3 papers
math.OC2026
Deep Learning as the Disciplined Construction of Tame Objects
Gilles Bareilles, Allen Gehret, Johannes Aspman +2
One can see deep-learning models as compositions of functions within the so-called tame geometry. In this expository note, we give an overview of some topics at the interface of ta…
math.LO2025
Dimension theory for the asymptotic couple of the field of logarithmic transseries
Allen Gehret, Elliot Kaplan, Nigel Pynn-Coates
In this paper we completely characterize all dimension functions on all models of the theory of the asymptotic couple of the field of logarithmic transseries (Dimension…
cs.LG2025
Stochastic Sample Approximations of (Local) Moduli of Continuity
Rodion Nazarov, Allen Gehret, Robert Shorten +1
Modulus of local continuity is used to evaluate the robustness of neural networks and fairness of their repeated uses in closed-loop models. Here, we revisit a connection between g…