1. 06 Apr, 2021 1 commit
    • Jeremiah Liu's avatar
      Disable temperature scaling during training. · fab47e9e
      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
      fab47e9e
  2. 05 Apr, 2021 12 commits
  3. 04 Apr, 2021 1 commit
  4. 03 Apr, 2021 1 commit
  5. 02 Apr, 2021 9 commits
  6. 01 Apr, 2021 6 commits
  7. 31 Mar, 2021 3 commits
  8. 30 Mar, 2021 7 commits