Tag
embedding-geometry
- Mar 13, 2026 Alignment and Uniformity as Separate Objectives Contrastive losses can be decomposed into a term that pulls positive pairs together and a term that spreads all representations apart, and the two terms trade against each other in measurable ways. deep learning
- Jul 28, 2025 Distance Concentration and Hubness in Embedding Spaces Why nearest-neighbour search degrades in high dimensions, how a few points become hubs that absorb most queries, and what those effects imply for measuring similarity between learned vectors. deep learning