Thesis icon

Thesis

Spectral machine learning

Abstract:

In this thesis we develop a spectral approach to large kernel matrices, graphs and the Hessians of neural networks. This approach paves the way for efficient and improved inference schemes, novel algorithms and theoretical results. The first contribution of the thesis is the development of a novel Maximum Entropy algorithm applied to the problems of log determinant estimation (necessitated by Bayesian model selection), cluster counting and graph similarity. The method produces strong empirica...

Expand abstract

Actions


Access Document


Files:

Authors


More by this author
Division:
MPLS
Department:
Engineering Science
Role:
Author

Contributors

Role:
Supervisor
Type of award:
DPhil
Level of award:
Doctoral
Awarding institution:
University of Oxford

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP