Sample Complexity Bounds on Differentially Private Learning via Communication Complexity

نویسندگان
چکیده

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Sample Complexity Bounds on Differentially Private Learning via Communication Complexity

In this work we analyze the sample complexity of classification by differentially private algorithms. Differential privacy is a strong and well-studied notion of privacy introduced by Dwork et al. (2006) that ensures that the output of an algorithm leaks little information about the data point provided by any of the participating individuals. Sample complexity of private PAC and agnostic learni...

متن کامل

Sample Complexity Bounds for Differentially Private Learning

This work studies the problem of privacy-preserving classification - namely, learning a classifier from sensitive data while preserving the privacy of individuals in the training set. In particular, the learning algorithm is required in this problem to guarantee differential privacy, a very strong notion of privacy that has gained significant attention in recent years. A natural question to ask...

متن کامل

Coarse sample complexity bounds for active learning

We characterize the sample complexity of active learning problems in terms of a parameter which takes into account the distribution over the input space, the specific target hypothesis, and the desired accuracy.

متن کامل

Lower Bounds on Communication Complexity ∗

A notion of ”communication complexity” is used to formally measure the degree to which a Boolean function is ”global”. An explicit combinatorial lower bound for this complexity measure is presented. In particular, this leads to an exp(Ω( √ n)) lower bound on the complexity of depth-restricted contact schemes computing some natural Boolean functions in NP.

متن کامل

Neural Network Learning: Testing Bounds on Sample Complexity

Several authors have theoretically determined distribution-free bounds on sample complexity. Formulas based on several learning paradigms have been presented. However, little is known on how these formulas perform and compare with each other in practice. To our knowledge, controlled experimental results using these formulas, and comparing of their behavior, have not so far been presented. The p...

متن کامل

ذخیره 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: SIAM Journal on Computing

سال: 2015

ISSN: 0097-5397,1095-7111

DOI: 10.1137/140991844