Yashar Hezaveh

Sampling-Based Accuracy Testing of Posterior Estimators for General Inference

Feb 06, 2023
Pablo Lemos, Adam Coogan, Yashar Hezaveh, Laurence Perreault-Levasseur

Figure 2 for Sampling-Based Accuracy Testing of Posterior Estimators for General Inference

Figure 3 for Sampling-Based Accuracy Testing of Posterior Estimators for General Inference

Figure 4 for Sampling-Based Accuracy Testing of Posterior Estimators for General Inference

* 15 pages

Access Paper or Ask Questions

Pixelated Reconstruction of Foreground Density and Background Surface Brightness in Gravitational Lensing Systems using Recurrent Inference Machines

Jan 10, 2023
Alexandre Adam, Laurence Perreault-Levasseur, Yashar Hezaveh, Max Welling

Figure 1 for Pixelated Reconstruction of Foreground Density and Background Surface Brightness in Gravitational Lensing Systems using Recurrent Inference Machines

Figure 2 for Pixelated Reconstruction of Foreground Density and Background Surface Brightness in Gravitational Lensing Systems using Recurrent Inference Machines

Figure 3 for Pixelated Reconstruction of Foreground Density and Background Surface Brightness in Gravitational Lensing Systems using Recurrent Inference Machines

Figure 4 for Pixelated Reconstruction of Foreground Density and Background Surface Brightness in Gravitational Lensing Systems using Recurrent Inference Machines

* 13+7 pages, 13 figures; Submitted to The Astrophysical Journal. arXiv admin note: text overlap with arXiv:2207.01073

Access Paper or Ask Questions

Posterior samples of source galaxies in strong gravitational lenses with score-based priors

Nov 07, 2022
Alexandre Adam, Adam Coogan, Nikolay Malkin, Ronan Legin, Laurence Perreault-Levasseur, Yashar Hezaveh, Yoshua Bengio

Figure 2 for Posterior samples of source galaxies in strong gravitational lenses with score-based priors

Figure 3 for Posterior samples of source galaxies in strong gravitational lenses with score-based priors

* 5+6 pages, 3 figures, Accepted (poster + contributed talk) for the Machine Learning and the Physical Sciences Workshop at the 36th conference on Neural Information Processing Systems (NeurIPS 2022)

Access Paper or Ask Questions