AI Paper Atlas

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

Sample based Explanations via Generalized Representers

Che-Ping Tsai, Chih-Kuan Yeh, Pradeep Kumar Ravikumar

NeurIPS 2023 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel regression under shift · 0 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 tracking global importance instead of surrogate derivative (ablation)NTK-final generalized representer · MNISTAUC-DEL-: 1.88 -> 3.52Improved
use tracking global importance instead of surrogate derivative (ablation)NTK-final generalized representer · CIFAR-10AUC-DEL-: 2.27 -> 3.26Improved
use tracking global importance instead of target derivative (ablation)NTK-final generalized representer · ToxicityAUC-DEL-: 1.10 -> 2.08Improved
use tracking global importance instead of target derivative (ablation)NTK-final generalized representer · AGnewsAUC-DEL-: 1.88 -> 2.56Improved
use target derivative instead of surrogate derivative (ablation)NTK-final generalized representer · MNISTAUC-DEL-: 1.88 -> 2.41Improved
use target derivative instead of surrogate derivative (ablation)NTK-final generalized representer · CIFAR-10AUC-DEL-: 2.27 -> 2.81Improved
use NTK-final kernel instead of NTK-init kernel (ablation)tracking representer · CIFAR-10AUC-DEL-: 1.35 -> 3.26Improved
use NTK-final kernel instead of NTK-init kernel (ablation)tracking representer · MNISTAUC-DEL-: 3.18 -> 3.52Mixed
use NTK-final kernel instead of last-layer kernel (ablation)tracking representer · CIFAR-10AUC-DEL-: 2.26 -> 3.26Improved
use NTK-final kernel instead of NTK-middle kernel (ablation)tracking representer · AGnewsAUC-DEL-: 2.54 -> 2.56No clear effect
use influence-function kernel instead of NTK-final kernel (ablation)tracking representer · CIFAR-10AUC-DEL-: 3.26 -> 3.46Improved
use influence-function kernel (last layer only) instead of NTK-final kernel (ablation)tracking representer · ToxicityAUC-DEL-: 2.08 -> 0.42Hurt

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