Timeline for What are the primary advantages of using Kernels in predicting continuous outcomes?
Current License: CC BY-SA 3.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 16, 2016 at 11:09 | vote | accept | tomka | ||
| Oct 10, 2016 at 23:05 | history | tweeted | twitter.com/StackStats/status/785617297536872448 | ||
| Oct 10, 2016 at 21:59 | answer | added | Joseph Santarcangelo | timeline score: 3 | |
| Oct 10, 2016 at 21:46 | comment | added | Sycorax♦ | Basically. You could cross-validate. On the other hand, you could explicitly model hyperparameters, with MCMC or a variant to average out the effect of alternative hyperparameters. Usually people assume that the RBF kernel is "good enough" and get on with their lives (cf "no one ever got fired for running OLS regression"), but there are a rich diversity of options. There's a good discussion in Gaussian Processes for Machine Learning and also Gelman's BDA3. | |
| Oct 10, 2016 at 21:41 | comment | added | tomka | @Sycorax So the idea is to find a better - nonlinear - representation of the data by smartly choosing Kernels? And the choice is perhaps guided by cross-validation? And that's it? | |
| Oct 10, 2016 at 21:39 | comment | added | Sycorax♦ | This regression will provide a smooth (and exact, if there's no error) interpolation between the observed data points; how and how sharply the function changes between the data points is informed by the choice of kernel and kernel hyper-parameters. | |
| Oct 10, 2016 at 21:39 | history | edited | tomka | CC BY-SA 3.0 |
edited body
|
| Oct 10, 2016 at 21:38 | comment | added | EngrStudent | On a uniform domain, for non-sick domain sizes, the inverse is relatively cheap. Also, it only has to be computed once. | |
| Oct 10, 2016 at 21:31 | history | asked | tomka | CC BY-SA 3.0 |