利用可能与梯度对齐的模型更新来改进遗忘
Improving Unlearning with Model Updates Probably Aligned with Gradients
AI总结：
本文将机器遗忘表述为约束优化问题，提出可行更新概念，通过掩码选择参数并考虑梯度估计噪声，提供统计保证，可作为附加组件提升一阶近似遗忘方法性能。
摘要：
我们将机器遗忘问题表述为一个一般的约束优化问题。它统一了近似机器遗忘文献中的一阶方法。本文随后引入了可行更新的概念，即模型的参数更新方向，这些方向有助于遗忘，同时不降低初始模型的效用。我们对可行更新的设计基于掩码，即仔细选择值得更新的模型参数。在处理每批数据时，它还考虑了梯度的估计噪声，以提供统计保证来推导局部可行更新。该技术可以作为附加组件插入到任何一阶近似遗忘方法中。使用计算机视觉分类器的实验验证了这种方法。
英文摘要：
We formulate the machine unlearning problem as a general constrained optimization problem. It unifies the first-order methods from the approximate machine unlearning literature. This paper then introduces the concept of feasible updates as the model's parameter update directions that help with unlearning while not degrading the utility of the initial model. Our design of feasible updates is based on masking, \ie\ a careful selection of the model's parameters worth updating. It also takes into account the estimation noise of the gradients when processing each batch of data to offer a statistical guarantee to derive locally feasible updates. The technique can be plugged in, as an add-on, to any first-order approximate unlearning methods. Experiments with computer vision classifiers validate this approach.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
