Fetching the paper…
Reading the bibliography…
In this paper we provide an algorithmic framework based on Langevin diffusion (LD) and its corresponding discretizations that allow us to simultaneously obtain: i) An algorithm for sampling from the exponential mechanism, whose privacy analysis does not depend on convexity and which can be stopped at anytime without compromising privacy, and ii) tight uniform stability guarantees for the exponential mechanism.
Stochastic differential equations with reflecting boundary condition in convex regions
Hiroshi Tanaka · 1979
Earlier work this paper cites.
Diffusions hypercontractives
Dominique Bakry and Michel Émery · 1985
Earlier work this paper cites.
Logarithmic sobolev inequalities and stochastic ising models
Richard Holley and Daniel W. Stroock · 1987
Earlier work this paper cites.
Concentration of measure and logarithmic sobolev inequalities
Michel Ledoux · 1999
Earlier work this paper cites.
Statistical modeling: The two cultures (with comments and a rejoinder by the author)
Leo Breiman · 2001
Earlier work this paper cites.
Logarithmic sobolev inequalities for unbounded spin systems revisited
Michel Ledoux · 2001
Earlier work this paper cites.
Stability and generalization
Olivier Bousquet and André Elisseeff · 2002
Earlier work this paper cites.
A large-deviation inequality for vector-valued martingales
Thomas P. Hayes · 2003
Earlier work this paper cites.
Local rademacher complexities
Peter L Bartlett, Olivier Bousquet, and Shahar Mendelson · 2005
Earlier work this paper cites.
Our data, ourselves: Privacy via distributed noise generation
Cynthia Dwork, Krishnaram Kenthapadi, Frank McSherry, Ilya Mironov, and Moni Naor · 2006
Earlier work this paper cites.
Calibrating noise to sensitivity in private data analysis
Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith · 2006
Earlier work this paper cites.
Mechanism design via differential privacy
Frank McSherry and Kunal Talwar · 2007
Earlier work this paper cites.
On the geometry of differential privacy
Moritz Hardt and Kunal Talwar · 2010
Earlier work this paper cites.
Stability selection
Nicolai Meinshausen and Peter Bühlmann · 2010
Earlier work this paper cites.
Smoothness, low noise and fast rates
Nathan Srebro, Karthik Sridharan, and Ambuj Tewari · 2010
Earlier work this paper cites.
Differentially private empirical risk minimization
Kamalika Chaudhuri, Claire Monteleoni, and Anand D Sarwate · 2011
Earlier work this paper cites.
Bayesian learning via stochastic gradient langevin dynamics
Max Welling and Yee W Teh · 2011
Earlier work this paper cites.
Private convex empirical risk minimization and high-dimensional regression
Daniel Kifer, Adam Smith, and Abhradeep Thakurta · 2012
Earlier work this paper cites.
Stochastic gradient descent with differentially private updates
Shuang Song, Kamalika Chaudhuri, and Anand D Sarwate · 2013
Earlier work this paper cites.
Machine learning with operational costs
Theja Tulabandhula and Cynthia Rudin · 2013
Earlier work this paper cites.
Private empirical risk minimization: Efficient algorithms and tight error bounds
Raef Bassily, Adam Smith, and Abhradeep Thakurta · 2014
Earlier work this paper cites.
The algorithmic foundations of differential privacy
Cynthia Dwork and Aaron Roth · 2014
Earlier work this paper cites.
On combining machine learning with decision making
Theja Tulabandhula and Cynthia Rudin · 2014
Earlier work this paper cites.
Robust optimization using machine learning for uncertainty sets
Theja Tulabandhula and Cynthia Rudin · 2014
Earlier work this paper cites.
Rényi divergence and Kullback-Leibler divergence
T. van Erven and P. Harremos · 2014
Earlier work this paper cites.
Between pure and approximate differential privacy
Thomas Steinke and Jonathan Ullman · 2015
Earlier work this paper cites.
Deep learning with differential privacy
Martín Abadi, Andy Chu, Ian J. Goodfellow, H. Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang · 2016
Earlier work this paper cites.
Train faster, generalize better: Stability of stochastic gradient descent
Moritz Hardt, Benjamin Recht, and Yoram Singer · 2016
Earlier work this paper cites.
Riemannian metrics on convex sets with applications to poincaré and log-sobolev inequalities
Alexander Kolesnikov and Emanuel Milman · 2016
Cited alongside, same era.
On large-batch training for deep learning: Generalization gap and sharp minima
Nitish Shirish Keskar, Dheevatsa Mudigere, Jorge Nocedal, Mikhail Smelyanskiy, and Ping Tak Peter Tang · 2016
Cited alongside, same era.
Prediction uncertainty and optimal experimental design for learning dynamical systems
Benjamin Letham, Portia A Letham, Cynthia Rudin, and Edward P Browne · 2016
Cited alongside, same era.
Theoretical guarantees for approximate sampling from smooth and log-concave densities
Arnak S. Dalalyan · 2017
Cited alongside, same era.
Nonasymptotic convergence analysis for the unadjusted langevin algorithm
Alain Durmus and Eric Moulines · 2017
Cited alongside, same era.
Stability of stochastic gradient descent on nonsmooth convex losses
Raef Bassily, Vitaly Feldman, Cristóbal Guzmán, and Kunal Talwar · 2020
Later among the works it cites.
On sampling from a log-concave density using kinetic langevin diffusions
Arnak S Dalalyan and Lionel Riou-Durand · 2020
Later among the works it cites.
Private stochastic convex optimization: Optimal rates in linear time
Vitaly Feldman, Tomer Koren, and Kunal Talwar · 2020
Later among the works it cites.
Faster differentially private samplers via rényi divergence analysis of discretized langevin mcmc
Arun Ganesh and Kunal Talwar · 2020
Later among the works it cites.
Algorithmic bias: should students pay the price?
Helen Smith · 2020
Later among the works it cites.
Characterizing private clipped gradient descent on convex generalized linear problems
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Rényi differential privacy
Ilya Mironov · 2017
Cited alongside, same era.
Identifying a minimal class of models for high-dimensional data
Daniel Nevo and Ya’acov Ritov · 2017
Cited alongside, same era.
Non-convex learning via stochastic gradient langevin dynamics: a nonasymptotic analysis
Maxim Raginsky, Alexander Rakhlin, and Matus Telgarsky · 2017
Cited alongside, same era.
Is interaction necessary for distributed private learning?
Adam Smith, Abhradeep Thakurta, and Jalaj Upadhyay · 2017
Cited alongside, same era.
Tight lower bounds for differentially private selection
Thomas Steinke and Jonathan Ullman · 2017
Cited alongside, same era.
Bolt-on differential privacy for scalable stochastic gradient descent-based analytics
Xi Wu, Fengan Li, Arun Kumar, Kamalika Chaudhuri, Somesh Jha, and Jeffrey F. Naughton · 2017
Cited alongside, same era.
Sampling from a log-concave distribution with projected langevin monte carlo
Sébastien Bubeck, Ronen Eldan, and Joseph Lehec · 2018
Cited alongside, same era.
Shuang Song, Om Thakkar, and Abhradeep Thakurta · 2020
Later among the works it cites.
Adapting to function difficulty and growth conditions in private optimization
Hilal Asi, Daniel Asher Nathan Levy, and John Duchi · 2021
Later among the works it cites.
Analysis of langevin monte carlo from poincar \ \backslash ’e to log-sobolev
Sinho Chewi, Murat A Erdogdu, Mufan Bill Li, Ruoqi Shen, and Matthew Zhang · 2021
Later among the works it cites.
Characterizing fairness over the set of good models under selective labels
Amanda Coston, Ashesh Rambachan, and Alexandra Chouldechova · 2021
Later among the works it cites.
A theory of statistical inference for ensuring the robustness of scientific results
Beau Coker, Cynthia Rudin, and Gary King · 2021
Later among the works it cites.
Differential privacy dynamics of langevin diffusion and noisy gradient descent
Rishav Chourasia, Jiayuan Ye, and Reza Shokri · 2021
Later among the works it cites.
Convergence of langevin monte carlo in chi-squared and renyi divergence, 2021
Murat A. Erdogdu, Rasa Hosseinzadeh, and Matthew S. Zhang · 2021
Later among the works it cites.
Private non-smooth erm and sco in subquadratic steps
Janardhan Kulkarni, Yin Tat Lee, and Daogao Liu · 2021
Later among the works it cites.
Sampling from log-concave distributions with infinity-distance guarantees
Oren Mangoubi and Nisheeth K Vishnoi · 2021
Later among the works it cites.
Concentration of the langevin algorithm’s stationary distribution
Jason M Altschuler and Kunal Talwar · 2022
Closest in time.
Privacy of noisy stochastic gradient descent: More iterations without more privacy loss
Jason M Altschuler and Kunal Talwar · 2022
Closest in time.
Jason M Altschuler and Kunal Talwar · 2022
Closest in time.
The algorithmic leviathan: Arbitrariness, fairness, and opportunity in algorithmic decision-making systems
Kathleen Creel and Deborah Hellman · 2022
Closest in time.
Private convex optimization via exponential mechanism
Sivakanth Gopi, Yin Tat Lee, and Daogao Liu · 2022
Closest in time.
Rashomon capacity: Measuring predictive multiplicity in probabilistic classification
Hsiang Hsu and Flavio P Calmon · 2022
Closest in time.
Re-analyze gauss: Bounds for private matrix approximation via dyson brownian motion
Oren Mangoubi and Nisheeth K Vishnoi · 2022
Closest in time.
Differential privacy guarantees for stochastic gradient langevin dynamics
Théo Ryffel, Francis Bach, and David Pointcheval · 2022
Closest in time.
Interpretable machine learning: Fundamental principles and 10 grand challenges
Cynthia Rudin, Chaofan Chen, Zhi Chen, Haiyang Huang, Lesia Semenova, and Chudi Zhong · 2022
Closest in time.
Recycling scraps: Improving private learning by leveraging intermediate checkpoints
Virat Shejwalkar, Arun Ganesh, Rajiv Mathews, Om Thakkar, and Abhradeep Thakurta · 2022
Closest in time.
On the existence of simpler machine learning models
Lesia Semenova, Cynthia Rudin, and Ronald Parr · 2022
Closest in time.
Robustness implies privacy in statistical estimation
Samuel B Hopkins, Gautam Kamath, Mahbod Majid, and Shyam Narayanan · 2023
Closest in time.
Training private models that know what they don’t know
Stephan Rabanser, Anvith Thudi, Abhradeep Thakurta, Krishnamurthy Dvijotham, and Nicolas Papernot · 2023
Closest in time.