AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Fast Similarity Search via Optimal Sparse Lifting

Wenye Li, Jingwei Mao, Yin Zhang, Shuguang Cui

NeurIPS 2018 · Learning theory and algorithms › Combinatorial and search optimization · approach: Heuristic and local search algorithms · 15 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
learn optimal lifting operator instead of random sparse projection (fly algorithm)sparse binary hashing · SIFT, GLOVE, MNIST similarity searchmean average precisionImproved
fly random sparse lifting instead of LSH dense random projectionhashing for similarity search · SIFT, GLOVE, MNIST similarity searchmean average precisionImproved
use optimal lifting instead of autoencoder at large hash length (k=16, 32)hashing · SIFT, MNISTmean average precisionNo clear effect
use optimal lifting instead of autoencoder at small hash length (k=2,4,8)hashing · SIFT, MNISTmean average precisionImproved
use sparse binary lifted vectors instead of LSH/autoencoder vectorsquery processing · WIKI query timequery time: 4 to 9 times fasterImproved
use optimal lifting with d'=2000 instead of autoencoder trainingtraining · WIKI training timetraining timeMixed
use optimal lifting vs resized ground truth images on 20x20optimal lifting step · MNISTrelative deviationNo clear effect

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