AI Paper Atlas

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

Kernel-Based Generalized Median Computation for Consensus Learning

Andreas Nienkötter, Xiaoyi Jiang

TPAMI 2022 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel regression under shift · 4 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
use a distance-preserving kernel instead of K_rbf (ablation)kernel median · Darwin, lin-recsum of distances: 0.8284 -> 0.2070Improved
use a distance-preserving kernel instead of K_rbf (ablation)kernel median · UCI Cluster, lin-recsum of distances: 1.4435 -> 0.3055Improved
use linear recursive instead of plain linear reconstructionK_lin · Darwinsum of distances: 0.3683 -> 0.2070Improved
use triangular recursive instead of triangular reconstructionK_lin · Darwinsum of distances: 0.3090 -> 0.1969Improved
add linear search post-processingK_lin lin-rec · Darwinsum of distances: 0.2070 -> 0.1056Improved
use kernel median instead of CCA embeddingK_lin · Darwin, lin-recsum of distances: 0.2425 -> 0.2070Improved
use kernel median instead of CCA embeddingK_lin · CCD, lin-searchsum of distances: 0.2590 -> 0.2330Improved
use kernel median instead of CCA embeddingK_lin · Darwin, lin-searchsum of distances: 0.0988 -> 0.1056Hurt
use kernel median instead of CCA embeddingK_lin · Gen. Cluster, linearsum of distances: 0.4575 -> 0.4575No clear effect
use string subsequence domain kernel instead of K_linkernel median · Darwin, lin-recsum of distances: 0.2070 -> 0.4023Hurt
use partition domain kernel instead of K_linkernel median · Gen. Cluster, lin-recsum of distances: 0.4412 -> 0.4412No clear effect
use kernel median instead of Prototype embeddingK_lin · Darwin, linearsum of distances: 0.6411 -> 0.3683Improved

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