# `Tinkex.Regularizers.GradientPenalty`
[🔗](https://github.com/North-Shore-AI/tinkex/blob/v0.4.0/lib/tinkex/regularizers/gradient_penalty.ex#L1)

Gradient penalty adapter built on NxPenalties primitives.

Modes:
  * `:output` - Penalize gradient norm w.r.t. current logprobs
  * `:interpolated` - WGAN-GP style penalty between logprobs and a reference

---

*Consult [api-reference.md](api-reference.md) for complete listing*