61–70 of 123 posts
On a related note, Amazon also had a model for time series forecasting called Chronos. https://github.com/amazon-science/chronos-forecasting
And like all deep learning forecasting models thus far, it makes for a nice paper but is not worth anyone using for a real problem. Much slower than the classical methods it fails to beat.
Earlier quoted context omitted.
What do you mean by “observability”?
Telemetry. Dashboards. The application is knowing when a signal is anomalous. https://en.wikipedia.org/wiki/Observability_(software)
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.
> 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…
Earlier quoted context omitted.
And like all deep learning forecasting models thus far, it makes for a nice paper but is not worth anyone using for a real problem. Much slower than the classical methods it fails to beat.
That’s what people said about CV models in 2011.
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.
Fundamentally, the pre-trained model would need to learn a "world model" to predict well in distinct domains. This should be possible not regarding compute requirements and the exact architecture. After all, the physical world (down to the subatomic level) is governed by physical laws. Ilya Sutskever from OpenAI stated that next-token prediction might be enough to learn a world model (see [1]). That would imply that…
Earlier quoted context omitted.
Fundamentally, the pre-trained model would need to learn a "world model" to predict well in distinct domains. This should be possible not regarding compute requirements and the exact architecture. After all, the physical world (down to the subatomic level) is governed by physical laws. Ilya Sutskever from OpenAI stated that next-token prediction might be enough to learn a world model (see [1]). That would imply that…
But the data generating process could be literally anything. We are not constrained by physics in any real sense if we predicting financial markets or occurrences of a certain build error or termite behavior.
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.