2
$\begingroup$

I have a dataset with two independent variables $X,Z \in \mathbb{R}$ and a dependent variable $Y \in \mathbb{R}$.

This dataset has the following characteristics:

  • given some number $z$ and a "small" $\varepsilon > 0$, if we consider only the observations where $Z \in [z, z+\varepsilon]$ we find out that the relation $Y=f(X)$ in that subset is estimable quite easily with a polynomial function (it is a physical phenomenon).

  • if we consider an adjacent interval in some sense (i.e. $[z,z+2\varepsilon]$ or $[z+\varepsilon,z+2\varepsilon]$) the previous estimate may either still be a good estimate or not with respect to some criteria.

I'm asked to "find a clusterization in $N$ adjacent intervals with respect to $Z$ where each interval is the largest possible interval where there exists a good fit $Y=f(X)$".

How should approach this problem? Is there any literature where problems like this have been studied? What would you recommend? I think this problem may be a "clustering of functionals" or something like that.

I hope I made myself clear, it is a bit difficult to explain, feel free to ask more details.

$\endgroup$
  • $\begingroup$ This is a solid question, and it has good application in automotive and complex system engineering. The question behind the question is "where does linearity break down". Your polynomial model is a Taylor series approximation of the actual, and so how do you determine where you need to put your dividing lines? Many folks would say when you get more than 2% error then you need to use an updated model (aka move to another cluster). This problem has been around for decades in control system engineering. $\endgroup$ – EngrStudent Oct 15 '18 at 18:31
  • 2
    $\begingroup$ It would probably help if you could provide a small example dataset. At any rate, what you're describing does not seem to be clustering, in the typical sense of the term. $\endgroup$ – gung Oct 15 '18 at 19:40
  • $\begingroup$ Please revise if my edit of the title is all right for you. Your problem does not seem to me a cluster analysis proem at all $\endgroup$ – ttnphns Oct 19 '18 at 10:17
  • $\begingroup$ You are right, this title suits better to the problem, thank you $\endgroup$ – edoedoedo Oct 21 '18 at 20:48
0
+50
$\begingroup$

Here's a go at the (very interesting!) problem.

If we can assume some kind of a distribution on $Y|X, Z, \theta$, for example a polynomial regression as you suggested, for example, $Y|X, Z, \theta \sim N(f_{\theta_Z}(X), \sigma_n^2)$, we obtain the conditional distribution $p(Y|X, Z, \theta)$.

To construct a full posterior, one needs the joint distribution $p(Y, X, Z, \theta)$. The remaining piece, considering the conditional distribution above is $p(X, Z, \theta)$.

Answering the other part of your question, fitting $Y=f(X)$ for different intervals of $Z$, is equivalent to finding the set of parameters $\theta(Z)$ for the range of $Z$ - which a GP could model beautifully.

You enforce a different $\theta$ for a prespecified number of intervals by treating $\theta$s and the interval bounds $[Z_{(i)}]$ as parameters. On the other hand, you could enforce a continuity in the function $\theta(Z)$ by using, for example, an RBF kernel.

This way, we'd have the distribution $p(\theta|Z)$ (a multivariate normal), and the "learning" could be done by using MCMC techniques (using Stan for example) or by simply finding the set of parameters that maximises the joint likelihood described here (using Tensorflow or any other optimiser).

After obtaining a fit, I guess that it'd be possible to use other parametric models to replace the GP once you're more confident about what the function $\theta(Z)$ looks like.

Side note: I've used GPs in vaguely similar ways before (to model "latent mappings" I guess I'd call them - which are essentially functionals), and I've had some great results. They're quite powerful when framed well.

$\endgroup$
  • $\begingroup$ Thank you, I'll try to implement your solution to see if I can get it to work! $\endgroup$ – edoedoedo Oct 21 '18 at 20:49

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.