oh, we just train the model in the standardized space which will help the convergence of LBFGS. Then we convert the weights to original space so the whole thing is transparent to users.
Sincerely, DB Tsai ------------------------------------------------------- My Blog: https://www.dbtsai.com LinkedIn: https://www.linkedin.com/in/dbtsai On Fri, Oct 24, 2014 at 3:13 PM, Debasish Das <[email protected]> wrote: > @dbtsai for condition number what did you use ? Diagonal preconditioning of > the inverse of B matrix ? But then B matrix keeps on changing...did u > condition it after every few iterations ? > > Will it be possible to put that code in Breeze since it will be very useful > to condition other solvers as well... > > On Fri, Oct 24, 2014 at 3:02 PM, DB Tsai <[email protected]> wrote: >> >> We don't have SVMWithLBFGS, but you can check out how we implement >> LogisticRegressionWithLBFGS, and we also deal with some condition >> number improving stuff in LogisticRegressionWithLBFGS which improves >> the performance dramatically. >> >> Sincerely, >> >> DB Tsai >> ------------------------------------------------------- >> My Blog: https://www.dbtsai.com >> LinkedIn: https://www.linkedin.com/in/dbtsai >> >> >> On Fri, Oct 24, 2014 at 2:39 PM, k.tham <[email protected]> wrote: >> > Oh, I've only seen SVMWithSGD, hadn't realized LBFGS was implemented. >> > I'll >> > try it out when I have time. Thanks! >> > >> > >> > >> > -- >> > View this message in context: >> > http://apache-spark-user-list.1001560.n3.nabble.com/Spark-LIBLINEAR-tp5546p17240.html >> > Sent from the Apache Spark User List mailing list archive at Nabble.com. >> > >> > --------------------------------------------------------------------- >> > To unsubscribe, e-mail: [email protected] >> > For additional commands, e-mail: [email protected] >> > >> >> --------------------------------------------------------------------- >> To unsubscribe, e-mail: [email protected] >> For additional commands, e-mail: [email protected] >> > --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
