Efficient Thompson sampling for online matrix-factorization recommendation
- Submitting institution
-
The University of Warwick
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 12487
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- NIPS'15: 28th International Conference on Neural Information Processing Systems
- First page
- 1297
- Volume
- 1
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- December
- Year of publication
- 2015
- 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
-
4
- Research group(s)
-
I - Artificial Intelligence and Human-Centred Computing
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This research was published in a top-tier machine learning conference, and was later patented (ID: US10332015). It resulted from a collaboration between Tran-Thanh and Adobe Research to develop a novel technique for online matrix factorisation, based on a non-trivial application of Thompson sampling. It led to new lines of research on theoretical analyses of novel online machine learning models such as low-rank bandits (Katariya, AISTATS 2017), factorisation bandits (Li, SIGIR 2016; Wu, WWW 2019; Christakopoulou, AISTATS 2020), and new versions of Thompson sampling (Zhou, ICML 2018; Phan, NeurIPS 2019).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -