activity
20162022
most citedLocal Regularization of Noisy Point Clouds: Improved Global Geometric Estimates and Data Analysis

8 citations · 19 across the 7 of their papers we have counts for

collaborators

12 papers

stat.CO2022

Hierarchical Ensemble Kalman Methods with Sparsity-Promoting Generalized Gamma Hyperpriors

Hwanwoo Kim, Daniel Sanz-Alonso, Alexander Strang

This paper introduces a computational framework to incorporate flexible regularization techniques in ensemble Kalman methods for nonlinear inverse problems. The proposed methodolog…

stat.ML20212 cited

Auto-differentiable Ensemble Kalman Filters

Yuming Chen, Daniel Sanz-Alonso, Rebecca Willett

Data assimilation is concerned with sequentially estimating a temporally-evolving state. This task, which arises in a wide range of scientific and engineering applications, is part…

math.NA20202 cited

Iterative Ensemble Kalman Methods: A Unified Perspective with Some New Variants

Neil K. Chada, Yuming Chen, Daniel Sanz-Alonso

This paper provides a unified perspective of iterative ensemble Kalman methods, a family of derivative-free algorithms for parameter reconstruction and other related tasks. We iden…

stat.CO2020

Bayesian Update with Importance Sampling: Required Sample Size

Daniel Sanz-Alonso, Zijian Wang

Importance sampling is used to approximate Bayes' rule in many computational approaches to Bayesian inverse problems, data assimilation and machine learning. This paper reviews and…

stat.CO2020

Data-Driven Forward Discretizations for Bayesian Inversion

Daniele Bigoni, Yuming Chen, Nicolas Garcia Trillos +2

This paper suggests a framework for the learning of discretizations of expensive forward models in Bayesian inverse problems. The main idea is to incorporate the parameters governi…

stat.CO2019

HMC: avoiding rejections by not using leapfrog and some results on the acceptance rate

M. P. Calvo, D. Sanz-Alonso, J. M. Sanz-Serna

The leapfrog integrator is routinely used within the Hamiltonian Monte Carlo method and its variants. We give strong numerical evidence that alternative, easy to implement algorith…