Learning Privately with Labeled and Unlabeled Examples
نویسندگان
چکیده
منابع مشابه
Learning Privately with Labeled and Unlabeled Examples
A private learner is an algorithm that given a sample of labeled individual examples outputs a generalizing hypothesis while preserving the privacy of each individual. In 2008, Kasiviswanathan et al. (FOCS 2008) gave a generic construction of private learners, in which the sample complexity is (generally) higher than what is needed for non-private learners. This gap in the sample complexity was...
متن کاملMachine Learning with Labeled and Unlabeled Data
The field of semi-supervised learning has been expanding rapidly in the past few years, with a sheer increase in the number of related publications. In this paper we present the SSL problem in contrast with supervised and unsupervised learning. In addition, we propose a taxonomy with which we categorize many existing approaches described in the literature based on their underlying framework, da...
متن کاملLearning with labeled and unlabeled data
In this paper, on the one hand, we aim to give a review on literature dealing with the problem of supervised learning aided by additional unlabeled data. On the other hand, being a part of the author’s first year PhD report, the paper serves as a frame to bundle related work by the author as well as numerous suggestions for potential future work. Therefore, this work contains more speculative a...
متن کاملPositive and Unlabeled Examples Help Learning
In many learning problems, labeled examples are rare or expensive while numerous unlabeled and positive examples are available. However, most learning algorithms only use labeled examples. Thus we address the problem of learning with the help of positive and unlabeled data given a small number of labeled examples. We present both theoretical and empirical arguments showing that learning algorit...
متن کاملLearning from Positive and Unlabeled Examples
In many machine learning settings, labeled examples are difficult to collect while unlabeled data are abundant. Also, for some binary classification problems, positive examples which are elements of the target concept are available. Can these additional data be used to improve accuracy of supervised learning algorithms? We investigate in this paper the design of learning algorithms from positiv...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Algorithmica
سال: 2020
ISSN: 0178-4617,1432-0541
DOI: 10.1007/s00453-020-00753-z