AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Statistical Advantage of Softmax Attention: Insights from Single-Location Regression

O Duranthon, Pierre Marion, Claire Boyer, Bruno Loureiro, Lenka Zdeborová

ICLR 2026 · Architectures and efficiency › Attention and transformers · approach: Sparse and structured attention

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 softmax instead of linear attention (ablation)single-layer attention on single-location regression · Spiked-SLR and max-SLR, population riskminimal population riskImproved
use softmax instead of linear attention at finite samples (ablation)single-layer attention on single-location regression · Spiked-SLR and max-SLR, finite sample ratio, L=3minimal test riskImproved
vary sequence length (L uniform on {1,2,3}) instead of fixed L=2 (ablation)linear attention · Single-location regression, population riskminimal population riskHurt
use element-wise erf activation instead of a normalized activation (ablation)attention activation · Single-location regression with variable Lminimal population riskHurt
use softplus kernelized attention instead of softmax (ablation)attention activation · Single-location regression, larger Lminimal population riskHurt
use erf or softplus activation instead of linear (ablation)attention activation · Spiked-SLR and max-SLR, population riskminimal population riskImproved
add a constant bias term to the activation (1 + chi instead of chi) (ablation)linear and erf attention · Single-location regression, gradient at initializationnonzero gradient on recovery order parametersImproved

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