Sample-wise Constrained Learning via a Sequential Penalty Approach with Applications in Image Processing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lanzillotta, Francesca, Albisani, Chiara, Pucci, Davide, Baracchi, Daniele, Piva, Alessandro, Lapucci, Matteo
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914275607445504
author Lanzillotta, Francesca
Albisani, Chiara
Pucci, Davide
Baracchi, Daniele
Piva, Alessandro
Lapucci, Matteo
author_facet Lanzillotta, Francesca
Albisani, Chiara
Pucci, Davide
Baracchi, Daniele
Piva, Alessandro
Lapucci, Matteo
contents In many learning tasks, certain requirements on the processing of individual data samples should arguably be formalized as strict constraints in the underlying optimization problem, rather than by means of arbitrary penalties. We show that, in these scenarios, learning can be carried out exploiting a sequential penalty method that allows to properly deal with constraints. The proposed algorithm is shown to possess convergence guarantees under assumptions that are reasonable in deep learning scenarios. Moreover, the results of experiments on image processing tasks show that the method is indeed viable to be used in practice.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16812
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Sample-wise Constrained Learning via a Sequential Penalty Approach with Applications in Image Processing
Lanzillotta, Francesca
Albisani, Chiara
Pucci, Davide
Baracchi, Daniele
Piva, Alessandro
Lapucci, Matteo
Machine Learning
Image and Video Processing
Optimization and Control
68T07, 90C30, 68U10, 90C06, 65K05, 90C26
In many learning tasks, certain requirements on the processing of individual data samples should arguably be formalized as strict constraints in the underlying optimization problem, rather than by means of arbitrary penalties. We show that, in these scenarios, learning can be carried out exploiting a sequential penalty method that allows to properly deal with constraints. The proposed algorithm is shown to possess convergence guarantees under assumptions that are reasonable in deep learning scenarios. Moreover, the results of experiments on image processing tasks show that the method is indeed viable to be used in practice.
title Sample-wise Constrained Learning via a Sequential Penalty Approach with Applications in Image Processing
topic Machine Learning
Image and Video Processing
Optimization and Control
68T07, 90C30, 68U10, 90C06, 65K05, 90C26
url https://arxiv.org/abs/2601.16812