Publications
Detailed Information
Self-Discrepancy Conditional Independence Test
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Sanghack | - |
dc.contributor.author | Honavar, Vasant | - |
dc.date.accessioned | 2024-05-13T05:11:44Z | - |
dc.date.available | 2024-05-13T05:11:44Z | - |
dc.date.created | 2024-05-13 | - |
dc.date.issued | 2017 | - |
dc.identifier.citation | CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE (UAI2017) | - |
dc.identifier.uri | https://hdl.handle.net/10371/201563 | - |
dc.description.abstract | Tests of conditional independence (CI) of random variables play an important role in machine learning and causal inference. Of particular interest are kernel-based CI tests which allow us to test for independence among random variables with complex distribution functions. The efficacy of a CI test is measured in terms of its power and its calibratedness. We show that the Kernel CI Permutation Test (KCIPT) suffers from a loss of calibratedness as its power is increased by increasing the number of bootstraps. To address this limitation, we propose a novel CI test, called Self-Discrepancy Conditional Independence Test (SDCIT). SDCIT uses a test statistic that is a modified unbiased estimate of maximum mean discrepancy (MMD), the largest difference in the means of features of the given sample and its permuted counterpart in the kernel-induced Hilbert space. We present results of experiments that demonstrate SDCIT is, relative to the other methods: (i) competitive in terms of its power and calibratedness, outperforming other methods when the number of conditioning variables is large; (ii) more robust with respect to the choice of the kernel function; and (iii) competitive in run time. | - |
dc.language | 영어 | - |
dc.publisher | AUAI PRESS | - |
dc.title | Self-Discrepancy Conditional Independence Test | - |
dc.type | Article | - |
dc.citation.journaltitle | CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE (UAI2017) | - |
dc.identifier.wosid | 000493309500004 | - |
dc.identifier.scopusid | 2-s2.0-85031121897 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Lee, Sanghack | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.