Abstract: Phase retrieval is an inverse problem which consists in recovering an unknown signal from a set of absolute squared projections. Recently, gradient descent algorithms have been developed to ...

This repository contains PyTorch code for the Sparse Label Smoothing Regularization (SparseLSR) loss function proposed in the paper "Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning" ...

Abstract: Many effective algorithms have been proposed for the global optimization problems arisen in various practical fields. However, some of these problems exist many local optima, which may lead ...

A procedure is described for smoothing a convex function which not only preserves its convexity, but also, under suitable conditions, leaves the function unchanged over nearly all the regions where it ...

Smoothness penalties are efficient regularization and dimension reduction tools for functional regressions. However, for spiky functional data observed on a dense grid, the coefficient function in a ...

However, when specialized to quadratic function, conjugate gradient is optimal in a strong sense among function-gradient methods. Therefore, there is seemingly a gap in the menu of available ...