Abstract: I will overview two approaches to parametrize and generate new samples from highly nonGaussian distributions: normalizing flows and variational autoencoders. Time perimitting, I will briefly discuss some applications to the early Universe and field theory.
Generative NonGaussianity: Normalizing Flows and Variational Autoencoders
Jonathan Braden (CITA) // February 15, 2023
Abstract: I will overview two approaches to parametrize and generate new samples from highly nonGaussian distributions: normalizing flows and variational autoencoders. Time perimitting, I will briefly discuss some applications to the early Universe and field theory.
- The Event Horizon Telescope Collaboration Reports a Spectacular Flare from the Centre of the Messier 87 Galaxy December 13, 2024
- CITA Researcher Helps Locate the “Missing Link” in Giant Black Hole’s Power Source January 28, 2026
- PLANCK ALERT: The Veils Come Off March 21st March 18, 2013
- PLANCK reveals the Universe’s First Light March 21, 2013
- CITA – Planck coverage in the Canadian Media March 23, 2013
- How to Build a Really Big Star March 28, 2013