UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Optimization Methods for Structured Machine Learning Problems

Tsipinakis, Nikolaos; (2019) Optimization Methods for Structured Machine Learning Problems. Doctoral thesis (Ph.D), UCL (University College London). Green open access

[img]
Preview
Text
Tsipinakis_0000_Thesis.pdf - Accepted version

Download (1MB) | Preview

Abstract

Solving large-scale optimization problems lies at the core of modern machine learning applications. Unfortunately, obtaining a sufficiently accurate solution quickly is a difficult task. However, the problems we consider in many machine learning applications exhibit a particular structure. In this thesis we study optimization methods and improve their convergence behavior by taking advantage of such structures. In particular, this thesis constitutes of two parts: In the first part of the thesis, we consider the Temporal Difference learning (TD) problem in off-line Reinforcement Learning (RL). In off-line RL, it is typically the case that the number of samples is small compared to the number of features. Therefore, recent advances have focused on efficient algorithms to incorporate feature selection via `1-regularization which effectively avoids over-fitting. Unfortunately, the TD optimization problem reduces to a fixed-point problem where convexity of the objective function cannot be assumed. Further, it remains unclear whether existing algorithms have the ability to offer good approximations for the task of policy evaluation and improvement (either they are non-convergent or do not solve the fixed-point problem). In this part of the thesis, we attempt to solve the `1- regularized fixed-point problem with the help of Alternating Direction Method of Multipliers (ADMM) and we argue that the proposed method is well suited to the structure of the aforementioned fixed-point problem. In the second part of the thesis, we study multilevel methods for large-scale optimization and extend their theoretical analysis to self-concordant functions. In particular, we address the following issues that arise in the analysis of second-order optimization methods based either on sampling, randomization or sketching: (a) the analysis of the iterates is not scale-invariant and (b) lack of global fast convergence rates without restrictive assumptions. We argue that, with the analysis undertaken in this part of the thesis, the analysis of randomized second-order methods can be considered on-par with the analysis of the classical Newton method. Further, we demonstrate how our proposed method can exploit typical spectral structures of the Hessian that arise in machine learning applications to further improve the convergence rates.

Type: Thesis (Doctoral)
Qualification: Ph.D
Title: Optimization Methods for Structured Machine Learning Problems
Event: UCL (University College London)
Open access status: An open access version is available from UCL Discovery
Language: English
Additional information: Copyright © The Author 2019. Original content in this thesis is licensed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) Licence (https://creativecommons.org/licenses/by/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms.
UCL classification: UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
URI: https://discovery.ucl.ac.uk/id/eprint/10072938
Downloads since deposit
67Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item