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

Abstract: 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. For the proposed algorithm, under classical assumptions we prove correctness and almost sure convergence to stationary points. Moreover, the results of experiments on image processing tasks show that the method is indeed viable to be used in practical deep learning scenarios.

Submission Type: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Ahmet_Alacaoglu2

Submission Number: 8689