Interpreting and Improving on Unsupervised Learning Algorithms
PhD defence, Monday November 4th 2024, Andrew Draganov
During his PhD, Andrew analyzed essential techniques in the data-analysis toolkit. Namely, Andrew studied how to interpret those algorithms which are used commonly to cluster and visualize datasets and helped improve on theoretical methods for compressing and processing datasets. Along the way, Andrew drew connections between the theoretical properties of various datasets and how algorithms can leverage these properties.
The PhD study was completed at the Department of Computer Science, Faculty of Natural Sciences, Aarhus University.
This summary was prepared by the PhD student.
Time: Monday 4 November 2024 10.00
Place: 5335, room 295 (Nygaard), Department of Computer Science, Åbogade 34 , 8200 Aarhus N
Title of dissertation: Bridging the Gap Between Theory and Practice in Unsupervised Learning
Contact information: Andrew Draganov, e-mail: draganovandrew@cs.au.dk, tel.: +45 5261 6873
Members of the assessment committee:
Assistant Professor Michael Schaub, RWTH Aachen University, Department of Computer Science, Germany
Assistant Professor Morteza Monemizadeh, TU Eindhoven, Department of Mathematics and Computer Science, The Netherlands
Chair: Associate Professor Peyman Afshani, Department of Computer Science, Aarhus University
Main supervisor:
Associate Professor Chris Schwiegelshohn, Department of Computer Science, Aarhus University, Denmark
Co-supervisor:
Assistant Professor Cigdem Aslay, Department of Computer Science, Aarhus University, Denmark
Language: The PhD dissertation will be defended in English
The defence is public.
The PhD thesis is available for reading at the Graduate School of Natural Sciences/GSNS, Ny Munkegade 120, building 1521, 8000 Aarhus C.