CODEWITHSUNDEEP
tensorflow-probability
safetyduck
safetyduck

Reputation: 6874

In tensorflow probabiliy, is there a vanilla "Dense" bijector?

For example, consider a bunch of layers "a traditional keras model". One might put a prior on the weights, a prior on the data in or out. If the Dense network is a bijector, a lot of stuff is handled magically. Looks like Affine and some other layers will allow one to build this manually. There is DenseVariational but that uses a surogate posterior.

Upvotes: 0

Views: 95

Answers (1)

Brian Patton
Brian Patton

Reputation: 1076

A traditional Dense layer is not bijective. tfb.Affine with a scale_tril parameterization (and optionally a shift to act like a bias) is the bijective equivalent. Can you say more about what you're trying to achieve?

Upvotes: 2

Related Questions