The Lattice Overparametrization Paradigm for the Machine Learning of Lattice Operators

Author(s)

Marcondes, Diego ; Barrera, Junior

• Document type: Journal article
• Source: DISCRETE GEOMETRY AND MATHEMATICAL MORPHOLOGY, DGMM 2024; v. 14605, p. 13-pg., 2024-01-01.

Abstract

The machine learning of lattice operators has three possible bottlenecks. From a statistical standpoint, it is necessary to design a constrained class of operators based on prior information with low bias, and low complexity relative to the sample size. From a computational perspective, there should be an efficient algorithm to minimize an empirical error over the class. From an understanding point of view, the properties of the learned operator need to be derived, so its behavior can be theoretically understood. The statistical bottleneck can be overcome due to the rich literature about the representation of lattice operators, but there is no general learning algorithm for them. In this paper, we discuss a learning paradigm in which, by overparametrizing a class via elements in a lattice, an algorithm for minimizing functions in a lattice is applied to learn. We present the stochastic lattice descent algorithm as a general algorithm to learn on constrained classes of operators as long as a lattice overparametrization of it is fixed, and we discuss previous works which are proves of concept. Moreover, if there are algorithms to compute the basis of an operator from its overparametrization, then its properties can be deduced and the understanding bottleneck is also overcome. This learning paradigm has three properties that modern methods based on neural networks lack: control, transparency and interpretability. Nowadays, there is an increasing demand for methods with these characteristics, and we believe that mathematical morphology is in a unique position to supply them. The lattice overparametrization paradigm could be a missing piece for it to achieve its full potential within modern machine learning. (AU)

• FAPESP's process: 22/06211-2 - Machine learning via learning spaces, from theory to practice: how the lack of data may be mitigated by high computational power
• Grantee: Diego Ribeiro Marcondes
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• FAPESP's process: 23/00256-7 - Prior information in neural networks
• Grantee: Diego Ribeiro Marcondes
• Support Opportunities: Scholarships abroad - Research Internship - Post-doctor
• FAPESP's process: 20/06950-4 - Center for Research and Development on Live Knowledge
• Grantee: João Eduardo Ferreira
• Support Opportunities: Research Grants - Problem-Oriented Research Centers in São Paulo