Avoiding Random Walks
More sophisticated algorithms use some method of preventing the walker from doubling back. These algorithms may be harder to implement, but may exhibit faster convergence (i.e. fewer steps for an accurate result).
- Successive over-relaxation: A Monte Carlo version of this technique can be seen as a variation on Gibbs sampling; it sometimes avoids random walks.
- Hybrid Monte Carlo (HMC): Tries to avoid random walk behaviour by introducing an auxiliary momentum vector and implementing Hamiltonian dynamics where the potential energy function is the target density. The momentum samples are discarded after sampling. The end result of Hybrid MCMC is that proposals move across the sample space in larger steps and are therefore less correlated and converge to the target distribution more rapidly.
- Some variations on slice sampling also avoid random walks.
- Langevin MCMC and other methods that rely on the gradient (and possibly second derivative) of the log posterior avoid random walks by making proposals that are more likely to be in the direction of higher probability density.
Read more about this topic: Markov Chain Monte Carlo
Famous quotes containing the words avoiding, random and/or walks:
“Caring for children is a dance between setting appropriate limits as caretakers and avoiding unnecessary power struggles that result in unhappiness.”
—Charlotte Davis Kasl (20th century)
“It is a secret from nobody that the famous random event is most likely to arise from those parts of the world where the old adage “There is no alternative to victory” retains a high degree of plausibility.”
—Hannah Arendt (1906–1975)
“But who walks with Him? dares to take His arm,
To slap Him on the shoulder, tweak His ear,
Buy Him a Coca-Cola or a beer,
Pooh-pooh His politics, call Him a fool?”
—Gwendolyn Brooks (b. 1917)