Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization
暂无分享,去创建一个
[1] Jürgen Schmidhuber,et al. Long Short-Term Memory , 1997, Neural Computation.
[2] Yoshua Bengio,et al. Gradient-based learning applied to document recognition , 1998, Proc. IEEE.
[3] Pierangela Samarati,et al. Generalizing Data to Provide Anonymity when Disclosing Information , 1998, PODS 1998.
[4] Yann LeCun,et al. The mnist database of handwritten digits , 2005 .
[5] Cynthia Dwork,et al. Calibrating Noise to Sensitivity in Private Data Analysis , 2006, TCC.
[6] Alex Krizhevsky,et al. Learning Multiple Layers of Features from Tiny Images , 2009 .
[7] Christopher Potts,et al. Learning Word Vectors for Sentiment Analysis , 2011, ACL.
[8] Anand D. Sarwate,et al. Stochastic gradient descent with differentially private updates , 2013, 2013 IEEE Global Conference on Signal and Information Processing.
[9] Úlfar Erlingsson,et al. RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response , 2014, CCS.
[10] Raef Bassily,et al. Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds , 2014, 1405.7085.
[11] Tong Zhang,et al. Stochastic Optimization with Importance Sampling for Regularized Loss Minimization , 2014, ICML.
[12] Ian J. Goodfellow,et al. Efficient Per-Example Gradient Computations , 2015, ArXiv.
[13] Cynthia Dwork,et al. Calibrating Noise to Sensitivity in Private Data Analysis , 2016, J. Priv. Confidentiality.
[14] Yuan Yu,et al. TensorFlow: A system for large-scale machine learning , 2016, OSDI.
[15] Ian Goodfellow,et al. Deep Learning with Differential Privacy , 2016, CCS.
[16] Úlfar Erlingsson,et al. Prochlo: Strong Privacy for Analytics in the Crowd , 2017, SOSP.
[17] Janardhan Kulkarni,et al. Collecting Telemetry Data Privately , 2017, NIPS.
[18] Vishesh Karwa,et al. Finite Sample Differentially Private Confidence Intervals , 2017, ITCS.
[19] Gaurav Kapoor,et al. Protection Against Reconstruction and Its Applications in Private Federated Learning , 2018, ArXiv.
[20] Matthew Johnson,et al. Compiling machine learning programs via high-level tracing , 2018 .
[21] H. Brendan McMahan,et al. A General Approach to Adding Differential Privacy to Iterative Training Procedures , 2018, ArXiv.
[22] Eric W. Tramel,et al. Efficient Per-Example Gradient Computations in Convolutional Neural Networks , 2019, ArXiv.
[23] Dawn Song,et al. Towards Practical Differentially Private Convex Optimization , 2019, 2019 IEEE Symposium on Security and Privacy (SP).
[24] Natalia Gimelshein,et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.
[25] Úlfar Erlingsson,et al. The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks , 2018, USENIX Security Symposium.
[26] Ashish Agarwal,et al. Auto-Vectorizing TensorFlow Graphs: Jacobians, Auto-Batching And Beyond , 2019, ArXiv.
[27] Jerry Li,et al. Privately Learning High-Dimensional Distributions , 2018, COLT.
[28] Jaime Fern'andez del R'io,et al. Array programming with NumPy , 2020, Nature.
[29] Jonathan Ullman,et al. Private Mean Estimation of Heavy-Tailed Distributions , 2020, COLT.
[30] Philipp Hennig,et al. BackPACK: Packing more into backprop , 2019, International Conference on Learning Representations.
[31] FAST DIFFERENTIALLY PRIVATE-SGD VIA JL PROJECTIONS , 2020 .
[32] Dietrich Klakow,et al. Investigating the Impact of Pre-trained Word Embeddings on Memorization in Neural Networks , 2020, TDS.
[33] Jonathan Ullman,et al. CoinPress: Practical Private Mean and Covariance Estimation , 2020, NeurIPS.
[34] Rachel Cummings,et al. Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation , 2021, AIES.
[35] Badih Ghazi,et al. Large-Scale Differentially Private BERT , 2021, EMNLP.
[36] Úlfar Erlingsson,et al. Tempered Sigmoid Activations for Deep Learning with Differential Privacy , 2020, AAAI.
[37] Janardhan Kulkarni,et al. Fast and Memory Efficient Differentially Private-SGD via JL Projections , 2021, NeurIPS.
[38] Graham Cormode,et al. Opacus: User-Friendly Differential Privacy Library in PyTorch , 2021, ArXiv.
[39] Daniel Kifer,et al. Scaling up Differentially Private Deep Learning with Fast Per-Example Gradient Clipping , 2020, Proc. Priv. Enhancing Technol..