37 citations · 151 across the 27 of their papers we have counts for
9 papers · 1 filter
Error Analysis of Bayesian Inverse Problems with Generative Priors
Bamdad Hosseini, Ziqi Huang
Data-driven methods for the solution of inverse problems have become widely popular in recent years thanks to the rise of machine learning techniques. A popular approach concerns t…
Gaussian Measures Conditioned on Nonlinear Observations: Consistency, MAP Estimators, and Simulation
Yifan Chen, Bamdad Hosseini, Houman Owhadi +1
The article presents a systematic study of the problem of conditioning a Gaussian random variable on nonlinear observations of the form where $ϕ: \mathcal{X} \to…
Diffeomorphic Measure Matching with Kernels for Generative Modeling
Biraj Pandey, Bamdad Hosseini, Pau Batlle +1
This article presents a general framework for the transport of probability measures towards minimum divergence generative modeling and sampling using ordinary differential equation…
Kernel Methods are Competitive for Operator Learning
Pau Batlle, Matthieu Darcy, Bamdad Hosseini +1
We present a general kernel-based framework for learning operators between Banach spaces along with a priori error analysis and comprehensive numerical comparisons with popular neu…
Bayesian Posterior Perturbation Analysis with Integral Probability Metrics
Alfredo Garbuno-Inigo, Tapio Helin, Franca Hoffmann +1
In recent years, Bayesian inference in large-scale inverse problems found in science, engineering and machine learning has gained significant attention. This paper examines the rob…
A Kernel Approach for PDE Discovery and Operator Learning
Da Long, Nicole Mrvaljevic, Shandian Zhe +1
This article presents a three-step framework for learning and solving partial differential equations (PDEs) using kernel methods. Given a training set consisting of pairs of noisy…
Posterior Consistency of Semi-Supervised Regression on Graphs
Andrea L. Bertozzi, Bamdad Hosseini, Hao Li +2
Graph-based semi-supervised regression (SSR) is the problem of estimating the value of a function on a weighted graph from its values (labels) on a small subset of the vertices. Th…
Conditional Sampling with Monotone GANs: from Generative Models to Likelihood-Free Inference
Ricardo Baptista, Bamdad Hosseini, Nikola B. Kovachki +1
We present a novel framework for conditional sampling of probability measures, using block triangular transport maps. We develop the theoretical foundations of block triangular tra…
Consistency of semi-supervised learning algorithms on graphs: Probit and one-hot methods
Franca Hoffmann, Bamdad Hosseini, Zhi Ren +1
Graph-based semi-supervised learning is the problem of propagating labels from a small number of labelled data points to a larger set of unlabelled data. This paper is concerned wi…