“Convex Until Proven Guilty” Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions

“ConvexUntilProvenGuilty”:Dimension-FreeAccelerationofGradientDescentonNon-ConvexFunctionsYairCarmonJohnC.DuchiOliverHinderAaronSidford1AbstractOptimizationbecomesmoredifficultwithoutconvexity,as...