A
Antti Solonen
Researcher at Lappeenranta University of Technology
Publications - 45
Citations - 1218
Antti Solonen is an academic researcher from Lappeenranta University of Technology. The author has contributed to research in topics: Markov chain Monte Carlo & Inverse problem. The author has an hindex of 17, co-authored 43 publications receiving 1060 citations. Previous affiliations of Antti Solonen include Massachusetts Institute of Technology & Finnish Meteorological Institute.
Papers
More filters
Journal ArticleDOI
Optimal low-rank approximations of Bayesian linear inverse problems
TL;DR: In this paper, a low-rank update of the prior covariance matrix is proposed to characterize and approximate the posterior distribution of the parameters in inverse problems, based on the leading eigendirections of the matrix pencil defined by the Hessian of the negative log-likelihood and the prior precision.
Journal ArticleDOI
Randomize-Then-Optimize: A Method for Sampling from Posterior Distributions in Nonlinear Inverse Problems
TL;DR: High-dimensional inverse problems present a challenge for Markov chain Monte Carlo (MCMC)-type sampling schemes that rely on finding an efficient proposal distribution, which can be dif...
Journal ArticleDOI
Likelihood-informed dimension reduction for nonlinear inverse problems
TL;DR: In this paper, a likelihood-informed subspace (LIS) is defined and identified by characterizing the relative influences of the prior and the likelihood over the support of the posterior distribution, which enables more efficient computational methods for Bayesian inference with nonlinear forward models and Gaussian priors.
Journal ArticleDOI
Likelihood-informed dimension reduction for nonlinear inverse problems
TL;DR: In this paper, the authors proposed an approach to solve the problem of distributed computing with the U.S. Dept. of Energy grant DE-SC0003908 (US Dept. Office of Advanced Scientific Computing Research).
Journal ArticleDOI
Efficient MCMC for Climate Model Parameter Estimation: Parallel Adaptive Chains and Early Rejection
TL;DR: An early rejection (ER) approach, where model simulation is stopped as soon as one can conclude that the proposed parameter value will be rejected by the MCMC algorithm, is presented.