Against Time-Series Foundation Models

Or: My Experience In Modern Forecasting

Time-series foundational models (TSFMs) are currently engaged in a knife fight to prove their worth against statistical models that have been around for half a century. TSFMs borrow similar architectural patterns from LLMs, and take a similar approach to curating large foundational datasets and pretraining. Only instead of words, the primitive is a time-series. Why are they struggling to prove their worth? This is obviously not what happened in other domains where foundational models have emerged. Is it some property of reality that forecasting time-series is harder? Or are these models…

saved by

• Oscar Marret

related reading

• The Unreasonable Difficulty of Time Series Forecastingsuzyahyah.github.io
• 2402.03885arxiv.org
• GitHub - google-research/timesfm: TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.github.com
• Time Series - From Analyzing the Past to Predicting the Future | Towards Data Sciencetowardsdatascience.com
• TimeGPT-1 | Hacker Newsnews.ycombinator.com
• [2310.07820] Large Language Models Are Zero-Shot Time Series Forecastersarxiv.org
• On the Opportunities and Risks of Foundation Modelsarxiv.org
• ML Blog - Everything you need to know about Time Series Forecastingmrtunguyen.github.io
• An introduction to time series forecasting | InfoWorldinfoworld.com
• Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Mostarxiv.org
• Generalist - GEN-0 / Embodied Foundation Models That Scale with Physical Interactiongeneralistai.com
• frontier model training methodologies | Alex Wa's Blogdjdumpling.github.io