Astronomy today is fundamentally different than it was even just a decade ago. Our increasing ability to collect a large amount of data from ever more powerful instruments has enabled many new opportunities. However, such an opportunity also comes with new challenges. The bottleneck stems from the fact that most astronomical observations are inherently high dimension — from “imaging” the Universe at the finest details to fully characterising millions of spectra consisting of thousands of wavelength pixels. In this regime, classical astrostatistics approaches struggle.
I will present two different machine-learning approaches to quantify complex systems in astronomy. (1) Mathematics of information: I will discuss how machine learning can optimally compress information and extract higher-order moment information in stochastic processes. (2) A generative approach: I will discuss how generative models, such as normalising flow, allow us to properly model the vast astronomy data set, enabling the study of complex astronomy systems directly in their observational space.
BIO
Yuan-Sen is an Associate Professor at the Australian National University, jointly affiliated with the astronomy and computer science departments. Yuan-Sen's research focuses on applying machine learning to advance statistical inferences using large astronomical survey data. Yuan-Sen grew up in Malaysia and received his PhD in astronomy and astrophysics from Harvard University in 2017. After graduating, Yuan Sen was awarded a four-way fellowship from Princeton University, Carnegie Institute for Sciences, NASA Hubble and the Institute for Advanced Study at Princeton. He was also named a Future Leader by the Association of Universities for Research in Astronomy and was a NASA Earth and Space Science Fellow. Upon joining ANU, recently received the ARC DECRA fellowship.
Meanwhile, Yuan-Sen serves as the co-chair of the NASA Cosmic Programs Stars Science Interest Group and led multiple future spectroscopic surveys as the science group leader. Yuan-Sen is passionate about public outreach. He wrote monthly "popular science" articles in the largest Chinese newspaper in Malaysia and has produced two TED education videos with more than 4 million views. He also worked as a consultant developing tools to detect art forgery in paintings using machine learning. He was once a semi-professional gamer and a top Night-Elf player in Warcraft 3 in Malaysia.
Host: Shude Mao
