A linear-time kernel goodness-of-fit test
- Submitting institution
-
University College London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 16210
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Advances in Neural Information Processing Systems
- First page
- 262
- Volume
- 2017-December
- Issue
- -
- ISSN
- 1049-5258
- Open access status
- Compliant
- Month of publication
- December
- 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
-
4
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Selected for oral presentation (1.2% of submissions 2017). Winner, best paper award. An adaptive, linear-time, nonparametric test of goodness of fit for statistical models. Previous tests were quadratic time; or required the normalising constant of the models to be known (often impossible for interesting models), or were not interpretable. The proposed test is much faster, interpretable, yet still more powerful than earlier tests. The new test was provably better than the previous state-of-the-art linear time test, for practically applicable problem settings. The first author won the ELLIS PhD award for this work, and is now at Google Brain.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -