2 papers
cs.LG2025
Softmax as a Lagrangian-Legendrian Seam
Christopher R. Lee-Jenkins
This note offers a first bridge from machine learning to modern differential geometry. We show that the logits-to-probabilities step implemented by softmax can be modeled as a geom…
cs.LG2025
Manifold Trajectories in Next-Token Prediction: From Replicator Dynamics to Softmax Equilibrium
Christopher R. Lee-Jenkins
Decoding in large language models is often described as scoring tokens and normalizing with softmax. We give a minimal, self-contained account of this step as a constrained variati…