Fetching the paper…
Reading the bibliography…
Prior work on differential privacy analysis of randomized SGD algorithms relies on composition theorems, where the implicit (unrealistic) assumption is that the internal state of the iterative algorithm is revealed to the adversary.
On measures of entropy and information
Alfréd Rényi · 1961
Earlier work this paper cites.
Multinomial logistic regression algorithm
Dankmar Böhning · 1992
Earlier work this paper cites.
Relative information of type s, csiszár’s f-divergence, and information inequalities
Inder Jeet Taneja and Pranesh Kumar · 2004
Earlier work this paper cites.
When random sampling preserves privacy
Kamalika Chaudhuri and Nina Mishra · 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.
Interpretation and generalization of score matching
Siwei Lyu · 2009
Earlier work this paper cites.
On sampling, anonymization, and differential privacy or, k-anonymization meets differential privacy
Ninghui Li, Wahbeh Qardaji, and Dong Su · 2012
Earlier work this paper cites.
Logarithmic sobolev inequalities for mollified compactly supported measures
David Zimmermann · 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, Aaron Roth, et al · 2014
Earlier work this paper cites.
Deep learning with differential privacy
Martin Abadi, Andy Chu, Ian Goodfellow, H Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang · 2016
Earlier work this paper cites.
Functional inequalities for convolution probability measures
Feng-Yu Wang and Jian Wang · 2016
Earlier work this paper cites.
Elementary proof of logarithmic sobolev inequalities for gaussian convolutions on ℝ \mathbb{R}
David Zimmermann · 2016
Earlier work this paper cites.
Rényi differential privacy
Ilya Mironov · 2017
Earlier work this paper cites.
Functional inequalities for gaussian convolutions of compactly supported measures: Explicit bounds and dimension dependence
Jean-Baptiste Bardet, Nathaël Gozlan, Florent Malrieu, and Pierre-André Zitt · 2018
Earlier work this paper cites.
Privacy amplification by iteration
Vitaly Feldman, Ilya Mironov, Kunal Talwar, and Abhradeep Thakurta · 2018
Cited alongside, same era.
Group normalization
Yuxin Wu and Kaiming He · 2018
Cited alongside, same era.
Privacy amplification by mixing and diffusion mechanisms
Borja Balle, Gilles Barthe, Marco Gaboardi, and Joseph Geumlek · 2019
Cited alongside, same era.
Private stochastic convex optimization with optimal rates
Raef Bassily, Vitaly Feldman, Kunal Talwar, and Abhradeep Guha Thakurta · 2019
Cited alongside, same era.
R \ \backslash ’enyi differential privacy of the sampled gaussian mechanism
Ilya Mironov, Kunal Talwar, and Li Zhang · 2019
Cited alongside, same era.
Private adaptive gradient methods for convex optimization
Hilal Asi, John Duchi, Alireza Fallah, Omid Javidbakht, and Kunal Talwar · 2021
Later among the works it cites.
On the convergence and calibration of deep learning with differential privacy
Zhiqi Bu, Hua Wang, and Qi Long · 2021
Later among the works it cites.
Extracting training data from large language models
Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, et al · 2021
Later among the works it cites.
Dimension-free log-sobolev inequalities for mixture distributions
Hong-Bin Chen, Sinho Chewi, and Jonathan Niles-Weed · 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.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Venkatadheeraj Pichapati, Ananda Theertha Suresh, Felix X Yu, Sashank J Reddi, and Sanjiv Kumar · 2019
Cited alongside, same era.
Rapid convergence of the unadjusted langevin algorithm: Isoperimetry suffices
Santosh Vempala and Andre Wibisono · 2019
Cited alongside, same era.
Subsampled rényi differential privacy and analytical moments accountant
Yu-Xiang Wang, Borja Balle, and Shiva Prasad Kasiviswanathan · 2019
Cited alongside, same era.
Why gradient clipping accelerates training: A theoretical justification for adaptivity
Jingzhao Zhang, Tianxing He, Suvrit Sra, and Ali Jadbabaie · 2019
Cited alongside, same era.
Understanding gradient clipping in private sgd: A geometric perspective
Xiangyi Chen, Steven Z Wu, and Mingyi Hong · 2020
Cited alongside, same era.
Private stochastic convex optimization: optimal rates in linear time
Vitaly Feldman, Tomer Koren, and Kunal Talwar · 2020
Cited alongside, same era.
Computing tight differential privacy guarantees using fft
Antti Koskela, Joonas Jälkö, and Antti Honkela · 2020
Cited alongside, same era.
Hiding among the clones: A simple and nearly optimal analysis of privacy amplification by shuffling
Vitaly Feldman, Audra McMillan, and Kunal Talwar · 2021
Later among the works it cites.
Stochastic training is not necessary for generalization
Jonas Geiping, Micah Goldblum, Phil Pope, Michael Moeller, and Tom Goldstein · 2021
Later among the works it cites.
Tensorflow privacy, 2021
Google et al · 2021
Later among the works it cites.
Practical and private (deep) learning without sampling or shuffling
Peter Kairouz, Brendan McMahan, Shuang Song, Om Thakkar, Abhradeep Thakurta, and Zheng Xu · 2021
Later among the works it cites.
Enhanced membership inference attacks against machine learning models
Jiayuan Ye, Aadyaa Maddi, Sasi Kumar Murakonda, Vincent Bindschaedler, and Reza Shokri · 2021
Later among the works it cites.
Opacus: User-friendly differential privacy library in pytorch
Ashkan Yousefpour, Igor Shilov, Alexandre Sablayrolles, Davide Testuggine, Karthik Prasad, Mani Malek, John Nguyen, Sayan Ghosh, Akash Bharadwaj, Jessica Zhao, et al · 2021
Later among the works it cites.
Privacy of noisy stochastic gradient descent: More iterations without more privacy loss
Jason M Altschuler and Kunal Talwar · 2022
Closest in time.
Langevin diffusion: An almost universal algorithm for private euclidean (convex) optimization
Arun Ganesh, Abhradeep Thakurta, and Jalaj Upadhyay · 2022
Closest in time.
Differential privacy guarantees for stochastic gradient langevin dynamics
Théo Ryffel, Francis Bach, and David Pointcheval · 2022
Closest in time.