Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Filters
























9,081 Hits in 4.3 sec

Piecewise Function Approximation With Private Data

Riccardo Lazzeretti, Tommaso Pignata, Mauro Barni
2016 IEEE Transactions on Information Forensics and Security  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.0 MB)
https://web.archive.org/web/20200829215713/https://arxiv.org/pdf/1503.05144v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

2015 pre-print arXiv:1503.05144v1 fatcat:cvieav7jwjgdnidubsamxnpwkm
We present two Secure Two Party Computation (STPC) protocols for piecewise function approximation on private data.  ...  The protocols rely on a piecewise approximation of the to-be-computed function easing the implementation in a STPC setting.  ...  [8] , processing of private user preferences [9] , fusion of private data [10] , etc.  ... 
doi:10.1109/tifs.2015.2503268 fatcat:ldolo5gr2vbexjx4ajgb4zlfqy
Multiple Versions
Citation

Riccardo Lazzeretti, Tommaso Pignata, Mauro Barni. "Piecewise Function Approximation With Private Data." IEEE Transactions on Information Forensics and Security 11.3 (2016) 642-657

Secure Approximation Guarantee for Cryptographically Private Empirical Risk Minimization [article]

Toshiyuki Takada, Hiroyuki Hanada, Yoshiji Yamada, Jun Sakuma, Ichiro Takeuchi
2016 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.2 MB)
https://web.archive.org/web/20200930172034/https://arxiv.org/pdf/1602.04579v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

One of limitations in current cryptographically private ML is that it is computationally intractable to evaluate non-linear functions such as logarithmic functions or exponential functions.  ...  In this paper, we introduce a novel cryptographically private tool called secure approximation guarantee (SAG) method.  ...  with true logistic function, while the latter is obtained with the approximate logistic function.  ... 
arXiv:1602.04579v1 fatcat:r4x4mqco3fgojcncqxucynn7jy
Citation

Toshiyuki Takada, Hiroyuki Hanada, Yoshiji Yamada, Jun Sakuma, Ichiro Takeuchi. "Secure Approximation Guarantee for Cryptographically Private Empirical Risk Minimization." arXiv (2016)

Differentially Private Learning of Structured Discrete Distributions

Ilias Diakonikolas, Moritz Hardt, Ludwig Schmidt
2015 Neural Information Processing Systems  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (384.5 kB)
https://web.archive.org/web/20160411063436/http://papers.nips.cc/paper/5713-differentially-private-learning-of-structured-discrete-distributions.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL. The file type is application/pdf.

Our experiments illustrate the speed and accuracy of our private estimators on both synthetic mixture models and a large public data set.  ...  We complement our theoretical guarantees with an experimental evaluation.  ...  a piecewise linear function.  ... 
dblp:conf/nips/DiakonikolasHS15 fatcat:jgq3kaoagzbbhgxmktly4oilqe
Citation

Ilias Diakonikolas, Moritz Hardt, Ludwig Schmidt. "Differentially Private Learning of Structured Discrete Distributions." Neural Information Processing Systems (2015) 2566-2574

More Flexible Differential Privacy: The Application of Piecewise Mixture Distributions in Query Release [article]

David B. Smith, Kanchana Thilakarathna, Mohamed Ali Kaafar
2017 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (935.7 kB)
https://web.archive.org/web/20191016032909/https://arxiv.org/pdf/1707.01189v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL. The file type is application/pdf.

Other Versions

2017 pre-print
arXiv:1707.01189v2 fatcat:rggf7zefcbdgfhb6mo4oh76fie
2017 pre-print
arXiv:1707.01189v1 fatcat:l3syg5gktfg77fqpbb3qxacsfu
We then empirically evaluate the performance of piecewise mixture distributions with extensive simulations and with a real-world dataset for both linear count queries and histogram queries.  ...  However, with a wide variety of sensitive data collected, protecting privacy of individuals, communities and organizations, is an essential factor in making data "open".  ...  data set particularly suited to private linear querying.  ... 
arXiv:1707.01189v3 fatcat:sugcxewma5fifni27ekvflqapu
Multiple Versions
Citation

David B. Smith, Kanchana Thilakarathna, Mohamed Ali Kaafar. "More Flexible Differential Privacy: The Application of Piecewise Mixture Distributions in Query Release." arXiv (2017)

Differentially private convex optimization with piecewise affine objectives

Shuo Han, Ufuk Topcu, George J. Pappas
2014 53rd IEEE Conference on Decision and Control  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (279.0 kB)
https://web.archive.org/web/20170808121727/http://www.seas.upenn.edu/~hanshuo/papers/2014-cdc-dp_pwa.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL. The file type is application/pdf.

The paper studies the problem of computing a differentially private solution to convex optimization problems whose objective function is piecewise affine.  ...  Such problems are motivated by applications in which the affine functions that define the objective function contain sensitive user information.  ...  The authors would like to thank Aaron Roth for providing early access to the draft on differentially private linear programming [11] and helpful discussions on differential privacy.  ... 
doi:10.1109/cdc.2014.7039718 dblp:conf/cdc/HanTP14 fatcat:r4zwavb4bjevdh3dp2wkrp2l2u
Citation

Shuo Han, Ufuk Topcu, George J. Pappas. "Differentially private convex optimization with piecewise affine objectives." 53rd IEEE Conference on Decision and Control (2014) 2160-2166

Privacy-Preserving Backpropagation Neural Network Learning

Tingting Chen, Sheng Zhong
2009 IEEE Transactions on Neural Networks  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (221.0 kB)
https://web.archive.org/web/20170808085924/https://www.cse.buffalo.edu//caeiae/documents/pdf/back-propagation-chen-zhong-2009.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL. The file type is application/pdf.

With the development of distributed computing environment, many learning problems now have to deal with distributed input data.  ...  To enhance coorperations in learning, it is important to address the privacy concern of each data holder by extending the privacy preservation notion to original learning algorithms.  ...  The piecewise linear approximation of activation function In this subsection, we introduce the piecewise linear approximation of activation function.  ... 
doi:10.1109/tnn.2009.2026902 pmid:19709975 fatcat:cgcyznpmmzdohoenrqpheu7ia4
Citation

Tingting Chen, Sheng Zhong. "Privacy-Preserving Backpropagation Neural Network Learning." IEEE Transactions on Neural Networks 20.10 (2009) 1554-1564

Dispersion for Data-Driven Algorithm Design, Online Learning, and Private Optimization [article]

Maria-Florina Balcan, Travis Dick, Ellen Vitercik
2018 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (981.9 kB)
https://web.archive.org/web/20200909034940/https://arxiv.org/pdf/1711.03091v4.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2018 pre-print
arXiv:1711.03091v2 fatcat:fyz3kppmevaubngi54ao6pr67i
2017 pre-print
arXiv:1711.03091v1 fatcat:4ahfzsj22nhltd5mgzlpw2cawa
2018 pre-print
arXiv:1711.03091v3 fatcat:u44akq7egnah7ldvv7mx3nwgx4
We present general techniques for online and private optimization of the sum of dispersed piecewise Lipschitz functions.  ...  We give a sufficient and general condition, dispersion, defining a family of piecewise Lipschitz functions that can be optimized online and privately, which includes the functions measuring the performance  ...  Private empirical risk minimization (ERM) The goal of private ERM is to find the best machine learning model parameters based on private data.  ... 
arXiv:1711.03091v4 fatcat:4yngbjnawzgz3eeo6cfhzudjyu
Multiple Versions
Citation

Maria-Florina Balcan, Travis Dick, Ellen Vitercik. "Dispersion for Data-Driven Algorithm Design, Online Learning, and Private Optimization." arXiv (2018)

Differentially Private Convex Optimization with Piecewise Affine Objectives [article]

Shuo Han, Ufuk Topcu, George J. Pappas
2014 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (516.6 kB)
https://web.archive.org/web/20200903045925/https://arxiv.org/pdf/1403.6135v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

The paper studies the problem of computing a differentially private solution to convex optimization problems whose objective function is piecewise affine.  ...  Such problem is motivated by applications in which the affine functions that define the objective function contain sensitive user information.  ...  The authors would like to thank Aaron Roth for providing early access to the draft on differentially private linear programming [11] and helpful discussions on differential privacy.  ... 
arXiv:1403.6135v1 fatcat:wubygykxrfeu3l5qxxv23is5o4
Citation

Shuo Han, Ufuk Topcu, George J. Pappas. "Differentially Private Convex Optimization with Piecewise Affine Objectives." arXiv (2014)

Privacy-preserving collaborative machine learning on genomic data using TensorFlow [article]

Cheng Hong, Zhicong Huang, Wen-jie Lu, Hunter Qu, Li Ma, Morten Dahl, Jason Mancuso
2020 arXiv   pre-print

Preserved Fulltext

Web Archive Capture PDF (333.7 kB)
https://web.archive.org/web/20200322043111/https://arxiv.org/pdf/2002.04344v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2020 pre-print
arXiv:2002.04344v1 fatcat:coo23bu5aff43aunm5odyrabl4
We design and implement several MPC-friendly ML primitives, including class weight adjustment and parallelizable approximation of activation function.  ...  However, genomic data are often held by different stakeholders (e.g. hospitals, universities, and healthcare companies) who consider the data as sensitive information, even though they desire to collaborate  ...  Note that we cannot lookup C yi directly since y i is a private input, so instead we compute it via C yi = (C 1 − C 0 ) · y i + C 0 . Parallel piecewise approximation of the sigmoid function.  ... 
arXiv:2002.04344v2 fatcat:dyiaoxewvfa3pcdcyn5yd2fh7i
Multiple Versions
Citation

Cheng Hong, Zhicong Huang, Wen-jie Lu, Hunter Qu, Li Ma, Morten Dahl, Jason Mancuso. "Privacy-preserving collaborative machine learning on genomic data using TensorFlow." arXiv (2020)

Congestion-aware Routing and Rebalancing of Autonomous Mobility-on-Demand Systems in Mixed Traffic [article]

Salomón Wollenstein-Betech, Arian Houshmand, Mauro Salazar, Marco Pavone, Christos G. Cassandras, Ioannis Ch. Paschalidis
2020 arXiv   pre-print

Preserved Fulltext

Web Archive Capture PDF (1.0 MB)
https://web.archive.org/web/20200320174530/https://arxiv.org/pdf/2003.04335v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Second, we capture reactive exogenous traffic consisting of private vehicles selfishly adapting to the AMoD flows in a user-centric fashion by leveraging an iterative approach.  ...  Finally, we showcase the effectiveness of our framework with two case-studies considering the transportation sub-networks in Eastern Massachusetts and New York City.  ...  Specifically, we approximate the latency function (Eq. (3)) using a piecewise-affine function as shown in Fig. 2 .  ... 
arXiv:2003.04335v1 fatcat:v6aamqp7cfh4zgzewfiouardhe
Citation

Salomón Wollenstein-Betech, Arian Houshmand, Mauro Salazar, Marco Pavone, Christos G. Cassandras, Ioannis Ch. Paschalidis. "Congestion-aware Routing and Rebalancing of Autonomous Mobility-on-Demand Systems in Mixed Traffic." arXiv (2020)

Piecewise Latent Variables for Neural Variational Text Processing [article]

Iulian V. Serban, Alexander G. Ororbia II, Joelle Pineau, Aaron Courville
2017 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.7 MB)
https://web.archive.org/web/20200911133654/https://arxiv.org/pdf/1612.00377v4.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2017 pre-print
arXiv:1612.00377v3 fatcat:vfgtqhykkfa2xdi7xpvtlrahei
2016 pre-print
arXiv:1612.00377v2 fatcat:5u52h4orpjbatexwvbjipxkzge
2016 pre-print
arXiv:1612.00377v1 fatcat:5rx6r5d3cjfx5gimt35vjcbngm
To overcome this restriction, we propose the simple, but highly flexible, piecewise constant distribution.  ...  The hope is that such models will learn to represent rich, multi-modal latent factors in real-world data, such as natural language text.  ...  how the piecewise variables capture different aspects of the document data.  ... 
arXiv:1612.00377v4 fatcat:beplaorujzemjcluxiq2nr7gr4
Multiple Versions
Citation

Iulian V. Serban, Alexander G. Ororbia II, Joelle Pineau, Aaron Courville. "Piecewise Latent Variables for Neural Variational Text Processing." arXiv (2017)

Congestion-aware Routing and Rebalancing of Autonomous Mobility-on-Demand Systems in Mixed Traffic

Salomon Wollenstein-Betech, Arian Houshmand, Mauro Salazar, Marco Pavone, Christos G. Cassandras, Ioannis Ch. Paschalidis
2020 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.1 MB)
https://web.archive.org/web/20220518065750/https://pure.tue.nl/ws/files/148820171/2003.04335v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for  ...  accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with  ...  Specifically, we approximate the latency function (Eq. ( 3 )) using a piecewise-affine function as shown in Fig. 2 .  ... 
doi:10.1109/itsc45102.2020.9294258 fatcat:3romkacgb5hmbm2nwwmev52ite
Citation

Salomon Wollenstein-Betech, Arian Houshmand, Mauro Salazar, Marco Pavone, Christos G. Cassandras, Ioannis Ch. Paschalidis. "Congestion-aware Routing and Rebalancing of Autonomous Mobility-on-Demand Systems in Mixed Traffic." 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC) (2020)

A study of publication trajectories of the Brazilian Computer Science community

MARCELO K. ALBERTINI, ANDRÉ R. BACKES, ADRIANO L. DE SÁ
2019 Anais da Academia Brasileira de Ciências  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.7 MB)
https://web.archive.org/web/20200217004802/http://www.scielo.br/pdf/aabc/v91n3/0001-3765-aabc-91-03-e20180559.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Way et al. (2017) have studied this pattern for faculty careers in Computer Science in North America using a piecewise linear model.  ...  First, we have evaluated how the median publication count of researchers is related to institution prestige and public vs. private administration.  ...  The piecewise-linear function had the smallest BIC for 58 (20.1%) trajectories.  ... 
doi:10.1590/0001-3765201920180559 fatcat:lo37kpudznbftjnzht6ejkwrge
DOAJ SciELO
Citation

MARCELO K. ALBERTINI, ANDRÉ R. BACKES, ADRIANO L. DE SÁ. "A study of publication trajectories of the Brazilian Computer Science community." Anais da Academia Brasileira de Ciências 91.3 (2019)

Nonlinear self-scheduling of a single unit small hydro plant in the day-ahead electricity market

Juan I. Pérez, José R. Wilhelmi
2007 The Renewable Energies and Power Quality Journal (RE&PQJ)  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (635.7 kB)
https://web.archive.org/web/20180605001722/http://www.icrepq.com/icrepq07/254-perez.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL. The file type is application/pdf.

The scheduling problem is solved with commercially available optimization software.  ...  The proposed model considers hydro power generation as a function of the water discharge and the net head and takes into account the unit start-ups and shut-downs.  ...  This target level can be modeled either with an equality constraint [13] or with a penalty function [7] .  ... 
doi:10.24084/repqj05.254 fatcat:lk4bixkykbeg3jn2nl6qni52ua
Citation

Juan I. Pérez, José R. Wilhelmi. "Nonlinear self-scheduling of a single unit small hydro plant in the day-ahead electricity market." The Renewable Energies and Power Quality Journal (RE&PQJ) 1.05 (2007) 216-222

HVDC Loss Factors in the Nordic Power Market [article]

Andrea Tosatto, Spyros Chatzivasileiadis
2020 arXiv   pre-print

Preserved Fulltext

Web Archive Capture PDF (3.1 MB)
https://web.archive.org/web/20200609001010/https://arxiv.org/pdf/1910.05607v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

Other Versions

2019 pre-print
arXiv:1910.05607v1 fatcat:nqpgfjmoezcpbbqi6bdzkjlwdy
In this regard, we propose piecewise-linear loss factors: a simple to implement but highly effective solution.  ...  For the simulations in Section IV, quadratic loss functions are approximated with linear and piecewise-linear functions.  ...  Finally, the piecewise-linear approximations are obtained with the least squares regression method.  ... 
arXiv:1910.05607v2 fatcat:fouinp4lnbhlbhyzttam3gayju
Multiple Versions
Citation

Andrea Tosatto, Spyros Chatzivasileiadis. "HVDC Loss Factors in the Nordic Power Market." arXiv (2020)

« Previous Showing results 1 — 15 out of 9,081 results