AI RESEARCH
Form and Function: Machine Unlearning as a Problem of Misaligned States
arXiv CS.LG
•
ArXi:2605.17590v1 Announce Type: new We formulate machine unlearning for online L-BFGS as a counterfactual state-alignment problem. Given an actual event stream and a deletion-edited counterfactual stream, the target of unlearning is the optimizer state that would have arisen had the deleted samples never been processed. We