E-means: 10x faster k-means at equal loss

4 comments

• Luke2642 18 minutes ago
  This is a great example of why p=np is sometimes the wrong question. For this np hard problem approximate solutions are good enough, and if you get them 45x faster that's even better!
• real_faxenoff 50 minutes ago
  I adapted the method to my IVF index (the code-daemon project) and achieved a 146x speedup on the GPU.

  That's impressive!
• wood_spirit 1 hour ago
  This looks awesome. Obvious in hindsight! The viz really explains it well.

  Hope it gets added to scipy - it’s much more available in the envs many use than facebooks own faiss library.

  [-]
  • porridgeraisin 1 hour ago
    The automatic hyperparameter laws don't seem intuitive to me yet. Do you have any intuition for it?
• bashhq_r 6 minutes ago
  so the epoch reduction is cool but the hyperparameter laws feel like they were fit post-hoc