Name
Abstract | ||
|---|---|---|
Given two candidate models, and a set of target observations, we address the problem of measuring the relative goodness of fit of the two models. We propose two new statistical tests which are nonparametric, computationally efficient (runtime complexity is linear in the sample size), and interpretable. As a unique advantage, our tests can produce a set of examples (informative features) indicating the regions in the data domain where one model fits significantly better than the other. In a real-world problem of comparing GAN models, the test power of our new test matches that of the state-of-the-art test of relative goodness of fit, while being one order of magnitude faster. |
Year | Venue | Keywords |
|---|---|---|
2018 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018) | computationally efficient,a set,sample size,natural language,model comparison,test matches,goodness of fit,statistical tests,test power |
DocType | Volume | ISSN |
Conference | 31 | 1049-5258 |
Citations | PageRank | References |
1 | 0.36 | 19 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jitkrittum, Wittawat | 1 | 1 | 0.36 |
| Heishiro Kanagawa | 2 | 6 | 2.12 |
| Patsorn Sangkloy | 3 | 143 | 5.60 |
| James Hays | 4 | 3942 | 172.72 |
| Bernhard Schölkopf | 5 | 23120 | 3091.82 |
| Arthur Gretton | 6 | 3638 | 226.18 |