AI Paper Atlas

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

Diffeomorphic Learning

Laurent Younes

JMLR 2020 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel regression under shift · 13 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 diffeomorphic transformation of the datalogistic regression · Tori (d=10, 250 per class)test error rate: 0.325 -> 0.023Improved
add diffeomorphic transformation of the datalogistic regression · Spherical layers (d=3, 100 per class)test error rate: 0.507 -> 0.246Improved
add diffeomorphic transformation of the datalogistic regression · Xor (d=50, 100 per class)test error rate: 0.505 -> 0.066Improved
add diffeomorphic transformation of the datalogistic regression · MNIST subset (d=196, 100 per class)test error rate: 0.128 -> 0.113Improved
add diffeomorphic transformation of the datakernel SVM · MNIST subset (d=196, 100 per class)test error rate: 0.228 -> 0.325Hurt
add diffeomorphic transformation of the dataMLP5 · RBF data (d=2, 500 per class)test error rate: 0.081 -> 0.142Hurt
add diffeomorphic transformation of the dataMLP1 · Segment lengths (d=100, 100 per class)test error rate: 0.337 -> 0.390Hurt
add diffeomorphic transformation of the datalogistic regression · Segment pairs (d=50, 100 per class)test error rate: 0.477 -> 0.461No clear effect
add diffeomorphic transformation of the datalogistic regression · Tori (d=20, 100 per class)test error rate: 0.320 -> 0.321No clear effect
increase time discretization steps from T=1 to T=100 (ablation)Diffeomorphic learning (logistic regression on transformed data) · Xor (100 per class)test error rate: 0.478 -> 0.039Improved
increase time discretization steps from T=1 to T=100 (ablation)Diffeomorphic learning (logistic regression on transformed data) · Mixture of Gaussians (100 per class)test error rate: 0.178 -> 0.109Improved
use kernel scale 4 rho_0 instead of rho_0 (ablation)Diffeomorphic learning (logistic regression on transformed data) · Xor (100 per class)test error rate: 0.092 -> 0.01Improved

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