works on
convergence speed 1embedding geometry 1loss functions 1representation learning 1tabular classification 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.LG2026

Contrastive-Collapsed Loss for Flexible and Geometrically Optimal Embeddings and Faster Convergence

Blanca Cano-Camarero, Ángela Fernández-Pascual, José R. Dorronsoro

The paper proposes CoCo, a contrastive-collapsed loss that encourages intra‑class collapse and inter‑class contrast to produce normalized, geometrically optimal embeddings with lar…