AI RESEARCH
Algorithmic warm starts for Hamiltonian Monte Carlo
arXiv CS.LG
•
ArXi:2603.22741v1 Announce Type: cross Generating samples from a continuous probability density is a central algorithmic problem across statistics, engineering, and the sciences. For high-dimensional settings, Hamiltonian Monte Carlo (HMC) is the default algorithm across mainstream software packages. However, despite the extensive line of work on HMC and its widespread empirical success, it remains unclear how many iterations of HMC are required as a function of the dimension $d