News for hackers. Stuff that matters.
Re:Matryoshka Representation Learning by radarsat1 on Thursday February 01, 2024 @11:29AM (#39217716)
Any relationship to residual vector quantized embeddings?
Re:Matryoshka Representation Learning by fzliu on Thursday February 01, 2024 @11:37AM (#39217843)
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.