AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective

Etienne Boursier, Claire Boyer

ICML 2026 · Architectures and efficiency › Attention and transformers · approach: Attention head mechanisms · 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
increase prompt length L (ablation)single-layer softmax attention vs normalized linear attention · in-context linear regression, Gaussian inputs, d=5output and gradient distance between softmax and linear modelsImproved
increase prompt length L (ablation)softmax attention training dynamics · in-context linear regression, isotropic covariatesparameter distance between softmax and linear attention trajectoriesImproved
use linear attention instead of softmax attentionsingle-layer attention · in-context linear regression ICL risk at convergenceICL riskImproved
use anisotropic (Kac-Murdock-Szego) covariates instead of isotropic (ablation)softmax and linear attention · in-context linear regression ICL riskconvergence of ICL risk to Bayes optimumHurt
use softmax instead of linear attentionsingle-layer attention training · in-context linear regression optimizationtraining stabilityImproved

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