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 2 commits
  3. 01 Apr, 2021 3 commits
  4. 25 Mar, 2021 1 commit
  5. 24 Mar, 2021 1 commit
  6. 22 Mar, 2021 4 commits
  7. 20 Mar, 2021 1 commit
  8. 17 Mar, 2021 1 commit
  9. 16 Mar, 2021 2 commits
  10. 12 Mar, 2021 3 commits
  11. 10 Mar, 2021 1 commit
  12. 09 Mar, 2021 1 commit
  13. 08 Mar, 2021 1 commit
  14. 04 Mar, 2021 2 commits
  15. 02 Mar, 2021 1 commit
  16. 26 Feb, 2021 2 commits
  17. 23 Feb, 2021 1 commit
  18. 19 Feb, 2021 1 commit
  19. 17 Feb, 2021 1 commit
  20. 16 Feb, 2021 2 commits
  21. 28 Jan, 2021 1 commit
  22. 25 Jan, 2021 1 commit
  23. 19 Jan, 2021 1 commit
  24. 14 Jan, 2021 2 commits
  25. 12 Jan, 2021 2 commits
  26. 11 Jan, 2021 1 commit