Re:Matryoshka Representation Learning
by radarsat1 on Thursday February 01, 2024 @11:29AM
(#39217716)
Any relationship to residual vector quantized embeddings?
[ Parent
| on HN ]
Both are methods to reduce the overall size of your embeddings, but from what I understand, quantization is generally better than dimensionality reduction, especially if training is quantization-aware.