Faculty & Research

Publications

Publications

Filter Results : (2) Arrow Down

Show Results For

Unlearning Algorithm Remove Unlearning Algorithm →

Page 1 of 2 Results

Are you looking for?

→ Search All HBS Web
  • 2021
  • Article

Adaptive Machine Unlearning
By: Seth Neel
Data deletion algorithms aim to remove the influence of deleted data points from trained models at a cheaper computational cost than fully retraining those models. However, for sequences of deletions, most prior work in the non-convex setting gives valid guarantees...  View Details
Keywords: Machine Learning
Related
  • Mar 2021
  • Conference Presentation

Descent-to-Delete: Gradient-Based Methods for Machine Unlearning
By: Seth Neel, Aaron Leon Roth and 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...  View Details
Keywords: Machine Learning; Unlearning Algorithm; Mathematical Methods
Related

Are you looking for?

→ Search All HBS Web