Adding Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) to TFP

Hello there!

I noticed that TFP still lacks an implementation of SGHMC [1]. I would like to use it in some of my projects, and since I am already relying heavily on the TFP ecosystem, it would be very convenient if it was there. There is definitely interest in this, see Issue #361.

I am wondering whether the reason that it is not implemented yet is simply due to commitments towards more burning issues on the internal development side, or there are deeper reasons involving e.g. compatibility or planned refactoring? In case it is the former reason, I would be very happy to have a stab at implementing it, most likely following up on the suggestions made in #361. Concretely, it appears that it would be more appropriate to implement it as a tf.optimizers.Optimizer as it is done with tfp.optimizer.StochasticGradientLangevinDynamics.

Cheers,

Greg

[1] Chen, T., Fox, E., and Guestrin, C. Stochastic Gradient Hamiltonian Monte Carlo. ICML 2014.

Start by reading the suggestions in issue #361 and the existing tfp.optimizer.StochasticGradientLangevinDynamics entry point, along with the proposed tf.optimizers.Optimizer direction. Done means reaching agreement on compatibility and refactoring concerns and adding an SGHMC implementation to TFP.