What guarantees of optimality do we get when minimizing with Stochastic Gradient Descent a problem in its original formulation, after showing that it is a Geometric Programming instance (i.e. can be formulated as Convex Optimization when applying logarithmic transformation to the variables)?


migrated from stats.stackexchange.com Jun 28 '18 at 18:00

This question came from our site for people interested in statistics, machine learning, data analysis, data mining, and data visualization.

  • $\begingroup$ Cann you give more detail and context, please? And, without some connection to statistocs this would be better asked at math SE $\endgroup$ – kjetil b halvorsen Jun 28 '18 at 16:43

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.