AI Paper Atlas

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

On Uniform Error Bounds for Kernel Regression under Non-Gaussian Noise

Johannes Teutsch, Oleksii Molodchyk, Marion Leibold, Timm Faulwasser, Armin Lederer

ICML 2026 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel ridge regression analysis · 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 proposed uniform bound instead of Abbasi-Yadkori boundAbbasi-Yadkori bound · bounded noise, n_x 1-3uncertainty region sizeImproved
use proposed bound instead of Fiedler et al. with few data pointsFiedler et al. bound · bounded noise, low datauncertainty region size: up to 7.5%Hurt
use proposed bound instead of Fiedler et al. with many data pointsFiedler et al. bound · bounded noise, t up to 1000uncertainty region sizeImproved
use proposed bound instead of Fiedler et al. in low-data safe controlFiedler et al. bound · safe control, sub-Gaussian noisesuccess rate: <1.1%Hurt
use proposed bound instead of Abbasi-Yadkori in safe controlAbbasi-Yadkori bound · safe controlsuccess rateImproved
use bounded-noise bound (b) instead of sub-Gaussian bound (a) at n_x=1 with large datasub-Gaussian bound · bounded noiseuncertainty region sizeImproved
use sub-exponential bound (c) instead of Chowdhury and GopalanChowdhury and Gopalan bound · chi-squared noiseuncertainty region size: over two orders of magnitudeImproved
use sub-exponential bound (c) instead of the Proposition boundProposition bound · chi-squared noiseuncertainty region size: over an order of magnitudeImproved
use sub-exponential bound (c) in safe control instead of Proposition boundProposition bound · chi-squared noise safe controlsuccess rate: 0% -> 71.6%Improved

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