4 papers
Parameter-Efficient Generative Modeling with Controlled Vector Fields
Peyman Morteza
We introduce a continuous-time generative modeling framework, motivated by the Chow-Rashevskii theorem, that builds expressive flows from a small set of fixed vector fields and lea…
Representer Theorems for Metric and Preference Learning: Geometric Insights and Algorithms
Peyman Morteza
We develop a mathematical framework to address a broad class of metric and preference learning problems within a Hilbert space. We obtain a novel representer theorem for the simult…
Measures of association between algebraic varieties
Robert Lazarsfeld, Olivier Martin
This paper begins the exploration of what we call measures of association between two irreducible complex projective varieties of the same dimension. The idea is to study from vari…
The Calabi metric and desingularization of Einstein orbifolds
Peyman Morteza, Jeff A. Viaclovsky
Consider an Einstein orbifold of real dimension having a singularity with orbifold group the cyclic group of order in which is generated by an $…