None
EN
Comment on A Random Walk in 10 Dimensions by High Dimensional Optimization Remains Hard – Win Vector LLC
[]
Comments for Galileo Unbound
Within the rapidly-developing field of machine learning, which often deals with landscapes (loss functions or objective functions) in high dimensions that need to be minimized, high dimensions are usually referred to in the negative as “The Curse of Dimensionality”. Because each dimension is independent, a single random walker takes a random step along any of the 10 dimensions at each iteration so that motion in any one of the 10 dimensions is just a 1D random walk.