Fetching the paper…
Reading the bibliography…
Differentially Private Stochastic Gradient Descent (DP-SGD) limits the amount of private information deep learning models can memorize during training.
G. W. Brier, “Verification of Forecasts Expressed in Terms of Probability,”
1950
Earlier work this paper cites.
B. Polyak and A. B. Juditsky, “Acceleration of Stochastic Approximation by Averaging,”
1992
Earlier work this paper cites.
G. Chirikjian, A. Kyatkin, and A. Buckingham, “Engineering Applications of Noncommutative Harmonic Analysis: With Emphasis on Rotation and Motion Groups,”
2001
Earlier work this paper cites.
D. L. Donoho and M. Elad, “Maximal Sparsity Representation via l1 Minimization,”
2003
Earlier work this paper cites.
C. Dwork and A. Roth, “The Algorithmic Foundations of Differential Privacy,”
2014
Earlier work this paper cites.
M. Abadi, A. Chu, I. Goodfellow, H. B. McMahan, I. Mironov, K. Talwar, and L. Zhang, “Deep Learning with Differential Privacy,” in
2016
Earlier work this paper cites.
T. Cohen and M. Welling, “Group Equivariant Convolutional Networks,” in
2016
Earlier work this paper cites.
——, “Steerable CNNs,” in
2017
Earlier work this paper cites.
I. Mironov, “Rényi Differential Privacy,”
2017
Earlier work this paper cites.
2017
Earlier work this paper cites.
T. Cohen, M. Geiger, J. Köhler, and M. Welling, “Spherical CNNs,”
2018
Earlier work this paper cites.
M. Weiler, F. A. Hamprecht, and M. Storath, “Learning Steerable Filters for Rotation Equivariant CNNs,”
2018
Earlier work this paper cites.
A. F. Agarap, “Deep Learning using Rectified Linear Units (ReLU),”
2018
Earlier work this paper cites.
K. He, R. Girshick, and P. Dollar, “Rethinking ImageNet Pre-Training,” in
2019
Cited alongside, same era.
I. Mironov, K. Talwar, and L. Zhang, “Rényi Differential Privacy of the Sampled Gaussian Mechanism,”
2019
Cited alongside, same era.
M. Weiler and G. Cesa, “General E(2)-Equivariant Steerable CNNs,”
2019
Cited alongside, same era.
S. Qiao, H. Wang, C. Liu, W. Shen, and A. L. Yuille, “Weight Standardization,”
2019
Cited alongside, same era.
E. Hoffer, T. Ben-Nun, I. Hubara, N. Giladi, T. Hoefler, and D. Soudry, “Augment Your Batch: Improving Generalization through Instance Repetition,”
2020
Cited alongside, same era.
2021
Later among the works it cites.
B. Balle, G. Cherubin, and J. Hayes, “Reconstructing Training Data with Informed Adversaries,”
2022
Later among the works it cites.
2022
Later among the works it cites.
T. Sander, P. Stock, and A. Sablayrolles, “TAN without a Burn: Scaling Laws of DP-SGD,”
2022
Later among the works it cites.
A. Golatkar, A. Achille, Y.-X. Wang, A. Roth, M. Kearns, and S. Soatto, “Mixed Differential Privacy in Computer Vision,”
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
D. Misra, “Mish: A Self Regularized Non-Monotonic Activation Function,” in
2020
Cited alongside, same era.
N. Carlini, F. Tramèr, E. Wallace, M. Jagielski, A. Herbert-Voss, K. Lee, A. Roberts, T. B. Brown, D. X. Song, Ú. Erlingsson, A. Oprea, and C. Raffel, “Extracting Training Data from Large Language Models,” in
2021
Cited alongside, same era.
F. Dörmann, O. Frisk, L. N. Andersen, and C. F. Pedersen, “Not All Noise is Accounted Equally: How Differentially Private Learning Benefits from Large Sampling Rates,”
2021
Cited alongside, same era.
2021
Cited alongside, same era.
2021
Cited alongside, same era.
T. Hoefler, D. Alistarh, T. Ben-Nun, N. Dryden, and A. Peste, “Sparsity in Deep Learning: Pruning and Growth for Efficient Inference and Training in Neural Networks,”
2021
Cited alongside, same era.
F. Tramèr and D. Boneh, “Differentially Private Learning Needs Better Features (or Much More Data),” in
2021
Cited alongside, same era.
2022
Later among the works it cites.
2022
Later among the works it cites.
G. Cesa, L. Lang, and M. Weiler, “A Program to Build E(N)-Equivariant Steerable CNNs,” in
2022
Later among the works it cites.
M. Geiger and T. Smidt, “e3nn: Euclidean Neural Networks,” 2022. [Online]. Available:
2022
Later among the works it cites.
H. Klause, A. Ziller, D. Rueckert, K. Hammernik, and G. Kaissis, “Differentially Private Training of Residual Networks with Scale Normalisation,” in
2022
Later among the works it cites.
2022
Later among the works it cites.
2022
Later among the works it cites.
2022
Later among the works it cites.