What can linear attention learn from nonlinear teachers in-context?

arXiv:2610.10761 · stat.ML, cs.LG · Submitted 2026-10-07 · Read on arXiv

stat.ML, cs.LG

Submitted: 2026-10-07

Updated: 2026-10-07

Terminology

• In-Context Learning — 10× in this paper · explained in 4 episodes
• Transformer — 9× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Anisotropy — 1× in this paper · explained in 3 episodes
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Sample Complexity — 1× in this paper · explained in 15 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Trace — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time
• In-context Learning of Single-index Targets: Comparing Kernel and Feature Learners
• Pretrained transformer efficiently learns low-dimensional target functions in-context
• Gated Linear Attention Transformers with Hardware-Efficient Training
• What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
• Online Conformal Prediction for Non-Exchangeable Panel Data
• Deep Time-Series Forecasting in 10 Years: A Survey