[computer-go] ELO Ratings of move pattern

[Álvaro Begué]

On Dec 20, 2007 10:36 PM, Jason House <jason.james.house at gmail.com> wrote:

>
>
> On Dec 20, 2007 5:39 PM, Álvaro Begué <alvaro.begue at gmail.com> wrote:
>
> > Over lunch I thought of another way of doing it that would be very
> > general and easy to implement. Basically, I can compute the log-likelihood
> > for a particular setting of the weights, and I can compute the gradient and
> > the Jacobian matrix (the derivative with respect to each weight or pair of
> > weights, respectively). Then I can approximate the function I am minimizing
> > using a paraboloid computed from that data, compute the minimum of the
> > paraboloid and take that point to be the new setting of the weights. Has
> > anyone tried something like this? It seems like the natural way to do it to
> > me.
>
>
> My knowledge of the Jacobian matrix is limited.  http://en.wikipedia.org/wiki/Jacobian
> seems to imply that your definition of the Jacobian matrix is unusual.
>

Ooops! It's been too long since I learned these things. What I meant to say
was the Hessian matrix ( http://en.wikipedia.org/wiki/Hessian_matrix ),
which does contain the second derivatives. You are right that assuming the
derivative changes linearly and using a paraboloid are the exact same thing.
So we are probably thinking of the same method, although I think I can code
it in very elegantly (maybe slow too?).


Álvaro.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://computer-go.org/pipermail/computer-go/attachments/20071220/172789cb/attachment.htm