Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

TimesFM: Time Series Foundation Model for time-series forecasting

github.com

Post reply on HN
Print view View original

81–90 of 123 posts

Re: TimesFM: Time Series Foundation Model for time-series forecasting

#81

Post by owl_brawl »

refibrillator wrote: post #79
whimsicalism wrote: post #17

I'm curious why we seem convinced that this is a task that is possible or something worthy of investigation. I've worked on language models since 2018, even then it was obvious why language was a useful and transferable task. I do not at all feel the same way about general univariate time series that could have any underlying process.

Why do you think language is so special? There's an extensive body of literature across numerous domains that demonstrates the benefits of Multi-Task Learning (MTL). Actually I have a whole folder of research papers on this topic, here's one of the earliest references on hand that I feel captures the idea succinctly in the context of modern ML: “MTL improves generalization by leveraging the domain-specific informatio…

For those who haven't read it, Rich Caruana's thesis on multi-task learning is beautifully written (the cited 1998 paper here). It's amazing to see how far the field has come, and, at the same time, how advanced the thinking was in the 90s too.

Re: TimesFM: Time Series Foundation Model for time-series forecasting

#82

Post by cscurmudgeon »

whimsicalism wrote: post #63
zeroxfe wrote: post #51

Earlier quoted context omitted.

> I'm curious why we seem convinced that this is a task that is possible or something worthy of investigation. There's a huge industry around time series forecasting used for all kinds of things like engineering, finance, climate science, etc. and many of the modern ones incorporate some kind of machine learning because they deal with very high dimensional data. Given the very surprising success of LLMs in non-langua…

Task specific time series models, not time series “foundation models” - we are discussing different things.

Foundational time series models have been around since 2019 and show competitive levels of performance with task specific models.

https://arxiv.org/abs/1905.10437

Re: TimesFM: Time Series Foundation Model for time-series forecasting

#84

Post by bigger_cheese »

whimsicalism wrote: post #17

I'm curious why we seem convinced that this is a task that is possible or something worthy of investigation. I've worked on language models since 2018, even then it was obvious why language was a useful and transferable task. I do not at all feel the same way about general univariate time series that could have any underlying process.

There is potential for integrating ML with time series data in industrial applications (things like smelters, reactors etc.), where you have continuous stream of time series measurements from things like gauges and thermocouples. If you can detect (and respond) to changing circumstances faster then a humans in control room reacting to trends or alarms then potential big efficiency gains...

Operator guidance is often based on heuristics - when metric A exceeds X value for Y seconds take action Z. Or rates of change if the signal is changing at a rate of more than x etc.

So in these areas there exists potential for ML solution, especially if it's capable of learning (i.e. last response overshot by X so trim next response appropriately).

Re: TimesFM: Time Series Foundation Model for time-series forecasting

#86

Post by fedeb95 »

whimsicalism wrote: post #17

I'm curious why we seem convinced that this is a task that is possible or something worthy of investigation. I've worked on language models since 2018, even then it was obvious why language was a useful and transferable task. I do not at all feel the same way about general univariate time series that could have any underlying process.

as you say, without knowing anything about the underlying process, we can't predict generally. Some other comments point to contexts in which we do know something about the underlying. For instance, I don't think finance is something where you can apply this kind of stuff.

Re: TimesFM: Time Series Foundation Model for time-series forecasting

#89

Post by kqr »

bigger_cheese wrote: post #84
whimsicalism wrote: post #17

I'm curious why we seem convinced that this is a task that is possible or something worthy of investigation. I've worked on language models since 2018, even then it was obvious why language was a useful and transferable task. I do not at all feel the same way about general univariate time series that could have any underlying process.

There is potential for integrating ML with time series data in industrial applications (things like smelters, reactors etc.), where you have continuous stream of time series measurements from things like gauges and thermocouples. If you can detect (and respond) to changing circumstances faster then a humans in control room reacting to trends or alarms then potential big efficiency gains... Operator guidance is often…

Every time i've actually tried something like this it has not outperformed statistical process control.

It's not just that control charts are great signal detectors, but also managing processes like that takes a certain statistical literacy one gets from applying SPC faithfully for a while, and does not get from tossing ML onto it and crossing fingers.

Post reply on HN