Hamiltonian Monte Carlo Methods in Machine Learning

Presents in-depth Hamiltonian Monte Carlo methods for Machine Learning, one of the most influential algorithms for today's scientific practice

Tshilidzi Marwala (Author), Rendani Mbuvha (Author), Wilson Tsakane Mongwe (Author)

9780443190353, Elsevier Science

Paperback / softback, published 16 February 2023

220 pages
23.5 x 19 x 1.5 cm, 0.45 kg

Hamiltonian Monte Carlo Methods in Machine Learning introduces methods for optimal tuning of HMC parameters, along with an introduction of Shadow and Non-canonical HMC methods with improvements and speedup. Lastly, the authors address the critical issues of variance reduction for parameter estimates of numerous HMC based samplers. The book offers a comprehensive introduction to Hamiltonian Monte Carlo methods and provides a cutting-edge exposition of the current pathologies of HMC-based methods in both tuning, scaling and sampling complex real-world posteriors. These are mainly in the scaling of inference (e.g., Deep Neural Networks), tuning of performance-sensitive sampling parameters and high sample autocorrelation.

1. Introduction to Hamiltonian Monte Carlo 2. Sampling Benchmarks and Performance Metrics 3. Stochastic Volatility Metropolis-Hastings 4. Quantum-Inspired Magnetic Hamiltonian Monte Carlo 5. Generalised Magnetic and Shadow Hamiltonian Monte Carlo 6. Shadow Hamiltonian Monte Carlo Methods 7. Adaptive Shadow Hamiltonian Monte Carlo Methods 8. Adaptive Noncanonical Hamiltonian Monte Carlo 9. Antithetic Hamiltonian Monte Carlo Techniques 10. Application: Bayesian Neural Network Inference in Wind Speed Forecasting 11. Application: A Bayesian Analysis of Lockdown Alert Level Framework for Combating COVID-19 12. Application: Probabilistic Inference of Equity Option Prices Under Jump-Di 13. Application: Bayesian Inference of Local Government Audit Outcomes 14. Open Problems in Sampling

Subject Areas: Machine learning [UYQM]