[Computer-go] Parameter Optimization with Local Quadratic Regression
jloup at gailly.net
Thu Mar 18 18:07:44 PDT 2010
Thanks Rémi for these slides, looking forward to see the paper.
> For this application it is safe to assume that the function to be
> optimized (the winning rate) is a smooth function of parameters,
> and it has no tricky local optima
Why is it safe to assume no local optimum? This is only a guess,
but with high dimension (many parameters to tune) I would expect
local optima. Does your algorithm scale to many dimensions?
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Computer-go