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

07/06/2020
by   Seth Neel, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/12/2021

Listwise Deletion in High Dimensions

We consider the properties of listwise deletion when both n and the numb...
research
08/11/2022

Quantum Deletion Codes derived from Classical Deletion Codes (Extended Abstract)

This manuscript is an extended abstract version of the paper entitled “Q...
research
01/15/2020

Insertion-Deletion Transformer

We propose the Insertion-Deletion Transformer, a novel transformer-based...
research
06/08/2021

Adaptive Machine Unlearning

Data deletion algorithms aim to remove the influence of deleted data poi...
research
05/29/2020

Algorithms for reconstruction over single and multiple deletion channels

Recent advances in DNA sequencing technology and DNA storage systems hav...
research
06/08/2019

Applications of Gaussian Binomials to Coding Theory for Deletion Error Correction

We present new applications on q-binomials, also known as Gaussian binom...
research
09/11/2018

On the aberrations of mixed level Orthogonal Arrays with removed runs

Given an Orthogonal Array we analyze the aberrations of the sub-fraction...

Please sign up or login with your details

Forgot password? Click here to reset