Latest

Every published item, in order · 7652 items
Oct 9
Chinese contentSequential deletion Gaussian mechanism for machine unlearning with GDP privacy certification

arXiv has a new theory paper on machine unlearning, proving that Gaussian noise plus GDP can certify that models after sequential deletion are nearly indistinguishable from retraining, with quantitative bounds on how much less noise is needed for the random walk solution.

arXiv cs.LG@Qi Kuang, Yin XiaSource
Tomorrow 08:00, the daily lands in your inboxTelegram channel or email. Same screening as this page, no ads.
Oct 8

Only the latest 2000 items are listed; for older ones see the daily archive