paper-with-me

홈 › Papers

Descent-to-Delete: Gradient-Based Methods for Machine Unlearning

2020-07-06 · Seth Neel, Aaron Roth, Saeed Sharifi-Malvajerdi

We study the data deletion problem for convex models. By leveraging techniques from convex optimization and reservoir sampling, we give the first data deletion algorithms that are able to handle an arbitrarily long sequence of adversarial updates while promising both per-deletion run-time and steady-state error that do not grow with the length of the update sequence. We also introduce several new conceptual distinctions: for example, we can ask that after a deletion, the entire state maintained by the optimization algorithm is statistically indistinguishable from the state that would have resulted had we retrained, or we can ask for the weaker condition that only the observable output is statistically indistinguishable from the observable output that would have resulted from retraining. We are able to give more efficient deletion algorithms under this weaker deletion criterion.

📄 PDF Abstract BibTeX arXiv:2007.02923

Code (2)

ChrisWaites/data-deletion jax
ChrisWaites/descent-to-delete jax

Tasks

Machine Unlearning

Similar Papers 제목 키워드 기반

Forget Unlearning: Towards True Data-Deletion in Machine Learning

2022-10-17 · Rishav Chourasia, Neil Shah

Unlearning algorithms aim to remove deleted data's influence from trained models at a cost lower than full retraining. However, prior guarantees of unlearning in literature are flawed and don't protect the privacy of del…

Machine Unlearning

Descend or Rewind? Stochastic Gradient Descent Unlearning

2025-11-20 · Siqiao Mu, Diego Klabjan arxiv

Machine unlearning algorithms aim to remove the impact of selected training data from a model without the computational expenses of retraining from scratch. Two such algorithms are ``Descent-to-Delete" (D2D) and ``Rewind…

Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions

2024-09-15 · Siqiao Mu, Diego Klabjan

Machine unlearning algorithms aim to efficiently remove data from a model without retraining it from scratch, in order to remove corrupted or outdated data or respect a user's ``right to be forgotten." Certified machine …

Machine Unlearning

Online Learning and Unlearning

2025-05-13 · Yaxi Hu, Bernhard Schölkopf, Amartya Sanyal

We formalize the problem of online learning-unlearning, where a model is updated sequentially in an online setting while accommodating unlearning requests between updates. After a data point is unlearned, all subsequent …

Certifiable Machine Unlearning for Linear Models

2021-06-29 · Ananth Mahadevan, Michael Mathioudakis

Machine unlearning is the task of updating machine learning (ML) models after a subset of the training data they were trained on is deleted. Methods for the task are desired to combine effectiveness and efficiency, i.e.,…

Machine Unlearning