A couple of years ago I learned about recent work in parallelizing slice sampling methods. More recently, I have read great things about NUTS and Hamiltonian Monte Carlo methods (HMC) in general (e.g. pymc3 uses NUTS) This makes me wonder:
- What are NUTS and HMC particularly good for? Can they benefit from parallelization as much as, e.g. slice sampling?
- How do they compare to elliptical slice sampling and other methods in general?