全部动态

AI 相关资讯全量信息流 · 6048 条
10月9日
Sequential 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 Xia原文
10月8日

仅展示最近 2000 条内容,更早的内容请查阅 AI 日报存档