Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series

no code implementations • 8 Jan 2024 • Vijay Ekambaram, Arindam Jati, Nam H. Nguyen, Pankaj Dayama, Chandra Reddy, Wesley M. Gifford, Jayant Kalagnanam

Consequently, there has been a recent surge in utilizing pre-trained large language models (LLMs) with token adaptations for TS forecasting.

Few-Shot Learning Time Series +2

Hierarchical Proxy Modeling for Improved HPO in Time Series Forecasting

no code implementations • 28 Nov 2022 • Arindam Jati, Vijay Ekambaram, Shaonli Pal, Brian Quanz, Wesley M. Gifford, Pavithra Harsha, Stuart Siegel, Sumanta Mukherjee, Chandra Narayanaswami

To address this test-validation mismatch, we propose a novel technique, H-Pro to drive HPO via test proxies by exploiting data hierarchies often associated with time series datasets.

Hyperparameter Optimization Model Selection +2

Generative Adversarial Network for Probabilistic Forecast of Random Dynamical System

no code implementations • 4 Nov 2021 • Kyongmin Yeo, Zan Li, Wesley M. Gifford

We present a deep learning model for data-driven simulations of random dynamical systems without a distributional assumption.

Generative Adversarial Network

AutoAI-TS: AutoAI for Time Series Forecasting

no code implementations • 24 Feb 2021 • Syed Yousaf Shah, Dhaval Patel, Long Vu, Xuan-Hong Dang, Bei Chen, Peter Kirchner, Horst Samulowitz, David Wood, Gregory Bramble, Wesley M. Gifford, Giridhar Ganapavarapu, Roman Vaculin, Petros Zerfos

We present AutoAI for Time Series Forecasting (AutoAI-TS) that provides users with a zero configuration (zero-conf ) system to efficiently train, optimize and choose best forecasting model among various classes of models for the given dataset.

Benchmarking BIG-bench Machine Learning +3