English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Machine unlearning has raised significant interest with the adoption of lawsensuring the ``right to be forgotten''. Researchers have provided aprobabilistic notion of approximate unlearning under a similar definition ofDifferential Privacy (DP), where privacy is defined as statisticalindistinguishability to retraining from scratch. We propose Langevinunlearning, an unlearning framework based on noisy gradient descent withprivacy guarantees for approximate unlearning problems. Langevin unlearningunifies the DP learning process and the privacy-certified unlearning processwith many algorithmic benefits. These include approximate certified unlearningfor non-convex problems, complexity saving compared to retraining, sequentialand batch unlearning for multiple unlearning requests. We verify thepracticality of Langevin unlearning by studying its privacy-utility-complexitytrade-off via experiments on benchmark datasets, and also demonstrate itssuperiority against gradient-decent-plus-output-perturbation based approximateunlearning.

Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning