Events
CDS Seminar: Efficient deletion of data from trained AI models
Speaker: Sam Gunn (MIT)
Location: 60 Fifth Avenue, Room 7th Floor Open Space
Date: Friday, October 23, 2026
Abstract: How does the choice of training data influence an AI model? This question is of central importance to interpretability, privacy, data attribution, and basic science. At its core is the data deletion problem: after a reasonable amount of precomputation, quickly predict how the model would behave if a given subset of training data had been deleted.
I will present a data deletion scheme capable of predicting model outputs to arbitrary precision. A bound on the error can be derived from a simple assumption about the stability of the AI model. In contrast to the assumptions made by prior work, ours appears to be fully compatible with deep learning. We believe that this method opens up a range of new possibilities for theory in AI. For instance, it gives the first 'machine unlearning' scheme with provable security in the deep learning setting.
Based on my recent work "How to sketch a learning algorithm" at https://arxiv.org/pdf/2604.07328.