somehow I missed this post and only caught it now. This was helpful for a few things.
That I should think of some algorithms primarily as populating a space with the given data and then ‘deciding’ on the topology of the space
That ‘the valley of bad X’ is the inverse of a ‘goldilocks zone’
That overfitting can be thought of as occurring in a valley of bad parameterization.
somehow I missed this post and only caught it now. This was helpful for a few things.
That I should think of some algorithms primarily as populating a space with the given data and then ‘deciding’ on the topology of the space
That ‘the valley of bad X’ is the inverse of a ‘goldilocks zone’
That overfitting can be thought of as occurring in a valley of bad parameterization.