Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
In-context classification: Calibration and noise in linear attention with softmax readout
Arman Rysmakhanov, Mary Letey, Yue M. Lu +2
We study in-context binary classification in a simple attention model trained to minimise a logistic loss. Each prompt has a latent logistic teacher, and the learner must infer its…
stat.ML2026
What can linear attention learn from nonlinear teachers in-context?
Mary Letey, Arman Rysmakhanov, Yue M. Lu +2
Linear attention is a tractable model for understanding the mechanisms governing in-context learning in transformers. For linear regression tasks, recent asymptotic analyses have c…