Efficient Scalable Accurate Regression Queries in In-DBMS Analytics
- Submitting institution
-
University of Glasgow
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-04244
- Type
- E - Conference contribution
- DOI
-
10.1109/ICDE.2017.111
- Title of conference / published proceedings
- IEEE International Conference on Data Engineering (ICDE)
- First page
- 559
- Volume
- -
- Issue
- -
- ISSN
- 2375-026X
- Open access status
- Technical exception
- Month of publication
- May
- Year of publication
- 2017
- URL
-
http://eprints.gla.ac.uk/136690/
- 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
-
1
- Research group(s)
-
-
- Citation count
- 7
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- ORIGINALITY: The paper proposes a novel predictive algorithm for efficient regression analytics tasks, which are provably efficient, scalable and accurate. SIGNIFICANCE: The work was published at the premier-ranked conference on Data Engineering systems and has laid the foundation of the query-driven learning methodology by fusing regression techniques over large-scale data systems. It formed the basis for an MSCA-IF award (H2020/745829). RIGOUR: The paper contains a rigorous analytical formulation of a novel query-driven machine learning method, mathematically proved to provide efficient, scalable and accurate discovery of piecewise linear dependencies in commercial Database Systems.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -