Algorithm-dependent generalization bounds for multi-task learning
- Submitting institution
-
Birkbeck College
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 176
- Type
- D - Journal article
- DOI
-
10.1109/TPAMI.2016.2544314
- Title of journal
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Article number
- -
- First page
- 227
- Volume
- 39
- Issue
- 2
- ISSN
- 0162-8828
- Open access status
- Out of scope for open access requirements
- Month of publication
- March
- Year of publication
- 2016
- URL
-
http://eprints.bbk.ac.uk/id/eprint/14689/
- 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)
-
2 - Experimental Data Science
- Citation count
- 68
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper is the first to assess the learning of individual tasks within multi-task learning. The paper supported Liu’s successful application for funding for the Australian Research Council Project DE 190101743, and the short-listing of Liu for the J.G. Russell Award by the Australian Academy of Science (2019).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -