Strong Duality in Risk-Constrained Nonconvex Functional Programming

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kalogerias, Dionysis, Pougkakiotis, Spyridon
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911264673890304
author Kalogerias, Dionysis
Pougkakiotis, Spyridon
author_facet Kalogerias, Dionysis
Pougkakiotis, Spyridon
contents We show that a wide class of risk-constrained nonconvex functional optimization problems exhibit strong duality, regardless of nonconvexity. We develop two novel results under distinct sets of assumptions, establishing strong duality over both decomposable policy spaces (matching and extending prior work in the risk neutral case), and nondecomposable policy spaces with structure (e.g., continuity or smoothness), including certain universal finite-dimensional (fixed depth/width) neural network parametrizations as special cases (improving established results in the risk-neutral setting as well). We consider constraints featuring convex and positively homogeneous risk measures with bounded risk envelopes, generalizing expectations. Popular risk measures supported within our setting include the conditional value-at-risk (CVaR), the (even non-monotone) mean-absolute deviation (MAD), certain distributionally robust representations and more generally all real-valued coherent risk measures on the space $L_1$. We further discuss various generalizations of our base model, extensions for risk measures supported on $L_{p>1}$, implications in the context of mean-risk tradeoff models, as well as applications in wireless systems resource allocation, and supervised constrained learning. Our core proof technique appears to be new and relies on risk conjugate duality in tandem with J. J. Uhl's weak extension of A. A. Lyapunov's convexity theorem for vector measures taking values in infinite-dimensional Banach spaces.
format Preprint
id arxiv_https___arxiv_org_abs_2206_11948
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Strong Duality in Risk-Constrained Nonconvex Functional Programming
Kalogerias, Dionysis
Pougkakiotis, Spyridon
Optimization and Control
Information Theory
Systems and Control
Signal Processing
We show that a wide class of risk-constrained nonconvex functional optimization problems exhibit strong duality, regardless of nonconvexity. We develop two novel results under distinct sets of assumptions, establishing strong duality over both decomposable policy spaces (matching and extending prior work in the risk neutral case), and nondecomposable policy spaces with structure (e.g., continuity or smoothness), including certain universal finite-dimensional (fixed depth/width) neural network parametrizations as special cases (improving established results in the risk-neutral setting as well). We consider constraints featuring convex and positively homogeneous risk measures with bounded risk envelopes, generalizing expectations. Popular risk measures supported within our setting include the conditional value-at-risk (CVaR), the (even non-monotone) mean-absolute deviation (MAD), certain distributionally robust representations and more generally all real-valued coherent risk measures on the space $L_1$. We further discuss various generalizations of our base model, extensions for risk measures supported on $L_{p>1}$, implications in the context of mean-risk tradeoff models, as well as applications in wireless systems resource allocation, and supervised constrained learning. Our core proof technique appears to be new and relies on risk conjugate duality in tandem with J. J. Uhl's weak extension of A. A. Lyapunov's convexity theorem for vector measures taking values in infinite-dimensional Banach spaces.
title Strong Duality in Risk-Constrained Nonconvex Functional Programming
topic Optimization and Control
Information Theory
Systems and Control
Signal Processing
url https://arxiv.org/abs/2206.11948