting, a covariate framework for known‑future variables, and a two‑stage training pipeline that first pre‑trains on synthetic data before fine‑tuning on real and synthetic data with extended context.
arXiv Machine Learning
Sep 25
fable.intermittent: benchmarking probabilistic forecasting methods for intermittent time series
The paper introduces fable.intermittent, an R package that consolidates various probabilistic forecasting methods for intermittent time series within the fable framework, enabling streamlined fitting and evaluation across multiple datasets. It also presents TWEES, a new exponential smoothing model using a Tweedie predictive distribution, and releases tweedieDistr, a faster implementation of the Tweedie distribution. The authors evaluate these tools on four datasets provided with the package.
arXiv Machine Learning
Aug 7
Timestep-Conditioned Transformers for Global Weather Forecasting
arXiv:2608. 06241v1 Announce Type: new Abstract: Existing machine-learning weather forecasting models rely on predetermined and fixed autoregressive timesteps.
arXiv Machine Learning
Sep 29
FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting
FLAME is a lightweight Time Series Foundation Model that uses Legendre Memory variants (LegT and LegS) in its encoding and decoding stages to capture inductive biases and perform efficient long‑range forecasting. It incorporates a normalizing‑flow forecasting head to generate complex probabilistic distributions over future horizons. Experiments on TSFM‑Bench, ProbTS, and TFB show FLAME performs strongly as an out‑of‑the‑box tool for decision intelligence.
arXiv Machine Learning
6d ago
Chronos-2: A foundation model for multivariate time series forecasting
Chronos-2 is a foundation model for multivariate time‑series forecasting that captures interactions among multiple series and heterogeneous covariates, enabling zero‑shot probabilistic forecasts without task‑specific tuning. It achieves state‑of‑the‑art accuracy, improving skill scores by 5.2 percentage points and win rates by 10 percentage points over leading baselines, while being computationally efficient—generating forecasts for 100 series in under one second on a single mid‑range GPU. The model demonstrates strong performance across diverse scientific domains such as infectious‑disease forecasting, macroeconomics, carbon‑flux prediction, and runoff simulation, matching or surpassing specialized methods.
arXiv Machine Learning
Jun 29
Unified Zero-Shot Time Series Forecasting: A Darts Foundation
arXiv:2606. 27438v1 Announce Type: new Abstract: Since its initial release in 2020, Darts has become a widely used open-source Python library for time series analysis.
Hugging Face Blog
Mar 10, 2023
Multivariate Probabilistic Time Series Forecasting with Informer
arXiv Machine Learning
Jun 11
Intermittent time series forecasting: local vs global models
arXiv:2601. 14031v2 Announce Type: replace-cross Abstract: Forecasting intermittent time series, which contain zeros, is a crucial challenge in supply chains as inventory policies require probabilistic forecasts to establish safety levels.