Skip to content
Tagged articles

multivariate time series

3 articles · Page 1 of 1
DeepHub IMBA
DeepHub IMBA
Oct 21, 2026 · Artificial Intelligence

Mistral's Timestral: DHF, Multivariate Modeling & 21-Quantile Probabilistic Forecasting

Mistral AI releases Timestral, a family of time series foundation models (5M–209M parameters) featuring Decoupled Horizon Forecasting (DHF), covariate-aware attention for exogenous variables, synthetic-first two-stage training, and direct 21-quantile probabilistic output, outperforming TimesFM-3 and Chronos-2 on GIFT-Eval and TIME benchmarks.

DHFMistral AIbenchmark
0 likes · 15 min read
Mistral's Timestral: DHF, Multivariate Modeling & 21-Quantile Probabilistic Forecasting
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Sep 16, 2025 · Artificial Intelligence

Paper Review: HGTS‑Former – A Hierarchical Hypergraph Transformer for Multivariate Time‑Series Analysis

The HGTS‑Former model introduces a hierarchical hypergraph backbone combined with a Transformer to capture high‑order and dynamic dependencies in multivariate time‑series data, and experimental results on eight datasets show it consistently outperforms state‑of‑the‑art methods in both long‑term forecasting and interpolation tasks.

HGTS-FormerHypergraphTransformer
0 likes · 11 min read
Paper Review: HGTS‑Former – A Hierarchical Hypergraph Transformer for Multivariate Time‑Series Analysis
JD Tech Talk
JD Tech Talk
Feb 24, 2021 · Artificial Intelligence

Memory-Gated Recurrent Networks for Multivariate Time Series Analysis

The paper introduces Memory-Gated Recurrent Networks (mGRN), a novel RNN architecture that separately captures marginal and joint memories of multivariate time series, demonstrating significant performance gains over LSTM/GRU across diverse applications such as ICU monitoring, speech recognition, handwriting, and high‑frequency stock price prediction.

AIRecurrent Neural Networkfinancial prediction
0 likes · 10 min read
Memory-Gated Recurrent Networks for Multivariate Time Series Analysis