Robust and rate-optimal Gibbs posterior inference on the boundary of a noisy image (Q2196231)

The authors develop a robust Gibbsian approach that constructs a posterior distribution for the image boundary directly, without modeling the pixel intensities. With this approach, adaptive to the boundary smoothness, the Gibbs posterior concentrates asymptotically at the minimax optimal rate. Monte Carlo computation of the Gibbs posterior is straightforward, and simulation results show that the corresponding inference is more accurate than that based on existing Bayesian methodology.