Re: [Help-gsl] Stochastic descent in multimin functions

[John Lamb]

James Bergstra wrote:
> Hi,
>
> I was wondering if is safe / sane to provide a function for minimization
> that uses a stochastic gradient estimate.  My gradient estimation would
> thus produce different estimates for the same point, depending on the
> internal state of the 'function'.  Aside from yeilding a noisy gradient,
> would this interfere with the optimization?  Would one optimization type
> be more appropriate than another in this case? (eg: grad descent vs.
> conjugate transpose vs ?)
>
> James Bergstra

You might have a look at some of the papers of WB Liu et al on SSC 
optimization methods.

--
JDL