AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models

Chenyang Zhang, Qingyue Zhao, Quanquan Gu, Yuan Cao

ICLR 2026 · Optimization › Implicit bias and generalization · approach: In-context learning as gradient descent · 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
train one-layer position-only transformer on teacher outputs (synthetic CNN/GCN)One-layer transformer · Synthetic teacher-studentexcess training loss slope: slope -1Improved
evaluate OOD loss of trained transformerOne-layer transformer · Synthetic teacher-studentexcess OOD test loss slope: slope -0.5Improved
use real MNIST-pretrained CNN teacher instead of syntheticOne-layer transformer · MNIST teacher CNNcosine similarity of W_V: above 0.9Improved

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