A Stein Gradient Descent Approach for Doubly Intractable Distributions

#professional #STEM #technology #data-analysis #modeling #application #methods #sim
Share

Title: A Stein Gradient Descent Approach for Doubly Intractable Distributions

Dr. Jaewoo Park

Assistant Professor, Department of Applied Statistics

Yonsei University

   

Friday, January 23rd, 2026  

11:00 A.M. – 12:00 P.M. Eastern Time  

Nguyen Engineering Building, Jajodia Auditorium, Room 1101  

4511 Patriot Circle, Fairfax, Virginia 22030 

The seminar talk is also live-streamed. Please register to receive the link. 

 

Abstract:  

Bayesian inference for doubly intractable distributions is challenging because they include intractable terms, which are functions of parameters of interest. Although several alternatives have been developed for such models, they are computationally intensive due to repeated auxiliary variable simulations. We propose a novel Monte Carlo Stein variational gradient descent (MC-SVGD) approach for inference for doubly intractable distributions. Through an efficient gradient approximation, our MC-SVGD approach rapidly transforms an arbitrary reference distribution to approximate the posterior distribution of interest, without necessitating any predefined variational distribution class for the posterior. Such a transport map is obtained by minimizing Kullback-Leibler divergence between the transformed and posterior distributions in a reproducing kernel Hilbert space (RKHS). We also investigate the convergence rate of the proposed method. We illustrate the application of the method to challenging examples, including a Potts model, an exponential random graph model, and a Conway--Maxwell--Poisson regression model. The proposed method achieves substantial computational gains over existing algorithms, while providing comparable inferential performance for the posterior distributions.

 

Bio:  

Jaewoo Park is an Assistant Professor in the Department of Applied Statistics at Yonsei University. His research focuses on computational methods for intractable likelihoods, Bayesian modeling for spatio-temporal data, and spatial functional data analysis.



  Date and Time

  Location

  Hosts

  Registration



  • Add_To_Calendar_icon Add Event to Calendar
  • George Mason University
  • Fairfax, Virginia
  • United States 22030
  • Building: Nguyen Engineering Building,
  • Room Number: Jajodia Auditorium, Room 1101 

  • Contact Event Host