Radu Herbei

About

Radu Herbei is a Professor of Statistics at The Ohio State University, having joined the faculty in 2006. His research focuses on statistical inference for stochastic processes, particularly univariate and multivariate stochastic differential equations and stochastic partial differential equations. He specializes in 'exact' inference methods that do not depend on user-selected grids or approximations, utilizing algorithms such as the Bernoulli factory to simulate exact Bernoulli random variates with unknown success probabilities. Herbei develops exact Markov chain Monte Carlo techniques that only use approximations of intractable target probability densities, with an emphasis on high-performance GPU computing to handle computationally intensive tasks. His work has been funded by NSF and ONR, reflecting its significance in the field.

Research topics

• Computer Science
• Mathematics
• Machine Learning
• Artificial Intelligence
• Statistics
• Algorithm
• Management science
• Theoretical computer science
• Programming language
• Engineering

Selected publications

• Analyzing Stochastic Computer Models: A Review with Opportunities

  Statistical Science · 2022 · 55 citations

  In modern science, computer models are often used to understand complex phenomena and a thriving statistical community has grown around analyzing them. This review aims to bring a spotlight to the growing prevalence of stochastic computer models—providing a catalogue of statistical methods for practitioners, an introductory view for statisticians (whether familiar with deterministic computer models or not), and an emphasis on open questions of relevance to practitioners and statisticians. Gaussi…

  PublisherOA PDFDOI

• Statistical inference for stochastic differential equations

  Wiley Interdisciplinary Reviews Computational Statistics · 2022 · 30 citations

  Abstract Many scientific fields have experienced growth in the use of stochastic differential equations (SDEs), also known as diffusion processes, to model scientific phenomena over time. SDEs can simultaneously capture the known deterministic dynamics of underlying variables of interest (e.g., ocean flow, chemical and physical characteristics of a body of water, presence, absence, and spread of a disease), while enabling a modeler to capture the unknown random dynamics in a stochastic setting.…

  PublisherOA PDFDOI

• Bayesian Registration of Functions With a Gaussian Process Prior

  Journal of Computational and Graphical Statistics · 2017-06-01 · 27 citations

  articleOpen access

  We present a Bayesian framework for registration of real-valued functional data. At the core of our approach is a series of transformations of the data and functional parameters, developed under a differential geometric framework. We aim to avoid discretization of functional objects for as long as possible, thus minimizing the potential pitfalls associated with high-dimensional Bayesian inference. Approximate draws from the posterior distribution are obtained using a novel Markov chain Monte Car…

  PublisherOA PDFDOI

• Modern Statistical Methods in Oceanography: A Hierarchical Perspective

  2016-08-15 · 22 citations

  article

  Processes in ocean physics, air–sea interaction and ocean biogeochemistry span enormous ranges in spatial and temporal scales, that is, from molecular to planetary and from seconds to millennia. Identifying and implementing sustainable human practices depend critically on our understandings of key aspects of ocean physics and ecology within these scale ranges. The set of all ocean data is distorted such that three- and four-dimensional (i.e., time-dependent) in situ data are very sparse, while o…

  Publisher

• Estimating Ocean Circulation: An MCMC Approach With Approximated Likelihoods via the Bernoulli Factory

  Journal of the American Statistical Association · 2014-04-24 · 20 citations

  article1st authorCorresponding

  We provide a Bayesian analysis of ocean circulation based on data collected in the South Atlantic Ocean. The analysis incorporates a reaction-diffusion partial differential equation that is not solvable in closed form. This leads to an intractable likelihood function. We describe a novel Markov chain Monte Carlo approach that does not require a likelihood evaluation. Rather, we use unbiased estimates of the likelihood and a Bernoulli factory to decide whether or not proposed states are accepted.…

  PublisherDOI

Recent grants

• Bayesian Inference via Markov Chains, Diffusion Processes, and Distributed Computing

  NSF · $150k · 2012–2017

Frequent coauthors

• Ralph F. Milliff

  Cooperative Institute for Research in Environmental Sciences

  13 shared

• Pierre Barbillon

  AgroParisTech

  10 shared

• Laura Kubatko

  The Ohio State University

  9 shared

• Christopher K. Wikle

  University of Missouri

  8 shared

• William B. Leeds

  Climate Central

  7 shared

• Pulong Ma

  6 shared

• Leah R. Johnson

  Virginia Tech

  4 shared

• Bianica Pires

  Mitre (United States)

  4 shared

Labs

• Department of Statistics, Ohio State UniversityPI

Similar researchers at Ohio State University

• Kate Huh-28
• Michelle Eversonh-22
• Eloise Kaizarh-17