Showing math.OCShow all
3 papers · 1 filter
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.OC2026
On Moment-Based Recovery of Measures with Atomic and Continuous Parts
Ruben Karapetyan, Shenyuan Ma, Aleš Wodecki +1
Recovering probability measures from moments is a central theme in statistics and optimization. In particular, we focus on the recovery of measures from moments and pseudo-moments,…
math.OC2026
Penalised and constrained geodesics in geometric control theory
Rufus Lawrence, Aleš Wodecki, Johannes Aspman +1
In many problems in optimal control, one seeks to minimise an objective function subject to constraints on the velocity of the system. Imposing these constraints directly -- the ``…