On the impact of measure pre-conditionings on general parametric ML models and transfer learning via domain adaptation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autor principal: García, Joaquín Sánchez
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914702039187456
author García, Joaquín Sánchez
author_facet García, Joaquín Sánchez
contents We study a new technique for understanding convergence of learning agents under small modifications of data. We show that such convergence can be understood via an analogue of Fatou's lemma which yields gamma-convergence. We show it's relevance and applications in general machine learning tasks and domain adaptation transfer learning.
format Preprint
id arxiv_https___arxiv_org_abs_2403_02432
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On the impact of measure pre-conditionings on general parametric ML models and transfer learning via domain adaptation
García, Joaquín Sánchez
Machine Learning
Optimization and Control
We study a new technique for understanding convergence of learning agents under small modifications of data. We show that such convergence can be understood via an analogue of Fatou's lemma which yields gamma-convergence. We show it's relevance and applications in general machine learning tasks and domain adaptation transfer learning.
title On the impact of measure pre-conditionings on general parametric ML models and transfer learning via domain adaptation
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2403.02432