AI Paper Atlas

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

Efficient Estimation of Kernel Surrogate Models for Task Attribution

Zhenshuo Zhang, Minxuan Duan, Hongyang R. Zhang

ICLR 2026 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel regression under shift · 3 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 kernel surrogate instead of linear surrogatesurrogate model · Modular arithmetic quadraticLDS: 0.44 -> 0.52Improved
use kernel surrogate instead of linear surrogatesurrogate model · Modular arithmetic additionLDS: 0.18 -> 0.30Improved
use kernel surrogate instead of linear surrogatesurrogate model · In-context learning Coin flipLDS: 0.43 -> 0.54Improved
use kernel surrogate instead of linear surrogatesurrogate model · In-context learning SST-2LDS: 0.33 -> 0.37Improved
use kernel surrogate instead of linear surrogatesurrogate model · Meta-World MT10LDS: 0.76 -> 0.80Improved
select ICL prompts with kernel surrogate attribution instead of linear surrogatetask selection · ICL Coin fliploss: 0.05 -> 0.02Improved
select ICL prompts with kernel surrogate attribution instead of linear surrogatetask selection · ICL SST-2loss: 0.20 -> 0.16Improved
co-train with top-3 tasks chosen by kernel surrogate instead of linear surrogatetask selection · Meta-World MT10target rewards: 13.1 -> 18.8Improved
increase number of prompt samples from 50 to 500kernel surrogate models · In-context learningLDS: 0.31 on SST-2 and 0.53 on Coin-FlipNo clear effect
use SAM or NSO Hessian regularization instead of plain SGD (ablation)linear surrogate model · Modular quadratic taskLDS: LDS dropped to 0.01 with SGDImproved

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