AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Probabilistic Kernel Function for Fast Angle Testing

Kejing Lu, Chuan Xiao, Yoshiharu Ishikawa

ICLR 2026 · Learning theory and algorithms › Kernels and regression theory · approach: Random feature approximation · 1 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
replace Gaussian projection vectors (CEOs) with S_pol structured projectionsKS1 · Word k-MIPS, Probe@10recall (%): 34.106 -> 34.395Improved
replace Gaussian projection vectors (CEOs) with S_pol structured projectionsKS1 · Word k-MIPS, Probe@10Krecall (%): 98.182 -> 98.404Improved
replace Gaussian projection vectors (CEOs) with S_pol structured projectionsKS1 · GloVe1M k-MIPS, Probe@10Krecall (%): 63.545 -> 64.355Improved
replace Gaussian projection vectors (CEOs) with S_pol structured projectionsKS1 · GloVe2M k-MIPS, Probe@10Krecall (%): 54.916 -> 55.394Improved
replace Gaussian projection vectors (CEOs) with S_pol structured projectionsKS1 · GloVe2M k-MIPS, Probe@10recall (%): 2.070 -> 1.996Hurt
replace Gaussian projection vectors (CEOs) with S_sym structured projectionsKS1 · GloVe2M k-MIPS, Probe@10recall (%): 2.070 -> 2.064Hurt
replace Gaussian projection vectors (CEOs) with S_sym structured projectionsKS1 · GloVe1M k-MIPS, Probe@10Krecall (%): 63.545 -> 64.041Improved
use S_pol configuration instead of S_sym (ablation)KS1 · GloVe1M k-MIPS, Probe@10Krecall (%): 64.041 -> 64.355Improved
use S_pol configuration instead of S_sym (ablation)KS1 · Word k-MIPS, Probe@1Krecall (%): 90.265 -> 90.678Improved
use S_pol configuration instead of S_sym (ablation)KS1 · GloVe2M k-MIPS, Probe@10recall (%): 2.064 -> 1.996Hurt
add KS2 routing test to HNSWHNSW · ANNS (datasets except Word), recall-QPSQPS: factor of 2.5 to 3Improved
replace PEOs test with KS2 test in HNSWHNSW+PEOs · ANNS (datasets except Word), recall-QPSQPS: 1.1 to 1.3 times fasterImproved

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