10,887 Hits in 1.4 sec

Differentially Private Quantiles [article]

Jennifer Gillenwater, Matthew Joseph, Alex Kulesza
2021 arXiv   pre-print
If that data is sensitive, it may be necessary to compute quantiles in a way that is differentially private, providing theoretical guarantees that the result does not reveal private information.  ...  However, when multiple quantiles are needed, existing differentially private algorithms fare poorly: they either compute quantiles individually, splitting the privacy budget, or summarize the entire distribution  ...  Acknowledgements We thank Thomas Steinke for discussions of concentrated differential privacy; Andrés Muñoz Medina for comments on an early draft of this paper; Uri Stemmer for discussion of the threshold  ... 
arXiv:2102.08244v3 fatcat:sa5ozkry7bbajc5y4knft4ubiy

Differentially Private Approximate Quantiles [article]

Haim Kaplan, Shachar Schnapp, Uri Stemmer
2021 arXiv   pre-print
In this work we study the problem of differentially private (DP) quantiles, in which given dataset X and quantiles q_1, ..., q_m ∈ [0,1], we want to output m quantile estimations which are as close as  ...  possible to the true quantiles and preserve DP.  ...  ApproximateQuantiles Algorithm This section demonstrates our differentially private quantiles algorithm, ApproximateQuantiles.  ... 
arXiv:2110.05429v1 fatcat:jippm2rd4fgpxhe2phpqdqlckq

Bounded Space Differentially Private Quantiles [article]

Daniel Alabi, Omri Ben-Eliezer, Anamay Chaturvedi
2022 arXiv   pre-print
In this work, we devise a differentially private algorithm for the quantile estimation problem, with strongly sublinear space complexity, in the one-shot and continual observation settings.  ...  Estimating the quantiles of a large dataset is a fundamental problem in both the streaming algorithms literature and the differential privacy literature.  ...  In our case, the general goal is to efficiently compute 𝛼-approximate quantiles in a (pure or approximate) differentially private manner.  ... 
arXiv:2201.03380v1 fatcat:jzmpfl347vepthxkahldmibiu4

Quantile Multi-Armed Bandits: Optimal Best-Arm Identification and a Differentially Private Scheme [article]

Kontantinos E. Nikolakakis, Dionysios S. Kalogerias, Or Sheffet, Anand D. Sarwate
2021 arXiv   pre-print
Second, motivated by applications where the rewards are private, we provide a differentially private successive elimination algorithm whose sample complexity is finite even for distributions with infinite  ...  We study the best-arm identification problem in multi-armed bandits with stochastic, potentially private rewards, when the goal is to identify the arm with the highest quantile at a fixed, prescribed level  ...  Differentially Private Successive Elimination for the Highest Quantile Arm The differentially private algorithm is shown in Algorithm 2.  ... 
arXiv:2006.06792v3 fatcat:ufpp3p5aunfgzjvxc6seru4f2y

Public-private sector wage differentials in Germany: Evidence from quantile regression

Blaise Melly
2005 Empirical Economics  
This paper measures the differences in earnings distributions between public sector and private sector employees in Germany in 2000.  ...  The use of quantile regressions indicates that the public sector wage premium is highest at the lower end of the wage distribution and then decreases monotonically as we move up the wage distribution.  ...  90th *** Quantile  ... 
doi:10.1007/s00181-005-0251-y fatcat:rwta37utwvbujlo34637myfs2a

Public–private sector wage differentials in Canada: evidence from quantile regressions

Richard E Mueller
1998 Economics Letters  
Quantile regressions are used to estimate the size of the public sector wage premium in Canada.  ...  Gunderson (1979) used 1971 data to measure the public-private sector earnings differential.  ...  Theoretical considerations and previous research There are a number of reasons that earnings differentials between the private and public sector exist.  ... 
doi:10.1016/s0165-1765(98)00110-4 fatcat:hyufve4boraejgb5o64lkh2twq

Public-Private Wage Differentials in Euro Area Countries: Evidence from Quantile Decomposition Analysis

Domenico Depalo, Raffaela Giordano, Evangelia Papapetrou
2013 Social Science Research Network  
We evaluate the public-private wage differential in ten euro area countries for men in the period 2004-2007.  ...  Using the most recent methodologies on a Mincerian equation, we assess how much of the pay differential between public and private sector workers depends on differences in endowments and how much on differences  ...  However, few studies have applied quantile decomposition methods to investigate the source of the public-private differential along the wage distribution.  ... 
doi:10.2139/ssrn.2259649 fatcat:btrlvnxjzfgr5bagegqm324fou

A Distributional Analysis of Public-Private Wage Differential in India

Mehtabul Azam, Nishith Prakash
2015 Labour  
A Distributional Analysis of the Public-Private Wage Differential in India * We investigate the public-private wage differential in India using nationally representative micro data.  ...  A quantile regression based decomposition analysis reveals that the differences in observed characteristics (covariate effect) account for only a small part of the wage differential at lower quantiles,  ...  , however, the price differential declines (covariate effect increases) as we move towards higher quantiles.  ... 
doi:10.1111/labr.12068 fatcat:wrhbgdjdkjbfxpx2bpjbmtevae

Differentially Private Linear Sketches: Efficient Implementations and Applications [article]

Fuheng Zhao, Dan Qiao, Rachel Redberg, Divyakant Agrawal, Amr El Abbadi, Yu-Xiang Wang
2022 arXiv   pre-print
From the differentially private linear sketches, we showcase that the state-of-the-art quantile sketch in the turnstile model can also be private and maintain high performance.  ...  Experiments further demonstrate that our proposed differentially private sketches are quantitatively and qualitatively similar to noise-free sketches with high utilization on synthetic and real datasets  ...  In addition, we propose the first differentially private quantile sketch in the turnstile model by leveraging the differentially private linear sketch.  ... 
arXiv:2205.09873v1 fatcat:pggboiiupfgandhzan4ibxkkbu

The Public and Private Sector Pay Gap in Pakistan: A Quantile Regression Analysis

Asma Hyder, Barry Reilly
2005 Pakistan Development Review  
This paper examines the magnitude of public/private wage differentials in Pakistan using data drawn from the 2001-02 Pakistan Labour Force Survey.  ...  The quantile regression estimates suggest that the mark-up was found to decline monotonically with movement up the conditional wage distribution.  ...  For example, the quantile regression of log public (private) sector wages on a constant term yields the relevant log wage at the particular quantile for the public (private) sector. 2.  ... 
doi:10.30541/v44i3pp.271-306 fatcat:m2hcytdce5clzo2obamcnmsbbu

The structure of wages during the economic transition in Romania

Emmanuel Skoufias
2003 Economic Systems  
Using quantile regression, the rate of return to education and experience at different quantiles of the wage distribution is estimated.  ...  In private firms, only college education is correlated with significantly higher wages.  ...  four quantile-quantile plots of male and female log wages in public and private firms.  ... 
doi:10.1016/j.ecosys.2003.10.001 fatcat:vaol7ftdszagvakn4ghndrihsm

DP-XGBoost: Private Machine Learning at Scale [article]

Nicolas Grislain, Joan Gonzalvez
2021 arXiv   pre-print
There has been many works on practical systems to compute statistical queries with Differential Privacy (DP).  ...  To make this step differentially private, one could try to design a DP (weighted) quantile sketching algorithm.  ...  Points are then passed to the sketch construction algorithm of XGBoost with differentially private points and weights, making the quantile sketch a post-processing step.  ... 
arXiv:2110.12770v1 fatcat:g36xkh26mjantd63ocw6fqdvfa

Private Prediction Sets [article]

Anastasios N. Angelopoulos and Stephen Bates and Tijana Zrnic and Michael I. Jordan
2021 arXiv   pre-print
To remedy this key problem, we develop a method that takes any pre-trained predictive model and outputs differentially private prediction sets.  ...  Our method follows the general approach of split conformal prediction; we use holdout data to calibrate the size of the prediction sets but preserve privacy by using a privatized quantile subroutine.  ...  private quantile computation.  ... 
arXiv:2102.06202v2 fatcat:nle5wnoxnjfc3nufkmhtgzju24

Investigating the gender wage gap in Vietnam by quantile regression: Sticky floor or glass ceiling

Tran Thi Tuan Anh
2018 Journal of Economic Development  
The quantile regression will be performed at some typical quantiles: 0.1 -0.25 -0.5 -0.75 -0.9. The coefficient of the gender dummy variable will show the gender wage differentials at each quantile.  ...  Hung and Reilly (2007) employed quantile regression to analyze the gender wage differential with the data for the period from 1992 to 2002.  ... 
doi:10.24311/jed/2018.25.s01.1 fatcat:e64xzj5jy5a6hkeqpgnny5wpmm


Claudio Lucifora, Dominique Meurs
2006 The Review of Income and Wealth  
We show that the public-private (hourly) wage differential is sensitive to the choice of quantile and that the pattern of premia varies with both gender and skill.  ...  While traditional methods focus on parametric methods to estimate the public sector pay gap, in this paper, we use both non-parametric (kernel) and quantile regression methods to analyse the distribution  ...  We show that the public-private (hourly) wage differential is sensitive to the choice of quantile and that the pattern of premia varies with both gender and skill.  ... 
doi:10.1111/j.1475-4991.2006.00175.x fatcat:co62fti7i5e5tnma5fi36tolsm
« Previous Showing results 1 — 15 out of 10,887 results