Learning Decision-Stump Thresholds in Context: Dynamics of Softmax Attention

Excerpt

arXiv:2610.07074v1 Announce Type: cross Abstract: Estimating a decision threshold requires locating observations near an unknown boundary. We study how gradient-based pretraining learns this statistical rule in a two-parameter softmax-attention model with a fixed feature and inequality direction. Pretraining uses labeled contexts and their true thresholds; a fresh threshold must be inferred from context alone. Under a large-resolution initialization, constant-step gradient descent on $m$ tasks w