Devon R. Graham
I study Artificial Intelligence and Machine Learning at the University of British Columbia, where I am working towards a PhD under Professor Kevin Leyton-Brown. Algorithms that come with internal parameters can often be sped up considerably with proper tuning. My work focuses on how to find automated procedures to choose these parameters so that the underlying algorithm performs well on typical future inputs. I am interested in using tools from economics, statistics and information theory to help improve this search process, and to reconsider exactly what "performs well" should mean. I completed my MSc, also at UBC, under Assistant Professor Siamak Ravanbakhsh. My research focused on applying Deep Learning methods to data from structured domains such as graphs or tensors, where the structure of the data helps to inform the learning model.
Publications
Utilitarian Algorithm Configuration
Devon R. Graham, Kevin Leyton-Brown, and Tim Roughgarden. NeurIPS, 2023.
pdf |
arXiv |
bibtex |
poster
Formalizing Preferences Over Runtime Distributions
Devon R. Graham, Kevin Leyton-Brown, and Tim Roughgarden. ICML, 2023.
pdf |
arXiv |
bibtex |
poster
ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool
Gellért Weisz, András György, Wei-I Lin, Devon Graham, Kevin Leyton-Brown, Csaba Szepesvári, Brendan Lucier. NeurIPS, 2020.
pdf |
bibtex |
data
Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration
Robert Kleinberg, Kevin Leyton-Brown, Brendan Lucier, and Devon Graham. NeurIPS, 2019.
pdf |
arXiv |
bibtex |
poster
Equivariant Entity-Relationship Networks
Devon Graham, Junhao Wang and Siamak Ravanbakhsh.
arXiv, 2019.
pdf |
arXiv |
bibtex
Deep Models of Interactions Across Sets
Jason Hartford*, Devon R. Graham*, Kevin Leyton-Brown, and Siamak Ravanbakhsh.
ICML, 2018.
pdf |
arXiv |
bibtex |
poster
Teaching
- Guest Lecturer (with Bobby Kleinberg):
- Caltech CS 159 - Data-Driven Algorithm Design (Professor Yisong Yue) - May 26th, 2020
-
Teaching Assistant, University of British Columbia:
- CPSC 340 - Machine Learning and Data Mining - Fall 2018
- CPSC 320 - Intermediate Algorithm Design and Analysis - Summer 2018
- CPSC 213 - Introduction to Computer Systems - Summer 2017
- CPSC 313 - Computer Hardware and Operating Systems - Spring 2017
- CPSC 421 - Introduction to Theory of Computing - Fall 2016
- CPSC 421 - Parallel Computation - Winter 2017, Fall 2017, Winter 2016
- CPSC 221 - Basic Algorithms and Data Structures - Spring 2018, Winter 2015, Fall 2015, Spring 2015
- Nominated for Killam Graduate TA Award, 2018.
- Recipient of Graduate TA Award, UBC Department of Computer Science, 2017.
Education
-
I have taken the following graduate-level courses at UBC:
- CPSC 532L - Artificial Intelligence for Social Impact - Winter 2019
- CPSC 532R - Probabilistic Graphical Models - Winter 2018
- CPSC 536E - Graph Drawing - Winter 2018
- CPSC 531H - Machine Learning Theory - Fall 2018
- CPSC 539W - Probabilistic Programming - Fall 2018
- CPSC 536N - Algorithms that Matter - Winter 2017
- CPSC 540 - Machine Learning - Winter 2017
- CPSC 506 - Complexity of Computation - Fall 2016
- CPSC 536F - Algorithmic Game Theory - Fall 2016
- MATH 503 - Discrete Mathematics - Fall 2016
Contact
Department of Computer Science
UNIVERSITY OF BRITISH COLUMBIA
ICICS X568 - 2366 Main Mall
Vancouver, B.C.
V6T 1Z4
Canada
E-mail: 
