We present a novel and flexible framework for localized tuning of Hamiltonian Monte Carlo (HMC) samplers by Gibbs sampling the algorithm's tuning parameters conditionally based on the position and momentum at each step. For adaptively sampling path lengths, the framework encompasses randomized HMC, multinomial HMC, the No-U-Turn Sampler (NUTS), and the Apogee-to-Apogee Path Sampler as special cases. The Gibbs self-tuning (GIST) framework is illustrated with an alternative to NUTS for locally adapting path lengths, evaluated with an exact Hamiltonian for an ill-conditioned normal and with the leapfrog algorithm for a test suite of diverse models.
翻译:暂无翻译