{"title":"从自适应查询释放到机器学习","authors":"Enayat Ullah, R. Arora","doi":"10.48550/arXiv.2307.11228","DOIUrl":null,"url":null,"abstract":"We formalize the problem of machine unlearning as design of efficient unlearning algorithms corresponding to learning algorithms which perform a selection of adaptive queries from structured query classes. We give efficient unlearning algorithms for linear and prefix-sum query classes. As applications, we show that unlearning in many problems, in particular, stochastic convex optimization (SCO), can be reduced to the above, yielding improved guarantees for the problem. In particular, for smooth Lipschitz losses and any $\\rho>0$, our results yield an unlearning algorithm with excess population risk of $\\tilde O\\big(\\frac{1}{\\sqrt{n}}+\\frac{\\sqrt{d}}{n\\rho}\\big)$ with unlearning query (gradient) complexity $\\tilde O(\\rho \\cdot \\text{Retraining Complexity})$, where $d$ is the model dimensionality and $n$ is the initial number of samples. For non-smooth Lipschitz losses, we give an unlearning algorithm with excess population risk $\\tilde O\\big(\\frac{1}{\\sqrt{n}}+\\big(\\frac{\\sqrt{d}}{n\\rho}\\big)^{1/2}\\big)$ with the same unlearning query (gradient) complexity. Furthermore, in the special case of Generalized Linear Models (GLMs), such as those in linear and logistic regression, we get dimension-independent rates of $\\tilde O\\big(\\frac{1}{\\sqrt{n}} +\\frac{1}{(n\\rho)^{2/3}}\\big)$ and $\\tilde O\\big(\\frac{1}{\\sqrt{n}} +\\frac{1}{(n\\rho)^{1/3}}\\big)$ for smooth Lipschitz and non-smooth Lipschitz losses respectively. Finally, we give generalizations of the above from one unlearning request to \\textit{dynamic} streams consisting of insertions and deletions.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"11 1","pages":"34642-34667"},"PeriodicalIF":0.0000,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"From Adaptive Query Release to Machine Unlearning\",\"authors\":\"Enayat Ullah, R. Arora\",\"doi\":\"10.48550/arXiv.2307.11228\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We formalize the problem of machine unlearning as design of efficient unlearning algorithms corresponding to learning algorithms which perform a selection of adaptive queries from structured query classes. We give efficient unlearning algorithms for linear and prefix-sum query classes. As applications, we show that unlearning in many problems, in particular, stochastic convex optimization (SCO), can be reduced to the above, yielding improved guarantees for the problem. In particular, for smooth Lipschitz losses and any $\\\\rho>0$, our results yield an unlearning algorithm with excess population risk of $\\\\tilde O\\\\big(\\\\frac{1}{\\\\sqrt{n}}+\\\\frac{\\\\sqrt{d}}{n\\\\rho}\\\\big)$ with unlearning query (gradient) complexity $\\\\tilde O(\\\\rho \\\\cdot \\\\text{Retraining Complexity})$, where $d$ is the model dimensionality and $n$ is the initial number of samples. For non-smooth Lipschitz losses, we give an unlearning algorithm with excess population risk $\\\\tilde O\\\\big(\\\\frac{1}{\\\\sqrt{n}}+\\\\big(\\\\frac{\\\\sqrt{d}}{n\\\\rho}\\\\big)^{1/2}\\\\big)$ with the same unlearning query (gradient) complexity. Furthermore, in the special case of Generalized Linear Models (GLMs), such as those in linear and logistic regression, we get dimension-independent rates of $\\\\tilde O\\\\big(\\\\frac{1}{\\\\sqrt{n}} +\\\\frac{1}{(n\\\\rho)^{2/3}}\\\\big)$ and $\\\\tilde O\\\\big(\\\\frac{1}{\\\\sqrt{n}} +\\\\frac{1}{(n\\\\rho)^{1/3}}\\\\big)$ for smooth Lipschitz and non-smooth Lipschitz losses respectively. Finally, we give generalizations of the above from one unlearning request to \\\\textit{dynamic} streams consisting of insertions and deletions.\",\"PeriodicalId\":74529,\"journal\":{\"name\":\"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning\",\"volume\":\"11 1\",\"pages\":\"34642-34667\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-07-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2307.11228\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2307.11228","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

我们将机器学习问题形式化为有效的学习算法的设计,该算法对应于从结构化查询类中选择自适应查询的学习算法。给出了线性查询类和前缀和查询类的有效学习算法。作为应用,我们证明了在许多问题中,特别是随机凸优化(SCO)中的学习可以简化为上述问题,从而提高了对问题的保证。特别是,对于平滑Lipschitz损失和任何$\rho>0$,我们的结果产生了一个具有过度人口风险的取消学习算法$\tilde O\big(\frac{1}{\sqrt{n}}+\frac{\sqrt{d}}{n\rho}\big)$和取消学习查询(梯度)复杂性$\tilde O(\rho \cdot \text{Retraining Complexity})$,其中$d$是模型维数,$n$是初始样本数。对于非光滑Lipschitz损失,我们给出了一种具有超额人口风险$\tilde O\big(\frac{1}{\sqrt{n}}+\big(\frac{\sqrt{d}}{n\rho}\big)^{1/2}\big)$的学习算法,该算法具有相同的学习查询(梯度)复杂度。此外,在广义线性模型(GLMs)的特殊情况下,如线性回归和逻辑回归,我们分别得到光滑Lipschitz和非光滑Lipschitz损失的$\tilde O\big(\frac{1}{\sqrt{n}} +\frac{1}{(n\rho)^{2/3}}\big)$和$\tilde O\big(\frac{1}{\sqrt{n}} +\frac{1}{(n\rho)^{1/3}}\big)$的维无关率。最后,我们给出了上述的概括,从一个遗忘请求到由插入和删除组成的\textit{动态}流。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
From Adaptive Query Release to Machine Unlearning
We formalize the problem of machine unlearning as design of efficient unlearning algorithms corresponding to learning algorithms which perform a selection of adaptive queries from structured query classes. We give efficient unlearning algorithms for linear and prefix-sum query classes. As applications, we show that unlearning in many problems, in particular, stochastic convex optimization (SCO), can be reduced to the above, yielding improved guarantees for the problem. In particular, for smooth Lipschitz losses and any $\rho>0$, our results yield an unlearning algorithm with excess population risk of $\tilde O\big(\frac{1}{\sqrt{n}}+\frac{\sqrt{d}}{n\rho}\big)$ with unlearning query (gradient) complexity $\tilde O(\rho \cdot \text{Retraining Complexity})$, where $d$ is the model dimensionality and $n$ is the initial number of samples. For non-smooth Lipschitz losses, we give an unlearning algorithm with excess population risk $\tilde O\big(\frac{1}{\sqrt{n}}+\big(\frac{\sqrt{d}}{n\rho}\big)^{1/2}\big)$ with the same unlearning query (gradient) complexity. Furthermore, in the special case of Generalized Linear Models (GLMs), such as those in linear and logistic regression, we get dimension-independent rates of $\tilde O\big(\frac{1}{\sqrt{n}} +\frac{1}{(n\rho)^{2/3}}\big)$ and $\tilde O\big(\frac{1}{\sqrt{n}} +\frac{1}{(n\rho)^{1/3}}\big)$ for smooth Lipschitz and non-smooth Lipschitz losses respectively. Finally, we give generalizations of the above from one unlearning request to \textit{dynamic} streams consisting of insertions and deletions.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition Probabilistic Imputation for Time-series Classification with Missing Data Decoding Layer Saliency in Language Transformers Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1