AI Paper Atlas

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

On lp-Support Vector Machines and Multidimensional Kernels

Victor Blanco, Justo Puerto, Antonio M. Rodriguez-Chia

JMLR 2020 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel regression under shift · 21 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 l4/3-SVM with monomial transformation (eta=1) instead of RBF l2-SVMRBF l2-SVM · housingtest accuracy (%): 85.35 -> 85.36No clear effect
use l3/2-SVM with Gaussian transformation (eta=3) instead of RBF l2-SVMRBF l2-SVM · german credittest accuracy (%): 77.30 -> 79.00Improved
use l4/3-SVM (eta=1) instead of RBF l2-SVMRBF l2-SVM · colontest accuracy (%): 80.24 -> 82.14Improved
use l4/3-SVM with monomial transformation eta=4 instead of RBF l2-SVMRBF l2-SVM · page blockstest accuracy (%): 92.31 -> 96.11Improved
use lp-SVM instead of RBF l2-SVMRBF l2-SVM · clevelandtest accuracy (%): 85.16 -> 83.48Hurt
raise monomial degree eta from 1 to 3 (ablation)l4/3-SVM, monomial transformation · clevelandtest accuracy (%): 82.84 -> 74.93Hurt
raise monomial degree eta from 1 to 4 (ablation)l4/3-SVM, monomial transformation · page blockstest accuracy (%): 93.49 -> 96.11Improved
use Gaussian instead of monomial transformation at eta=4 (ablation)l4/3-SVM · clevelandtest accuracy (%): 76.56 -> 83.47Improved
use Gaussian instead of monomial transformation at eta=3 (ablation)l4/3-SVM · german credittest accuracy (%): 71.90 -> 76.75Improved
use l4/3 norm instead of l2 norm (ablation)SVM, Gaussian transformation (eta=2) · clevelandtest accuracy (%): 80.58 -> 84.19Improved
use l4/3 norm instead of l2 norm (ablation)SVM, Gaussian transformation (eta=4) · clevelandnonzero coefficients (%): 41.97% -> 3.53%Improved
use l2 norm instead of lp norm (solve time) (ablation)SVM, Gaussian transformation (eta=4) · clevelandCPU time (s): 19.57 -> 0.19Improved

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