Estimating Multimodal Aleatoric Uncertainty in Regression Tasks

Ziliang Xiong, Arvi Jonnarth, Abdelrahman Eldesokey, Joakim Johnander, Bastian Wandt, Per-Erik Forssén

Abstract

Proposes a method for estimating multimodal aleatoric uncertainty in regression problems, extending prior uncertainty-estimation work beyond single-mode noise assumptions.