
HMC, an example of Functional Analysis applied to Algorithms in Data Mining. The convergence in L^p
We present a proof of convergence of the Hamiltonian Monte Carlo algorit...
read it

Nonparametric Hamiltonian Monte Carlo
Probabilistic programming uses programs to express generative models who...
read it

Hamiltonian Monte Carlo with Asymmetrical Momentum Distributions
Existing rigorous convergence guarantees for the Hamiltonian Monte Carlo...
read it

How to lose at Monte Carlo: a simple dynamical system whose typical statistical behavior is non computable
We consider the simplest nonlinear discrete dynamical systems, given by...
read it

Convergence Rate of Riemannian Hamiltonian Monte Carlo and Faster Polytope Volume Computation
We give the first rigorous proof of the convergence of Riemannian Hamilt...
read it

Concentration without measure
Although there doesn't exist the Lebesgue measure in the ball M of C[0,1...
read it

Probability distributions for analogtotarget distances
Some properties of chaotic dynamical systems can be probed through featu...
read it
HMC, an Algorithms in Data Mining, the Functional Analysis approach
The main purpose of this paper is to facilitate the communication between the Analytic, Probabilistic and Algorithmic communities. We present a proof of convergence of the Hamiltonian (Hybrid) Monte Carlo algorithm from the point of view of the Dynamical Systems, where the evolving objects are densities of probability distributions and the tool are derived from the Functional Analysis.
READ FULL TEXT
Comments
There are no comments yet.