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

31–40 of 123 posts

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

#31

Post by aeyes »

tasty_freeze wrote: post #22
throwtappedmac wrote: post #10

Earlier quoted context omitted.

Curious George here: why are you trying to predict where the mouse is going? :)

Game developers are constantly trying to minimize lag. I have no idea if computers are so fast these days that it is a "solved" problem, but I knew a game developer ages ago who used a predictive mouse model to reduce the apparent lag by guessing where the mouse would be at the time the frame was displayed (considering it took 30 ms or whatever to render the frame).

Quake internet play only became acceptable when client side prediction was implemented, I'm sure it would be better to have real prediction instead of simple interpolation.

https://raw.githubusercontent.com/ESWAT/john-carmack-plan-ar...

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

#32

Post by sarusso »

iamgopal wrote: post #3

How can time series model be pre-trained ? I think I’m missing something.

My understating is that, while your eye can naturally spot a dependency over time in time series data, machines can’t. So as we did for imaging, where we pre-trained models to let machines easily identify objects in pictures, now we are doing the same to let machines “see” dependencies over time. Then, how these dependencies work, this is another story.

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

#33

Post by wongarsu »

tasty_freeze wrote: post #22
throwtappedmac wrote: post #10

Earlier quoted context omitted.

Curious George here: why are you trying to predict where the mouse is going? :)

Game developers are constantly trying to minimize lag. I have no idea if computers are so fast these days that it is a "solved" problem, but I knew a game developer ages ago who used a predictive mouse model to reduce the apparent lag by guessing where the mouse would be at the time the frame was displayed (considering it took 30 ms or whatever to render the frame).

Competitive online games commonly predict the player's movement. Network latencies have improved and are now usually If you want to predict not just position but also orientation in a shooter game, that's basically predicting the mouse movements.

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

#35

Post by morkalork »

leeoniya wrote: post #23
esafak wrote: post #21

Is anyone using neural networks for anomaly detection in observability? If so, which model and how many metrics are you supporting per core?

LSTM is common for this. also https://facebook.github.io/prophet/

How data hungry is it, or what is the minimum volume of data needed before its worth investigating?

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

#36

Post by mhh__ »

Dear googler or meta-er or timeseries transformer startup something-er: Please make a ChatGPT/chat.lmsys.org style interface for one of these that I can throw data at and see what happens.

This one looks pretty easy to setup, in fairness, but some other models I've looked at have been surprisingly fiddly / locked behind an API.

Perhaps such a thing already exists somewhere?

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

#37

Post by rockinghigh »

VHRanger wrote: post #24
Pseudocrat wrote: post #15

Earlier quoted context omitted.

Depends on use case. Hybrid approaches have been dominating the M-Competitions, but there are generally small percentage differences in variance of statistical models vs machine learning models. And exponentially higher cost for ML models.

At the end of the day, if training or doing inference on the ML model is massively more costly in time or compute, you'll iterate much less with it. I also think it's a dead end to try to have foundation models for "time series" - it's a class of data! Like when people tried to have foundation models for any general graph type. You could make foundation models for data within that type - eg. meteorological time serie…

These models may be helpful if they speed up convergence when fine tuned on business-specific time series.

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

#40

Post by uoaei »

sarusso wrote: post #28
uoaei wrote: post #2

"Time series" is such an over-subscribed term. What sorts of time series is this actually useful for? For instance, will it be able to predict dynamics for a machine with thousands of sensors?

Even if it was for multivariate time series, the model would first need to infer what machine are we talking about, then its working conditions, and only then make a reasonable forecast based on an hypothesis of its dynamics. I don’t know, seems pretty hard.

Indeed. An issue I ran into over and over while doing research for semiconductor manufacturing.

My complaint was more illustrative than earnest.

Post reply on HN