Real order total variation with applications to the loss functions in learning schemes

DOI10.1142/S0219199723500165arXiv2204.04582OpenAlexW4362667046MaRDI QIDQ6396115FDOQ6396115

Authors: Pan Liu, Xin Yang Lu, Kunlun He 

Publication date: 9 April 2022

Abstract: Loss function are an essential part in modern data-driven approach, such as bi-level training scheme and machine learnings. In this paper we propose a loss function consisting of a $r$-order (an)-isotropic total variation semi-norms $T{V}^r$, $rinmathbb{R}^{+}$, defined via the Riemann-Liouville (R-L) fractional derivative. We focus on studying key theoretical properties, such as the lower semi-continuity and compactness with respect to both the function and the order of derivative $r$, of such loss functions.

Full work available at URL: https://doi.org/10.1142/s0219199723500165

Mathematics Subject Classification ID

Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Absolutely continuous real functions of several variables, functions of bounded variation (26B30) Variational and other types of inequalities involving nonlinear operators (general) (47J20)

This page was built for publication: Real order total variation with applications to the loss functions in learning schemes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6396115)