End-to-End Deep Learning of Optimization Heuristics
- Submitting institution
-
The University of Leeds
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- UOA11-4033
- Type
- E - Conference contribution
- DOI
-
10.1109/PACT.2017.24
- Title of conference / published proceedings
- 2017 26th International Conference on Parallel Architectures and Compilation Techniques (PACT)
- First page
- 219
- Volume
- -
- Issue
- -
- ISSN
- 1089-795X
- Open access status
- Technical exception
- Month of publication
- November
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
E - DSS (Distributed Systems and Services)
- Citation count
- 18
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Won the single Best paper award in PACT-17 (1 out 108 submissions). Develops an end-to-end approach for constructing compiler heuristics, offering a huge reduction in development effort. Was the mostly-downloaded paper of the proceeding on IEEE explore (as of 08/2020), and the top-20 most frequently accessed articles of all papers published over the last 28 years of the conference series between 2019 and 2020. Helped to secure a RAEng Research Fellowship, a Royal Society collaboration grant, industry research investment for over £330K for follow-up work. Part of a thesis that won the 2020 SICSA Best PhD Dissertation award.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
