Score: 0

Improving Unlearning with Model Updates Probably Aligned with Gradients

Published: November 4, 2025 | arXiv ID: 2511.02435v1

By: Virgile Dine, Teddy Furon, Charly Faure

Potential Business Impact:

Removes specific data from AI without breaking it.

Business Areas:
Machine Learning Artificial Intelligence, Data and Analytics, Software

We formulate the machine unlearning problem as a general constrained optimization problem. It unifies the first-order methods from the approximate machine unlearning literature. This paper then introduces the concept of feasible updates as the model's parameter update directions that help with unlearning while not degrading the utility of the initial model. Our design of feasible updates is based on masking, \ie\ a careful selection of the model's parameters worth updating. It also takes into account the estimation noise of the gradients when processing each batch of data to offer a statistical guarantee to derive locally feasible updates. The technique can be plugged in, as an add-on, to any first-order approximate unlearning methods. Experiments with computer vision classifiers validate this approach.

Page Count
25 pages

Category
Computer Science:
Machine Learning (CS)