Use this URL to cite or link to this record in EThOS: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.813632
Title: Between integrals and optima : new methods for scalable machine learning
Author: Maddison, Christopher
ISNI:       0000 0004 9351 5213
Awarding Body: University of Oxford
Current Institution: University of Oxford
Date of Award: 2020
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Abstract:
The success of machine learning is due in part to the effectiveness of scalable computational methods, like stochastic gradient descent or Monte Carlo methods, that undergird learning algorithms. This thesis contributes four new scalable methods for distinct problems that arise in machine learning. It introduces a new method for gradient estimation in discrete variable models, a new objective for maximum likelihood learning in the presence of latent variables, and two new gradient-based differentiable optimization methods. Although quite different, these contributions address distinct, critical parts of a typical machine learning workflow. Furthermore, each contribution is inspired by an interplay between the numerical problems of optimization and integration, an interplay that forms the central theme of this thesis.
Supervisor: Doucet, Arnaud ; Teh, Yee Whye Sponsor: DeepMind
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.813632  DOI: Not available
Keywords: Machine Learning
Share: