… Star-Convex Functions This paper focuses on the optimization of star-convex functions, a
particular class of (typically) non-convex functions that includes convex functions as a …

… class, which we call the class of smooth quasar-convex functions, is parameterized by a …
convex and star-convex functions, and smaller values of γ indicate that the function can be “…

… class, which we call the class of smooth quasar-convex functions, is parameterized by a …
convex and star-convex functions, and smaller values of γ indicate that the function can be “…

… by star-convex constrained optimization. The visible space is modeled as star convex … ,
the visibility constraint is formulated for trajectory optimization. The trajectory is confined in …

… In this paper, we propose an epochwise star-convex property of the optimization path of
SGD, which we validate in various experiments. Based on such a property, we show that SGD …

… refer to a particular class of (typically) non-convex functions whose global optimum is visible
… focus on optimizing and analyzing star-convex functions, while learning such functions is …

… We revisit star-convex functions, which are strictly unimodal on all … for star-convex functions
with α-Hölder continuous gradients. We also prove that our convergence rate is near optimal …

… , and globally optimal solutions are achieved subject to this constraint. The star convexity …
This section reviews the ideas of star-convex sets (Section 2.1) and how this concept is …

… For this class of optimization problems, we show that the last iterate of … star-convex functions
contain convex functions as a subclass (but not necessarily pseudo/quasi-convex functions…

… ) is being used routinely for optimizing non-convex functions. Yet, the … 2016, Section A.4)
we have that fi(Ax − b) is star convex … n Pn i=1 fi(Ax − b), is a star-convex function which also …