AI Paper Atlas

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

Diffeomorphism-based feature learning using Poincaré inequalities on augmented input space

Romain Verdière, Clémentine Prieur, Olivier Zahm

JMLR 2025 · Learning theory and algorithms › Kernels and regression theory · approach: Neural tangent kernel analysis · 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
add dimension augmentation (extra random inputs) (ablation)BACF_IS · u2 on [0,1]^20 (ntrain=100)NRMSE (%): 9.11 -> 4.29Improved
add dimension augmentation (ablation)BACF_IS · u2 on [-1,1]^8 (ntrain=500)NRMSE (%): 8.05 -> 2.47Improved
add dimension augmentation (ablation)BACF_IS · u3 on [-pi/2,pi/2]^8 (ntrain=100)NRMSE (%): 4.75 -> 1.40Improved
add dimension augmentation (ablation)BACF_IS · u3 on [-pi/2,pi/2]^12 (ntrain=100)NRMSE (%): 6.48 -> 3.26Improved
add dimension augmentation (ablation)BACF_IS · Thermal block d=16, m=1 (ntrain=100)NRMSE (%): 5.18 -> 3.73Improved
add dimension augmentation (ablation)BACF_IS · u1 on [-1,1]^8 (ntrain=50)NRMSE (%): 1.15 -> 1.41Hurt
add dimension augmentation (ablation)BACF_IS · Thermal block d=36, m=1 (ntrain=200)NRMSE (%): 3.44 -> 3.51No clear effect
add dimension augmentation (ablation)BACF_FS · Thermal block d=16, m=1 (ntrain=100)NRMSE (%): 5.27 -> 7.54Hurt
add dimension augmentation (ablation)BACF_FS · u3 on [-pi/2,pi/2]^12 (ntrain=500)NRMSE (%): 1.55 -> 1.28Improved
use input-space Poincare bound (IS) instead of feature-space bound (FS) (ablation)BACF · u3 on [-pi/2,pi/2]^8 (ntrain=100)NRMSE (%): 12.40 -> 4.75Improved
use BACF_ISd+2 instead of PFMfeature map · u3 on [-pi/2,pi/2]^8 (ntrain=500)NRMSE (%): 12.08 -> 0.56Improved
use PFM instead of BACF on a polynomial-friendly targetfeature map · u2 on [0,1]^20 (ntrain=500)NRMSE (%): 1.81 -> 0.39Improved

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