AITopics | curvature and hamiltonian monte carlo

Collaborating Authors

curvature and hamiltonian monte carlo

Information about AI from the News, Publications, and Conferences

Automatic Classification – Tagging and Summarization – Customizable Filtering and Analysis

If you are looking for an answer to the question What is Artificial Intelligence? and you only have a minute, then here's the definition the Association for the Advancement of Artificial Intelligence offers on its home page: "the scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines."

However, if you are fortunate enough to have more than a minute, then please get ready to embark upon an exciting journey exploring AI (but beware, it could last a lifetime) …

Positive Curvature and Hamiltonian Monte Carlo

Seiler, Christof, Rubinstein-Salzedo, Simon, Holmes, Susan

Neural Information Processing SystemsFeb-14-2020, 06:12:15 GMT

The Jacobi metric introduced in mathematical physics can be used to analyze Hamiltonian Monte Carlo (HMC). Our calculation of the sectional curvature of this HMC manifold allows us to see that it is positive in cases such as sampling from a high dimensional multivariate Gaussian. We show that positive curvature can be used to prove theoretical concentration results for HMC Markov chains. Papers published at the Neural Information Processing Systems Conference.

curvature and hamiltonian monte carlo, hamiltonian monte carlo, jacobi metric

Neural Information Processing Systems

Technology: Information Technology > Artificial Intelligence > Machine Learning (0.83)

Add feedback