Saved in:
Bibliographic Details
Main Author: Lee-Jenkins, Christopher R.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.11573
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911266320154624
author Lee-Jenkins, Christopher R.
author_facet Lee-Jenkins, Christopher R.
contents 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 geometric interface: two potential-generated, conservative descriptions (from negative entropy and log-sum-exp) meet along a Legendrian "seam" on a contact screen (the probability simplex) inside a simple folded symplectic collar. Bias-shift invariance appears as Reeb flow on the screen, and the Fenchel-Young equality/KL gap provides a computable distance to the seam. We work out the two- and three-class cases to make the picture concrete and outline next steps for ML: compact logit models (projective or spherical), global invariants, and connections to information geometry where on-screen dynamics manifest as replicator flows.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11573
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Softmax as a Lagrangian-Legendrian Seam
Lee-Jenkins, Christopher R.
Machine Learning
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 geometric interface: two potential-generated, conservative descriptions (from negative entropy and log-sum-exp) meet along a Legendrian "seam" on a contact screen (the probability simplex) inside a simple folded symplectic collar. Bias-shift invariance appears as Reeb flow on the screen, and the Fenchel-Young equality/KL gap provides a computable distance to the seam. We work out the two- and three-class cases to make the picture concrete and outline next steps for ML: compact logit models (projective or spherical), global invariants, and connections to information geometry where on-screen dynamics manifest as replicator flows.
title Softmax as a Lagrangian-Legendrian Seam
topic Machine Learning
url https://arxiv.org/abs/2511.11573