Coupled Adam, which gives every embedding the same effective learning rate by averaging Adam's second moment over the vocabulary, largely removes the mean-shift that causes anisotropic embeddings and improves embedding quality metrics.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Better Embeddings with Coupled Adam
Coupled Adam, which gives every embedding the same effective learning rate by averaging Adam's second moment over the vocabulary, largely removes the mean-shift that causes anisotropic embeddings and improves embedding quality metrics.