Hi, I'm one of the co-founders of SigOpt (YC W15) and am happy to answer any questions about this post or anything about the methods used.<p>More info on the Bayesian optimization behind SigOpt can be found on our research page [1].<p>The code used in this post can be found on github [2].<p>[1]: <a href="https://sigopt.com/research" rel="nofollow">https://sigopt.com/research</a><p>[2]: <a href="https://github.com/sigopt/sigopt-examples/tree/master/dnn-tuning-nervana" rel="nofollow">https://github.com/sigopt/sigopt-examples/tree/master/dnn-tu...</a>