PIRSA:24030099

Video URL

https://pirsa.org/24030099

Deep Probabilistic Models for Cosmological Analysis and Beyond

Dai, B. (2024). Deep Probabilistic Models for Cosmological Analysis and Beyond. Perimeter Institute for Theoretical Physics. https://pirsa.org/24030099

Dai, Biwei. Deep Probabilistic Models for Cosmological Analysis and Beyond. Perimeter Institute for Theoretical Physics, Mar. 05, 2024, https://pirsa.org/24030099 

          @misc{ scivideos_PIRSA:24030099,
            doi = {10.48660/24030099},
            url = {https://pirsa.org/24030099},
            author = {Dai, Biwei},
            keywords = {Other Physics},
            language = {en},
            title = {Deep Probabilistic Models for Cosmological Analysis and Beyond},
            publisher = {Perimeter Institute for Theoretical Physics},
            year = {2024},
            month = {mar},
            note = {PIRSA:24030099 see, \url{https://scivideos.org/index.php/pirsa/24030099}}
          }

Biwei Dai University of California, Berkeley

Talk numberPIRSA:24030099
DOI10.48660/24030099
Source RepositoryPIRSA
Collection
Talk Type Scientific Series
Subject

Abstract

Current and future weak lensing surveys contain significant information about our universe. However, their optimal cosmological analysis is challenging, with traditional analyses often resulting in information loss due to reliance on summary statistics like two-point correlation functions. While deep learning methods offer promise in capturing the complex non-linear features of these cosmological fields, they often suffer from issues such as inadequate uncertainty quantification, susceptibility to distribution shifts, and interpretability limitations, which hinder their scientific applicability. In this talk, I propose a novel approach leveraging generative probabilistic modeling with Normalizing Flows to learn the data likelihood function at the field level, facilitating more effective cosmological information extraction. This framework not only enables anomaly detection of distribution shifts to improve the robustness of the analysis, but also fostering interpretability via generated samples. I will also discuss incorporating physical prior knowledge, such as symmetries and multiscale structure, into the model architectures to improve their generalization capabilities. Finally, I will explore the broader implications of deep probabilistic models in physics, highlighting their potential applications in diverse areas ranging from astronomical observations to high-energy physics and lattice field theory.

---

Zoom link