AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time

Blake Bordelon, Mary Letey, Cengiz Pehlevan

ICLR 2026 · Architectures and efficiency › Attention and transformers · approach: Training dynamics of in-context learning

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
increase depth L at infinite context length (ablation)deep linear attention · ISO (isotropic covariates)ICL lossNo clear effect
increase depth L at finite context length alpha near 1 (ablation)deep linear attention · ISO (isotropic covariates)ICL lossImproved
increase depth L beyond 1 at long context (ablation)deep linear attention · FS (fixed structured covariance)ICL lossNo clear effect
increase depth L (ablation)deep linear attention · RRS (randomly rotated covariances), infinite contextICL lossImproved
scale only width or only depth (ablation)deep linear attention · RRS powerlaw dataICL lossHurt
increase width and depth together with compute (ablation)deep linear attention · RRS powerlaw dataICL lossImproved
evaluate FS-pretrained model under covariance shift (ablation)deep linear attention · FS, shifted covarianceOOD lossHurt
use softmax attention trained with Adam instead of linear attention (ablation)softmax transformer · ICL regressionICL lossImproved

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