AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Scalar Quantization as Sparse Least Square Optimization

Chen Wang, Xiaomei Yang, Shaomin Fei, Kai Zhou, Xiao‐Feng Gong, Miao Du, Ruisen Luo

TPAMI 2019 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 6 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 least-square refit of values to l1 quantization (ablation)l1 sparse quantization · Last-layer MNIST network weightsl2 information loss / accuracyImproved
add least square refit to l1 quantization (ablation)l1 sparse quantization · MNIST image quantizationl2 norm lossImproved
add least square refit to l1 quantization (ablation)l1 sparse quantization · Artificial 1-D data (Gaussian mixture, uniform, single Gaussian)l2 lossImproved
add negative l2 term to l1 quantization (ablation)l1 sparse quantization · Last-layer MNIST network weightsnumber of quantization valuesImproved
add negative l2 term to l1 quantization (ablation)l1 sparse quantization · Last-layer MNIST network weightsstabilityHurt
replace k-means with clustering-based least square (ablation)k-means quantization · Last-layer MNIST network weightsaccuracyImproved
replace k-means with l1 quantization with least square (ablation)k-means quantization · Medium-size datarunning timeImproved
use l1 quantization instead of k-means (ablation)k-means quantization · Neural network, MNIST, artificial datal2 information lossHurt
use l0 optimization quantization (ablation)l0 sparse quantization · Network weights and artificial datasolution successHurt
use l1 quantization instead of Mixture of Gaussian quantization (ablation)Mixture of Gaussian quantization · Last-layer MNIST network weightsaccuracyImproved

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