- 06 Apr, 2021 2 commits
-
-
Jeremiah Liu authored
For the `GaussianProcessClassificationHead`, the temperature scaling needs to be disabled during training to avoid unexpected modification to the learning rate, which harms model quality. (Unfortunately, this seems to require adding `training` to the `call` method). Also set the default of `gp_cov_ridge_penalty` in `RandomFeatureGaussianProcess` to 1 to be consistent with that in the `GaussianProcessClassificationHead`. PiperOrigin-RevId: 366917075
-
Jeremiah Liu authored
For the `GaussianProcessClassificationHead`, the temperature scaling needs to be disabled during training to avoid unexpected modification to the learning rate, which harms model quality. (Unfortunately, this seems to require adding `training` to the `call` method). Also set the default of `gp_cov_ridge_penalty` in `RandomFeatureGaussianProcess` to 1 to be consistent with that in the `GaussianProcessClassificationHead`. PiperOrigin-RevId: 366917075
-
- 01 Apr, 2021 4 commits
-
-
Jeremiah Liu authored
PiperOrigin-RevId: 366178203
-
Jeremiah Liu authored
PiperOrigin-RevId: 366178203
-
Jeremiah Liu authored
PiperOrigin-RevId: 366175727
-
Jeremiah Liu authored
PiperOrigin-RevId: 366175727
-
- 20 Mar, 2021 2 commits
-
-
Jeremiah Liu authored
PiperOrigin-RevId: 364109398
-
Jeremiah Liu authored
PiperOrigin-RevId: 364109398
-