2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton)最新文献_第7页

Recovering communities in weighted stochastic block models 加权随机块模型中的群落恢复

2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton) Pub Date : 2015-09-01 DOI: 10.1109/ALLERTON.2015.7447159

Varun Jog, Po-Ling Loh

{"title":"Recovering communities in weighted stochastic block models","authors":"Varun Jog, Po-Ling Loh","doi":"10.1109/ALLERTON.2015.7447159","DOIUrl":"https://doi.org/10.1109/ALLERTON.2015.7447159","url":null,"abstract":"We derive sharp thresholds for exact recovery of communities in a weighted stochastic block model, where observations are collected in the form of a weighted adjacency matrix, and the weight of each edge is generated independently from a distribution determined by the community membership of its endpoints. Our main result, characterizing the precise boundary between success and failure of maximum likelihood estimation when edge weights are drawn from discrete distributions, involves the Renyi divergence of order 1/2 between the distributions of within-community and between-community edges. When the Renyi divergence is above a certain threshold, meaning the edge distributions are sufficiently separated, maximum likelihood succeeds with probability tending to 1; when the Renyi divergence is below the threshold, maximum likelihood fails with probability bounded away from 0. In the language of graphical channels, the Renyi divergence pinpoints the information-theoretic capacity of discrete graphical channels with binary inputs. Our results generalize previously established thresholds derived specifically for unweighted block models, and support an important natural intuition relating the intrinsic hardness of community estimation to the problem of edge classification. Along the way, we establish a general relationship between the Renyi divergence and the probability of success of the maximum likelihood estimator for arbitrary edge weight distributions. Finally, we discuss consequences of our bounds for the related problems of censored block models and submatrix localization, which may be seen as special cases of the framework developed in our paper.","PeriodicalId":112948,"journal":{"name":"2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116708269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Privacy-preserving deep learning 保护隐私的深度学习

2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton) Pub Date : 2015-09-01 DOI: 10.1145/2810103.2813687

R. Shokri, Vitaly Shmatikov

{"title":"Privacy-preserving deep learning","authors":"R. Shokri, Vitaly Shmatikov","doi":"10.1145/2810103.2813687","DOIUrl":"https://doi.org/10.1145/2810103.2813687","url":null,"abstract":"Deep learning based on artificial neural networks is a very popular approach to modeling, classifying, and recognizing complex data such as images, speech, and text. The unprecedented accuracy of deep learning methods has turned them into the foundation of new AI-based services on the Internet. Commercial companies that collect user data on a large scale have been the main beneficiaries of this trend since the success of deep learning techniques is directly proportional to the amount of data available for training. Massive data collection required for deep learning presents obvious privacy issues. Users' personal, highly sensitive data such as photos and voice recordings is kept indefinitely by the companies that collect it. Users can neither delete it, nor restrict the purposes for which it is used. Furthermore, centrally kept data is subject to legal subpoenas and extrajudicial surveillance. Many data owners-for example, medical institutions that may want to apply deep learning methods to clinical records-are prevented by privacy and confidentiality concerns from sharing the data and thus benefitting from large-scale deep learning. In this paper, we present a practical system that enables multiple parties to jointly learn an accurate neural-network model for a given objective without sharing their input datasets. We exploit the fact that the optimization algorithms used in modern deep learning, namely, those based on stochastic gradient descent, can be parallelized and executed asynchronously. Our system lets participants train independently on their own datasets and selectively share small subsets of their models' key parameters during training. This offers an attractive point in the utility/privacy tradeoff space: participants preserve the privacy of their respective data while still benefitting from other participants' models and thus boosting their learning accuracy beyond what is achievable solely on their own inputs. We demonstrate the accuracy of our privacy-preserving deep learning on benchmark datasets.","PeriodicalId":112948,"journal":{"name":"2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton)","volume":"183 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115552707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1861

Statistical and information-theoretic optimization and performance bounds of video steganography 视频隐写的统计和信息论优化及性能界限

2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton) Pub Date : 2015-09-01 DOI: 10.1109/ALLERTON.2015.7447179

M. Sharifzadeh, D. Schonfeld

引用次数: 4

Quickest detection of Gauss-Markov random fields 快速检测高斯-马尔可夫随机场

2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton) Pub Date : 2015-09-01 DOI: 10.1109/ALLERTON.2015.7447089

Javad Heydari, A. Tajer, H. Poor

引用次数: 8

Partial compute-compress-and-forward for limited backhaul uplink multicell processing 有限回程上行链路多单元处理的部分计算压缩转发

2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton) Pub Date : 2015-09-01 DOI: 10.1109/ALLERTON.2015.7447153

Iñaki Estella Aguerri, A. Zaidi

引用次数: 5

Absence of isolated nodes in inhomogeneous random key graphs 非齐次随机键图中孤立节点的缺失

2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton) Pub Date : 2015-09-01 DOI: 10.1109/ALLERTON.2015.7447143

Osman Yağan

引用次数: 1

Robust estimation using context-aware filtering 使用上下文感知过滤的鲁棒估计

2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton) Pub Date : 2015-09-01 DOI: 10.1109/ALLERTON.2015.7447058

Radoslav Ivanov, Nikolay A. Atanasov, M. Pajic, George J. Pappas, Insup Lee

引用次数: 11

Degrees of freedom of bursty multiple access channels with a relay 带中继的突发多址信道的自由度

2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton) Pub Date : 2015-09-01 DOI: 10.1109/ALLERTON.2015.7447022

Sunghyun Kim, Changho Suh

引用次数: 1

Non-isomorphic distribution supports for calculating entropic vectors 非同构分布支持计算熵向量

2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton) Pub Date : 2015-09-01 DOI: 10.1109/ALLERTON.2015.7447064

Yunshu Liu, J. Walsh

引用次数: 3

Online learning for demand response 需求响应的在线学习

2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton) Pub Date : 2015-09-01 DOI: 10.1109/ALLERTON.2015.7447007

D. Kalathil, R. Rajagopal

引用次数: 15