Convex Geometry of the Generalized Matrix-Fractional Function
Generalized matrix-fractional (GMF) functions are a class of matrix support functions introduced by Burke and Hoheisel as a tool for unifying a range of seemingly divergent matrix optimization problems associated with inverse problems, regularization and learning. In this paper we dramatically simplify the support function representation for GMF functions as well as the representation of their subdifferentials. These new representations allow the ready computation of a range of important related geometric objects whose formulations were previously unavailable.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
The Novel Adaptive Fractional Order Gradient Decent Algorithms Design via Robust Control
The vanilla fractional order gradient descent may oscillatively converge to a region around the global minimum instead of converging to the exact minimum point, or even diverge, in the case where the objective function i…
Convergence Analysis of Fractional Gradient Descent
Fractional derivatives are a well-studied generalization of integer order derivatives. Naturally, for optimization, it is of interest to understand the convergence properties of gradient descent using fractional derivati…
A note on the Artstein-Avidan-Milman's generalized Legendre transforms
Artstein-Avidan and Milman [Annals of mathematics (2009), (169):661-674] characterized invertible reverse-ordering transforms on the space of lower semi-continuous extended real-valued convex functions as affine deformat…
The role of optimization geometry in single neuron learning
Recent numerical experiments have demonstrated that the choice of optimization geometry used during training can impact generalization performance when learning expressive nonlinear model classes such as deep neural netw…
A Framework for Fractional Matrix Programming Problems with Applications in FBL MU-MIMO
An efficient framework is conceived for fractional matrix programming (FMP) optimization problems (OPs) namely for minimization and maximization. In each generic OP, either the objective or the constraints are functions …