Understanding Gradient Clipping in Private SGD: A Geometric Perspective
暂无分享,去创建一个
[1] H. Brendan McMahan,et al. Differentially Private Learning with Adaptive Clipping , 2019, NeurIPS.
[2] Shuang Song,et al. Characterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems , 2020, ArXiv.
[3] Weijie J. Su,et al. Deep Learning with Gaussian Differential Privacy , 2019, Harvard data science review.
[4] Arindam Banerjee,et al. Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization , 2019, SDM.
[5] Suvrit Sra,et al. Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity , 2019, ICLR.
[6] Sashank J. Reddi,et al. AdaCliP: Adaptive Clipping for Private SGD , 2019, ArXiv.
[7] Di Wang,et al. Differentially Private Empirical Risk Minimization with Smooth Non-Convex Loss Functions: A Non-Stationary View , 2019, AAAI.
[8] Zhiwei Steven Wu,et al. Privacy-Preserving Generative Deep Neural Networks Support Clinical Data Sharing , 2017, bioRxiv.
[9] Yu-Xiang Wang,et al. Poission Subsampled Rényi Differential Privacy , 2019, ICML.
[10] Yu-Xiang Wang,et al. Subsampled Rényi Differential Privacy and Analytical Moments Accountant , 2018, AISTATS.
[11] Ethan Dyer,et al. Gradient Descent Happens in a Tiny Subspace , 2018, ArXiv.
[12] H. Brendan McMahan,et al. Learning Differentially Private Recurrent Language Models , 2017, ICLR.
[13] Ian Goodfellow,et al. Deep Learning with Differential Privacy , 2016, CCS.
[14] Martín Abadi,et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.
[15] Raef Bassily,et al. Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds , 2014, 1405.7085.
[16] Anand D. Sarwate,et al. Stochastic gradient descent with differentially private updates , 2013, 2013 IEEE Global Conference on Signal and Information Processing.
[17] Alex Krizhevsky,et al. Learning Multiple Layers of Features from Tiny Images , 2009 .
[18] Cynthia Dwork,et al. Calibrating Noise to Sensitivity in Private Data Analysis , 2006, TCC.