Algorithms for metric learning via contrastive embeddings

Diego Ihara Centurion, Neshat Mohammadi, Anastasios Sidiropoulos

We study the problem of supervised learning a metric space under discriminative constraints. Given a universe $X$ and sets $\mathcal{S},\mathcal{D}\subset \left(\genfrac{}{}{0ex}{}{X}{2}\right)$ of similar and…