Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Ahmed Mehdi Inane

Ahmed Mehdi Inane

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

ML×1Crypto×1

Frequent co-authors

Vincent Quirion1×
Gintare Karolina Dziugaite1×
Ioannis Mitliagkas1×

Research Timeline

2026
Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data

The paper introduces Asymmetric Langevin Unlearning (ALU), a novel framework that uses public data to significantly reduce the utility loss typically associated with certified machine unlearning, enabling mass unlearning while preserving model performance.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CRRecentMay 11, 2026

Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data

Ahmed Mehdi Inane, Vincent Quirion, Gintare Karolina Dziugaite, Ioannis Mitliagkas

The paper introduces Asymmetric Langevin Unlearning (ALU), a novel framework that uses public data to significantly reduce the utility loss typically associated with certified machine unlearning, enab…

View →