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

04/10/2022
by   Pan Liu, et al.
0

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 TV^r, r∈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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset