Machine unlearning for online L-BFGS requires aligning the full optimizer state including memory to a counterfactual history without deleted samples rather than parameter correction alone.
Hessian-free online certified unlearning.arXiv preprint arXiv:2404.01712
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
WIN-U delivers a retain-free unlearning update that approximates the gold-standard retrained model via a Woodbury-informed Newton step using only forget-set curvature information.
A survey that organizes machine unlearning verification methods into behavioral and parametric categories and outlines open problems.
Missing-by-Design learns property-aware embeddings and uses saliency-driven Gaussian updates to produce machine-verifiable certificates that remove a chosen modality without full retraining.
citing papers explorer
-
Form and Function: Machine Unlearning as a Problem of Misaligned States
Machine unlearning for online L-BFGS requires aligning the full optimizer state including memory to a counterfactual history without deleted samples rather than parameter correction alone.
-
WIN-U: Woodbury-Informed Newton-Unlearning as a retain-free Machine Unlearning Framework
WIN-U delivers a retain-free unlearning update that approximates the gold-standard retrained model via a Woodbury-informed Newton step using only forget-set curvature information.
-
Towards Reliable Forgetting: A Survey on Machine Unlearning Verification
A survey that organizes machine unlearning verification methods into behavioral and parametric categories and outlines open problems.
-
Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis
Missing-by-Design learns property-aware embeddings and uses saliency-driven Gaussian updates to produce machine-verifiable certificates that remove a chosen modality without full retraining.