Empirical Investigation of Learning Curves: Assessing Convexity Characteristics

Nonconvexity in learning curves is almost always undesirable. A machine learning model with a non-convex learning curve either requires a larger quantity of data to observe progress in its accuracy or experiences an exponential decrease of accuracy at low sample sizes, with no improvement in accuracy even when more data points are added. This...

Inexact distributed optimization schemes: A convergence analysis using monotone operator theory

Distributed optimization has been an <br/>extensively studied field for years. Recent developments in the area of sensors makes it possible to create networks consisting of a large number of nodes. The focus of this thesis will be optimizing distributed problems over a decentralized network. These distributed optimization schemes operate in an...

Investigation of convex residual penalty functions for orbit determination

This thesis aims to assess how different convex penalty functions can be used in orbit determination methods and to design an algorithm to test them under different conditions.<br/>Most traditional Precise Orbit Determination (POD) algorithms use the Least-Squares (LSQ) method to minimise the misfit between a set of modelled and actual...