AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Random Projections with Asymmetric Quantization

Xiaoyun Li, Ping Li

NeurIPS 2019 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add normalization to the quantized inner-product estimator (ablation)quantized random-projection cosine estimators (Scenario 1 and 2) · Arcene, BASEHOCK, COIL20 nearest neighbor search1-NN precisionImproved
increase quantization bits b for the normalized estimatornormalized quantized estimator · Arcene, BASEHOCK, COIL201-NN precisionImproved
use 1-bit instead of more bits for the unnormalized estimatorsimple quantized estimator (quantized vs full precision) · Arcene, COIL20 (high mean 1-NN rho)1-NN precisionMixed
debias the estimator by dividing by xi_{1,1}quantized-vs-full-precision estimator · theory, normalized estimatormean square errorImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy