News for hackers. Stuff that matters.

cutkosky

Re:Schedule-Free Learning – A New Way to Train on Saturday April 06, 2024 @03:38PM (#39954826)
(an) author here: paper will likely be coming out in O(month). But, yes it turns out that the method is minimax optimal for stochastic convex optimization for a wide variety of parameter settings. Of course, minimax optimality alone does not fully explain empirical success - we've had minimax optimal algorithms for decades!