Model selection with low complexity priors
- Submitting institution
-
The University of Bath
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 189723718
- Type
- D - Journal article
- DOI
-
10.1093/imaiai/iav005
- Title of journal
- Information and Inference
- Article number
- -
- First page
- 230
- Volume
- 4
- Issue
- 3
- ISSN
- 2049-8764
- Open access status
- Out of scope for open access requirements
- Month of publication
- April
- 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
-
3
- Research group(s)
-
-
- Citation count
- 13
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Appearing in one of the top journals in applied mathematics, this paper for the first time presented a unified theory for stable model selection in inverse problems using general non-smooth convex regularisations. This theory not only encompassed popular statistical models such as lasso, fused lasso, group lasso, elastic net as particular cases, but opened doors for studying more complex regularisations later used in the machine learning, optimisation, compressed sensing and imaging sciences communities, including work by researchers at Cambridge, Edinburgh, INRIA Rennes, and RWTH Aachen.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -