Fetching the paper…
Reading the bibliography…
In this paper, we revisit the problem of using in-distribution public data to improve the privacy/utility trade-offs for differentially private (DP) model training.
Problem Complexity and Method Efficiency in Optimization
Nemirovsky, A. and Yudin, D · 1983
Earlier work this paper cites.
A large-deviation inequality for vector-valued martingales
Hayes, T. P · 2003
Earlier work this paper cites.
Calibrating noise to sensitivity in private data analysis
Dwork, C., McSherry, F., Nissim, K., and Smith, A · 2006
Earlier work this paper cites.
Learning from mixtures of private and public populations
Bassily, R., Moran, S., and Nandi, A · 2008
Earlier work this paper cites.
Dimension independence in unconstrained private ERM via adaptive preconditioning
Kairouz, P., Ribero, M., Rush, K., and Thakurta, A · 2008
Earlier work this paper cites.
Learning multiple layers of features from tiny images, 2009
Krizhevsky, A · 2009
Earlier work this paper cites.
Differentially private empirical risk minimization
Chaudhuri, K., Monteleoni, C., and Sarwate, A. D · 2011
Earlier work this paper cites.
Adaptive subgradient methods for online learning and stochastic optimization
Duchi, J., Hazan, E., and Singer, Y · 2011
Earlier work this paper cites.
Stochastic gradient descent with differentially private updates
Song, S., Chaudhuri, K., and Sarwate, A. D · 2013
Earlier work this paper cites.
Private empirical risk minimization: Efficient algorithms and tight error bounds
Bassily, R., Smith, A., and Thakurta, A · 2014
Earlier work this paper cites.
The algorithmic foundations of differential privacy
Dwork, C. and Roth, A · 2014
Earlier work this paper cites.
Microsoft reminds privacy-concerned windows 10 beta testers that they’re volunteers
Merriman, C · 2014
Earlier work this paper cites.
Private empirical risk minimization beyond the worst case: The effect of the constraint set geometry
Talwar, K., Thakurta, A., and Zhang, L · 2014
Earlier work this paper cites.
Deep learning with differential privacy
Abadi, M., Chu, A., Goodfellow, I. J., McMahan, H. B., Mironov, I., Talwar, K., and Zhang, L · 2016
Earlier work this paper cites.
Semi-supervised knowledge transfer for deep learning from private training data
Papernot, N., Abadi, M., Erlingsson, U., Goodfellow, I., and Talwar, K · 2016
Cited alongside, same era.
Emnist: Extending mnist to handwritten letters
Cohen, G., Afshar, S., Tapson, J., and Schaik, A. V · 2017
Cited alongside, same era.
Communication-efficient learning of deep networks from decentralized data
McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B. A · 2017
Cited alongside, same era.
Pointer sentinel mixture models
Merity, S., Xiong, C., Bradbury, J., and Socher, R · 2017
Cited alongside, same era.
Differentially private empirical risk minimization revisited: Faster and more general
Wang, D., Ye, M., and Xu, J · 2017
Cited alongside, same era.
Privacy-preserving prediction
Dwork, C. and Feldman, V · 2018
Introduction to online convex optimization
Hazan, E · 2019
Later among the works it cites.
Stability of stochastic gradient descent on nonsmooth convex losses
Bassily, R., Feldman, V., Guzmán, C., and Talwar, K · 2020
Later among the works it cites.
Coinpress: Practical private mean and covariance estimation
Biswas, S., Dong, Y., Kamath, G., and Ullman, J · 2020
Later among the works it cites.
Privately answering classification queries in the agnostic pac model
Nandi, A. and Bassily, R · 2020
Later among the works it cites.
Tempered sigmoid activations for deep learning with differential privacy
Papernot, N., Thakurta, A., Song, S., Chien, S., and Erlingsson, Ú · 2020
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Privacy amplification by iteration
Feldman, V., Mironov, I., Talwar, K., and Thakurta, A · 2018
Cited alongside, same era.
Gradient descent happens in a tiny subspace
Gur-Ari, G., Roberts, D. A., and Dyer, E · 2018
Cited alongside, same era.
The Stack Overflow Data, 2018
Overflow, S · 2018
Cited alongside, same era.
Scalable private learning with pate
Papernot, N., Song, S., Mironov, I., Raghunathan, A., Talwar, K., and Erlingsson, Ú · 2018
Cited alongside, same era.
Efficient full-matrix adaptive regularization
Agarwal, N., Bullins, B., Chen, X., Hazan, E., Singh, K., Zhang, C., and Zhang, Y · 2019
Cited alongside, same era.
Limits of private learning with access to public data
Alon, N., Bassily, R., and Moran, S · 2019
Cited alongside, same era.
Differentially private learning needs better features (or much more data)
Tramer, F. and Boneh, D · 2020
Later among the works it cites.
Differentially private learning with small public data
Wang, J. and Zhou, Z.-H · 2020
Later among the works it cites.
Bypassing the ambient dimension: Private sgd with gradient subspace identification
Zhou, Y., Wu, Z. S., and Banerjee, A · 2020
Later among the works it cites.
Private adaptive gradient methods for convex optimization
Asi, H., Duchi, J., Fallah, A., Javidbakht, O., and Talwar, K · 2021
Closest in time.
Large language models can be strong differentially private learners
Li, X., Tramèr, F., Liang, P., and Hashimoto, T · 2021
Closest in time.
Leveraging public data for practical private query release
Liu, T., Vietri, G., Steinke, T., Ullman, J., and Wu, Z. S · 2021
Closest in time.
Do not let privacy overbill utility: Gradient embedding perturbation for private learning
Yu, D., Zhang, H., Chen, W., and Liu, T · 2021
Closest in time.
Private adaptive optimization with side information
Li, T., Zaheer, M., Reddi, S. J., and Smith, V · 2022
Closest in time.