We have formalized the paper "Bounding the Sum of Supports in the Transient of Accelerated Proximal Gradient via a Margin Parameter". The main results are: 1. `sum_support_transient`: Bounds the sum ...

This repository contains the implementation and experiments for my MSc Data Science thesis on Exploration of Accelerated Stochastic Gradient Methods for Least Squares Problems. It includes Python ...

Abstract: Federated Learning (FL) is widely used in mobile computing as a communication-efficient distributed machine learning (ML) paradigm; however, it faces challenges such as model convergence to ...

Abstract: Most distributed optimization methods used for distributed model predictive control (DMPC) are gradient based. Gradient based optimization algorithms are known to have iterations of low ...

ABSTRACT: Proximal gradient descent and its accelerated version are resultful methods for solving the sum of smooth and non-smooth problems. When the smooth function can be represented as a sum of ...