Fetching the paper…
Reading the bibliography…
Differentially private SGD (DP-SGD) is one of the most popular methods for solving differentially private empirical risk minimization (ERM).
Gradient methods for the minimisation of functionals
B. Polyak · 1963
Earlier work this paper cites.
Matrix Computations
G. H. Golub and C. F. Van Loan · 1996
Earlier work this paper cites.
Gradient-based learning applied to document recognition
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner · 1998
Earlier work this paper cites.
Random projection in dimensionality reduction: applications to image and text data
E. Bingham and H. Mannila · 2001
Earlier work this paper cites.
Private query release assisted by public data
R. Bassily, A. Cheu, S. Moran, A. Nikolov, J. Ullman, and Z. S. Wu · 2004
Earlier work this paper cites.
Spectral methods for data analysis
F. McSherry · 2004
Earlier work this paper cites.
Calibrating noise to sensitivity in private data analysis
C. Dwork, F. McSherry, K. Nissim, and A. Smith · 2006
Earlier work this paper cites.
Fast dimension independent private adagrad on publicly estimated subspaces
P. Kairouz, M. Ribero, K. Rush, and A. Thakurta · 2008
Earlier work this paper cites.
What can we learn privately?
S. P. Kasiviswanathan, H. K. Lee, K. Nissim, S. Raskhodnikova, and A. Smith · 2008
Earlier work this paper cites.
Boosting and differential privacy
C. Dwork, G. N. Rothblum, and S. P. Vadhan · 2010
Earlier work this paper cites.
The johnson-lindenstrauss transform itself preserves differential privacy
J. Blocki, A. Blum, A. Datta, and O. Sheffet · 2012
Earlier work this paper cites.
Matrix analysis
R. A. Horn and C. R. Johnson · 2012
Earlier work this paper cites.
Stochastic first- and zeroth-order methods for nonconvex stochastic programming
S. Ghadimi and G. Lan · 2013
Earlier work this paper cites.
Stochastic gradient descent with differentially private updates
S. Song, K. Chaudhuri, and A. D. Sarwate · 2013
Earlier work this paper cites.
Private empirical risk minimization: Efficient algorithms and tight error bounds
R. Bassily, A. Smith, and A. Thakurta · 2014
Cited alongside, same era.
Analyze gauss: optimal bounds for privacy-preserving principal component analysis
C. Dwork, K. Talwar, A. Thakurta, and L. Zhang · 2014
Cited alongside, same era.
(near) dimension independent risk bounds for differentially private learning
P. Jain and A. G. Thakurta · 2014
Cited alongside, same era.
Introductory Lectures on Convex Optimization: A Basic Course
Y. Nesterov · 2014
Cited alongside, same era.
Upper and Lower Bounds for Stochastic Processes
M. Talagrand · 2014
Cited alongside, same era.
Preserving statistical validity in adaptive data analysis
C. Dwork, V. Feldman, M. Hardt, T. Pitassi, O. Reingold, and A. L. Roth · 2015
Cited alongside, same era.
Gradient descent happens in a tiny subspace
G. Gur-Ari, D. A. Roberts, and E. Dyer · 2018
Later among the works it cites.
High-Dimensional Probability: An Introduction with Applications in Data Science
R. Vershynin · 2018
Later among the works it cites.
Deep learning with gaussian differential privacy
Z. Bu, J. Dong, Q. Long, and W. J. Su · 2019
Later among the works it cites.
Measurements of three-level hierarchical structure in the outliers in the spectrum of deepnet hessians
V. Papyan · 2019
Later among the works it cites.
High-dimensional statistics: A non-asymptotic viewpoint , volume 48
M. J. Wainwright · 2019
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Unified view of matrix completion under general structural constraints
S. Gunasekar, A. Banerjee, and J. Ghosh · 2015
Cited alongside, same era.
Deep learning with differential privacy
M. Abadi, A. Chu, I. Goodfellow, B. McMahan, I. Mironov, K. Talwar, and L. Zhang · 2016
Cited alongside, same era.
Algorithmic stability for adaptive data analysis
R. Bassily, K. Nissim, A. D. Smith, T. Steinke, U. Stemmer, and J. Ullman · 2016
Cited alongside, same era.
BLENDER: enabling local search with a hybrid differential privacy model
B. Avent, A. Korolova, D. Zeber, T. Hovden, and B. Livshits · 2017
Cited alongside, same era.
Semi-supervised knowledge transfer for deep learning from private training data
N. Papernot, M. Abadi, Ú. Erlingsson, I. J. Goodfellow, and K. Talwar · 2017
Cited alongside, same era.
Differentially private empirical risk minimization revisited: Faster and more general
D. Wang, M. Ye, and J. Xu · 2017
Cited alongside, same era.
Differentially private empirical risk minimization with smooth non-convex loss functions: A non-stationary view
D. Wang and J. Xu · 2019
Later among the works it cites.
A new analysis of differential privacy’s generalization guarantees
C. Jung, K. Ligett, S. Neel, A. Roth, S. Sharifi-Malvajerdi, and M. Shenfeld · 2020
Closest in time.
Hessian based analysis of SGD for deep nets: Dynamics and generalization
X. Li, Q. Gu, Y. Zhou, T. Chen, and A. Banerjee · 2020
Closest in time.
Tempered sigmoid activations for deep learning with differential privacy, 2020
N. Papernot, A. Thakurta, S. Song, S. Chien, and Úlfar Erlingsson · 2020
Closest in time.
Characterizing private clipped gradient descent on convex generalized linear problems
S. Song, O. Thakkar, and A. Thakurta · 2020
Closest in time.
Experiments with rich regime training for deep learning
X. Li and A. Banerjee · 2021
Closest in time.
Differentially private learning needs better features (or much more data)
F. Tramer and D. Boneh · 2021
Closest in time.
Do not let privacy overbill utility: Gradient embedding perturbation for private learning
D. Yu, H. Zhang, W. Chen, and T.-Y. Liu · 2021
Closest in time.
Wide network learning with differential privacy
H. Zhang, I. Mironov, and M. Hejazinia · 2021
Closest in time.