Thesis icon

Thesis

Mirror descent for high-dimensional statistical models

Abstract:

As vast amounts of data are being produced and processed in various fields of science and engineering, optimizing high-dimensional statistical models has become a ubiquitous task in many modern applications. Often, it is crucial to exploit underlying low-dimensional structures to extract useful information from high-dimensional data and models. To this end, numerous optimization algorithms such as gradient descent and its variants have been extensively studied both empirically and theoreti...

Expand abstract

Actions


Access Document


Files:

Authors


More by this author
Division:
MPLS
Department:
Statistics
Sub department:
Statistics
Oxford college:
St Peter's College
Role:
Author

Contributors

Institution:
University of Oxford
Division:
MPLS
Department:
Statistics
Sub department:
Statistics
Oxford college:
University College
Role:
Supervisor
ORCID:
0000-0001-7772-4160
More from this funder
Name:
Engineering and Physical Sciences Research Council and Medical Research Council Centre for Doctoral Training in Next Generation Statistical Science
Grant:
EP/L016710/1
Programme:
The Oxford-Warwick Statistics Programme
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