> In the following, we show that [taking cosine similarity between two features in a learned embedding] can lead to arbitrary results, and they may not even be unique.
Was uniqueness ever a guarantee? It's a distance metric. It's reasonable to assume that two features can be equidistant to the ideal solution to a linear system of equations. Maybe I'm missing something.
Was uniqueness ever a guarantee? It's a distance metric. It's reasonable to assume that two features can be equidistant to the ideal solution to a linear system of equations. Maybe I'm missing something.