School of Physics Colloquium

Siddarth Mishra-Sharma (MIT, Harvard University) A radical new future for (astro)physics enabled by machine learning

Speaker: Siddarth Mishra-Sharma (MIT)

Title: A radical new future for (astro)physics enabled by machine learning

Abstract: The next several years will witness an influx of data that will enable us to map out the distribution of matter in the Universe, image billions of stars and galaxies, and create maps of the Milky Way to unprecedented precision. While these observations will have significant discovery potential, the complexity of the data and underlying physical models also presents novel challenges. I will describe how maximizing the scientific return of astrophysical observations over a wide range of scales and modalities will require a qualitative shift in how we interact with the data, bringing together several advances in probabilistic machine learning. Beyond showcasing applications to astrophysics, I will highlight how the unique nature of astrophysical data motivates the advancement of machine learning methods with broad relevance to the physical sciences and beyond.

Bio: Siddharth is an IAIFI Fellow at The NSF AI Institute for Artificial Intelligence and Fundamental Interactions (IAIFI), working between MIT and Harvard. Siddharth is broadly interested in the application and development of machine learning methods motivated by problems in astrophysics, with a focus on searches for signatures of new physics. Previously, he was a postdoc at NYU’s Center for Cosmology and Particle Physics and obtained his Ph.D. in Physics from Princeton University.


Event Details


  • Date: 
    Wednesday, January 31, 2024 - 12:30pm to 1:30pm

Pettit Microelectronics Building Room 102A/102B