Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.10680 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910209371275264 |
|---|---|
| author | Dine, Virgile Furon, Teddy |
| author_facet | Dine, Virgile Furon, Teddy |
| contents | This paper proposes a paradigm shift linking machine unlearning directly to the structure of the data distributions rather than a mere update of the neural network parameters. We show that inferring these distributions with precision enables distilling the exact unlearning signal induced by the modeling. Theoretical bounds on the Kullback-Leibler divergence from the ideal retrained model to our unlearned model, under verifiable admissibility criterion, reveal the soundness of our framework. This method is experimentally validated over three forgetting scenarios as reaching the closest classifier to the ideal retrained model when compared to competitors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10680 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Exact Unlearning from Proxies Induces Closeness Guarantees on Approximate Unlearning Dine, Virgile Furon, Teddy Machine Learning This paper proposes a paradigm shift linking machine unlearning directly to the structure of the data distributions rather than a mere update of the neural network parameters. We show that inferring these distributions with precision enables distilling the exact unlearning signal induced by the modeling. Theoretical bounds on the Kullback-Leibler divergence from the ideal retrained model to our unlearned model, under verifiable admissibility criterion, reveal the soundness of our framework. This method is experimentally validated over three forgetting scenarios as reaching the closest classifier to the ideal retrained model when compared to competitors. |
| title | Exact Unlearning from Proxies Induces Closeness Guarantees on Approximate Unlearning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.10680 |