Fetching the paper…
Reading the bibliography…
The training of neural networks with Differentially Private Stochastic Gradient Descent offers formal Differential Privacy guarantees but introduces accuracy trade-offs.
Efficient estimations from a slowly convergent robbins-monro process
Ruppert, D · 1988
Earlier work this paper cites.
Acceleration of stochastic approximation by averaging
Polyak, B. T. and Juditsky, A. B · 1992
Earlier work this paper cites.
Imagenet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L · 2009
Earlier work this paper cites.
Learning multiple layers of features from tiny images
Krizhevsky, A., Hinton, G., et al · 2009
Earlier work this paper cites.
Understanding the difficulty of training deep feedforward neural networks
Glorot, X. and Bengio, Y · 2010
Earlier work this paper cites.
Deep learning with differential privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., and Zhang, L · 2016
Earlier work this paper cites.
Incorporating Nesterov Momentum into Adam
Dozat, T · 2016
Earlier work this paper cites.
Deep residual learning for image recognition
He, K., Zhang, X., Ren, S., and Sun, J · 2016
Earlier work this paper cites.
Scalable private learning with PATE
Papernot, N., Song, S., Mironov, I., Raghunathan, A., Talwar, K., and Erlingsson, U · 2018
Earlier work this paper cites.
Optuna: A next-generation hyperparameter optimization framework
Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M · 2019
Earlier work this paper cites.
Imagenette, 2019
Howard, J · 2019
Cited alongside, same era.
Efficientnet: Rethinking model scaling for convolutional neural networks
Tan, M. and Le, Q · 2019
Cited alongside, same era.
PyHessian: Neural Networks Through the Lens of the Hessian
Yao, Z., Gholami, A., Keutzer, K., and Mahoney, M · 2019
Cited alongside, same era.
Residual learning without normalization via better initialization
Zhang, H., Dauphin, Y. N., and Ma, T · 2019
Cited alongside, same era.
Mish: A self regularized non-monotonic activation function
Misra, D · 2020
Cited alongside, same era.
Making the shoe fit: Architectures, initializations, and tuning for learning with privacy, 2020
Papernot, N., Chien, S., Song, S., Thakurta, A., and Erlingsson, U · 2020
Cited alongside, same era.
Scalable differential privacy with sparse network finetuning
Luo, Z., Wu, D. J., Adeli, E., and Fei-Fei, L · 2021
Later among the works it cites.
Architecture matters: Investigating the influence of differential privacy on neural network design
Morsbach, F., Dehling, T., and Sunyaev, A · 2021
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, U · 2021
Later among the works it cites.
Enabling fast differentially private sgd via just-in-time compilation and vectorization
Subramani, P., Vadivelu, N., and Kamath, G · 2021
Later among the works it cites.
Differentially private learning needs better features (or much more data)
Tramèr, F. and Boneh, D · 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…
Private-KNN: Practical differential privacy for computer vision
Zhu, Y., Yu, X., Chandraker, M., and Wang, Y.-X · 2020
Cited alongside, same era.
On the effect of normalization layers on differentially private training of deep neural networks
Davody, A., Adelani, D. I., Kleinbauer, T., and Klakow, D · 2021
Cited alongside, same era.
Not all noise is accounted equally: How differentially private learning benefits from large sampling rates
Dörmann, F., Frisk, O., Andersen, L. N., and Pedersen, C. F · 2021
Cited alongside, same era.
Drawing multiple augmentation samples per image during training efficiently decreases test error
Fort, S., Brock, A., Pascanu, R., De, S., and Smith, S. L · 2021
Cited alongside, same era.
Wightman, R., Touvron, H., and Jégou, H · 2021
Later among the works it cites.
Opacus: User-friendly differential privacy library in PyTorch
Yousefpour, A., Shilov, I., Sablayrolles, A., Testuggine, D., Prasad, K., Malek, M., Nguyen, J., Ghosh, S., Bharadwaj, A., Zhao, J., Cormode, G., and Mironov, I · 2021
Later among the works it cites.
Unlocking high-accuracy differentially private image classification through scale
De, S., Berrada, L., Hayes, J., Smith, S. L., and Balle, B · 2022
Closest in time.
Toward training at imagenet scale with differential privacy
Kurakin, A., Song, S., Chien, S., Geambasu, R., Terzis, A., and Thakurta, A · 2022
Closest in time.