IEEE

Convergence analysis of distributed subgradient methods over random networks

Abstract: We consider the problem of cooperatively minimizing the sum of convex functions, where the functions represent local objective functions of the agents. We assume that each agent has ...
IEEE

Convergence Analysis of a Randomized Incremental Subgradient Method on Riemannian Manifolds

Abstract: This study presents and examines a randomized incremental subgradient algorithm designed to tackle convex optimization problems on Riemannian manifolds. The objective function comprises ...
Europe PMC

A Subgradient Projection Method for Quasiconvex Minimization

In this paper, a subgradient projection method for quasiconvex minimization problems is provided. By using strong subdifferentials, it is proved that the generated sequence of the proposed algorithm ...
Imperial College London

Nicolas Loizou (Johns Hopkins University): Next-Generation Adaptive Optimization Algorithms for Large-Scale Machine Learning Models

Stochastic gradient descent (SGD) is the workhorse for training modern large-scale supervised machine learning models. In this talk, we will discuss recent developments in the convergence analysis of ...