Skip to content
Live
Trending storyPast story

Apple proposes a method to accelerate retrieval

1 reports1 outlets14 days agoUpdate

The story so far

AI overview

Apple's Amortizing Maximum Inner Product Search, presented at ICML 2026, learns support functions by training small neural networks to understand typical query matching patterns at a fixed cost, achieving faster precise retrieval during inference. This method utilizes ICNN to learn support functions, and KeyNet directly outputs the best matching key vector, both trained on supervised datasets constructed based on actual query distributions, significantly improving retrieval efficiency in RAG scenarios.

AI-written from the reports · Updated 13 days ago

Coverage timeline

Follow the coverage to see every side of the story.

5 Nov
  1. Apple Machine Learning Research
    Faster Retrieval for Better, More Efficient RAG

    Apple's Amortizing Maximum Inner Product Search, presented at ICML 2026, learns support functions by training small neural networks to understand typical query matching patterns at a fixed cost, achieving faster precise retrieval during inference. This method utilizes ICNN to learn support functions, and KeyNet directly outputs the best matching key vector, both trained on supervised datasets constructed based on actual query distributions, significantly improving retrieval efficiency in RAG scenarios.