seminars:stat:191114
Differences
This shows you the differences between two versions of the page.
| Next revision | Previous revision | ||
| seminars:stat:191114 [2019/10/31 11:44] – created qyu | seminars:stat:191114 [2019/11/13 17:58] (current) – qyu | ||
|---|---|---|---|
| Line 1: | Line 1: | ||
| + | <WRAP centeralign>## | ||
| + | |||
| + | <WRAP 70% center> | ||
| + | ^ **DATE: | ||
| + | ^ **TIME: | ||
| + | ^ **LOCATION: | ||
| + | ^ **SPEAKER: | ||
| + | ^ **TITLE: | ||
| + | </ | ||
| + | \\ | ||
| + | |||
| + | <WRAP center box 80%> | ||
| + | <WRAP centeralign> | ||
| + | Conformal prediction uses past experience to determine | ||
| + | precise levels of confidence in new predictions. The proposed methodology | ||
| + | allows for the construction of a distribution-free prediction bands for | ||
| + | the response variable using any algorithm. The resulting prediction bands | ||
| + | preserves marginal coverage guarantee, where predictive coverage holds on | ||
| + | average over all possible test points, but is not sufficient for many | ||
| + | practical applications. We aim to produce predictive conditional coverage | ||
| + | rather than marginally with certain types of constrains and assumptions, | ||
| + | while still being possible to achieve in a distribution-free setting. | ||
| + | |||
| + | </ | ||
| + | |||
| + | |||
| + | |||
| + | |||
