中文
相关论文

相关论文: Statistical Unlearning of Distributions: A Hypothe…

200 篇论文

We provide a differentially private algorithm for hypothesis selection. Given samples from an unknown probability distribution $P$ and a set of $m$ probability distributions $\mathcal{H}$, the goal is to output, in a…

数据结构与算法 · 计算机科学 2021-01-05 Mark Bun , Gautam Kamath , Thomas Steinke , Zhiwei Steven Wu

This paper considers a problem of distributed hypothesis testing and social learning. Individual nodes in a network receive noisy local (private) observations whose distribution is parameterized by a discrete parameter (hypotheses). The…

统计理论 · 数学 2016-05-17 Anusha Lalitha , Tara Javidi , Anand Sarwate

Recent advances in machine unlearning have focused on developing algorithms to remove specific training samples from a trained model. In contrast, we observe that not all models are equally easy to unlearn. Hence, we introduce a family of…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Amber Yijia Zheng , Yu-Shan Tai , Raymond A. Yeh

Machine unlearning is the process of removing the impact of a particular set of training samples from a pretrained model. It aims to fulfill the "right to be forgotten", which grants the individuals such as patients the right to reconsider…

机器学习 · 计算机科学 2024-07-11 Reza Nasirigerdeh , Nader Razmi , Julia A. Schnabel , Daniel Rueckert , Georgios Kaissis

This paper presents a theoretical analysis of sample selection bias correction. The sample bias correction technique commonly used in machine learning consists of reweighting the cost of an error on each training point of a biased sample to…

机器学习 · 计算机科学 2008-12-18 Corinna Cortes , Mehryar Mohri , Michael Riley , Afshin Rostamizadeh

Machine unlearning is an emerging field that selectively removes specific data samples from a trained model. This capability is crucial for addressing privacy concerns, complying with data protection regulations, and correcting errors or…

机器学习 · 计算机科学 2025-01-29 Zitong Li , Qingqing Ye , Haibo Hu

Structure discovery in graphical models is the determination of the topology of a graph that encodes conditional independence properties of the joint distribution of all variables in the model. For some class of probability distributions,…

机器学习 · 统计学 2016-04-07 Wacha Bounliphone , Matthew Blaschko

We develop a unified theoretical framework for sparse knowledge distillation based on probability-domain softening operators. While the equivalence $p^{1/T} \propto \mathrm{softmax}(z/T)$ is well known, our contribution is an operator-level…

机器学习 · 计算机科学 2026-01-07 Aaron R. Flouro , Shawn P. Chadwick

Universal domain adaptation (UniDA) aims to transfer the knowledge from a labeled source domain to an unlabeled target domain without any assumptions of the label sets, which requires distinguishing the unknown samples from the known ones…

计算机视觉与模式识别 · 计算机科学 2024-10-02 Yifan Wang , Lin Zhang , Ran Song , Paul L. Rosin , Yibin Li , Wei Zhang

The machine learning community is increasingly recognizing the importance of fostering trust and safety in modern generative AI (GenAI) models. We posit machine unlearning (MU) as a crucial foundation for developing safe, secure, and…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Tianqi Chen , Shujian Zhang , Mingyuan Zhou

Machine unlearning focuses on the computationally efficient removal of specific training data from trained models, ensuring that the influence of forgotten data is effectively eliminated without the need for full retraining. Despite…

机器学习 · 统计学 2025-05-13 Haolin Zou , Arnab Auddy , Yongchan Kwon , Kamiar Rahnama Rad , Arian Maleki

Machine unlearning has emerged as a prevalent technical solution for selectively removing unwanted knowledge absorbed during pre-training, without requiring full retraining. While recent unlearning techniques can effectively remove…

机器学习 · 计算机科学 2025-11-04 Myeongseob Ko , Hoang Anh Just , Charles Fleming , Ming Jin , Ruoxi Jia

In unsupervised domain adaptation, it is widely known that the target domain error can be provably reduced by having a shared input representation that makes the source and target domains indistinguishable from each other. Very recently it…

机器学习 · 计算机科学 2019-02-26 Minyoung Kim , Pritish Sahu , Behnam Gholami , Vladimir Pavlovic

Machine learning components are now central to AI-infused software systems, from recommendations and code assistants to clinical decision support. As regulations and governance frameworks increasingly require deleting sensitive data from…

机器学习 · 计算机科学 2026-04-21 Anna Mazhar , Sainyam Galhotra

Large Language Models (LLMs) unlearning is crucial for removing hazardous or privacy-leaking information from the model. Practical LLM unlearning demands satisfying multiple challenging objectives simultaneously: removing undesirable…

机器学习 · 计算机科学 2026-04-20 Yisheng Zhong , Sijia Liu , Zhuangdi Zhu

Machine unlearning aims to remove specific outputs from trained models, often at the concept level, such as forgetting all occurrences of a particular celebrity or filtering content via text prompts. However, many undesired outputs, such as…

机器学习 · 计算机科学 2026-03-13 Kyungryeol Lee , Kyeonghyun Lee , Seongmin Hong , Byung Hyun Lee , Se Young Chun

In many application areas, predictive models are used to support or make important decisions. There is increasing awareness that these models may contain spurious or otherwise undesirable correlations. Such correlations may arise from a…

应用统计 · 统计学 2021-09-21 Emanuele Aliverti , Kristian Lum , James E. Johndrow , David B. Dunson

When learning a mapping from an input space to an output space, the assumption that the sample distribution of the training data is the same as that of the test data is often violated. Unsupervised domain shift methods adapt the learned…

机器学习 · 计算机科学 2017-03-07 Tomer Galanti , Lior Wolf

Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity. We show that these metrics can be misleading, as models can appear to…

计算与语言 · 计算机科学 2026-05-19 Xiaoyu Xu , Xiang Yue , Yang Liu , Qingqing Ye , Huadi Zheng , Peizhao Hu , Minxin Du , Haibo Hu