Twice epi-differentiability of extended-real-valued functions with applications in composite optimization
Ashkan Mohammadi, M. Ebrahim Sarabi

TL;DR
This paper investigates the twice epi-differentiability of extended-real-valued functions with composite structures, providing formulas for second subderivatives and deriving second-order optimality conditions in composite optimization.
Contribution
It establishes conditions for twice epi-differentiability of composite functions and derives second-order optimality conditions using parabolic regularity and metric subregularity.
Findings
Formulas for second subderivatives of composite functions
Second-order optimality conditions for composite optimization problems
Validation of twice epi-differentiability under parabolic regularity
Abstract
The paper is devoted to the study of the twice epi-differentiablity of extended-real-valued functions, with an emphasis on functions satisfying a certain composite representation. This will be conducted under the parabolic regularity, a second-order regularity condition that was recently utilized in [13] for second-order variational analysis of constraint systems. Besides justifying the twice epi-differentiablity of composite functions, we obtain precise formulas for their second subderivatives under the metric subregularity constraint qualification. The latter allows us to derive second-order optimality conditions for a large class of composite optimization problems.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
