Fast and Memory Efficient Differentially Private-SGD via JL Projections

Fast and Memory Efficient Differentially Private-SGD via JL Projections

5 February 2021

Janardhan Kulkarni

U. Tantipongpipat

Papers citing "Fast and Memory Efficient Differentially Private-SGD via JL Projections"

12 / 12 papers shown

Title
Selective Pre-training for Private Fine-tuning Da Yu Sivakanth Gopi Janardhan Kulkarni Zinan Lin Saurabh Naik Tomasz Religa Jian Yin Huishuai Zhang 38 19 0 23 May 2023
Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learning AprilPyone Maungmaung Hitoshi Kiya FedML DiffM 21 3 0 09 Mar 2023
On Differential Privacy and Adaptive Data Analysis with Bounded Space Itai Dinur Uri Stemmer David P. Woodruff Samson Zhou 24 12 0 11 Feb 2023
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping Jiyan He Xuechen Li Da Yu Huishuai Zhang Janardhan Kulkarni Y. Lee A. Backurs Nenghai Yu Jiang Bian 30 46 0 03 Dec 2022
Private Ad Modeling with DP-SGD Carson E. Denison Badih Ghazi Pritish Kamath Ravi Kumar Pasin Manurangsi Krishnagiri Narra Amer Sinha A. Varadarajan Chiyuan Zhang 32 14 0 21 Nov 2022
How to Make Your Approximation Algorithm Private: A Black-Box Differentially-Private Transformation for Tunable Approximation Algorithms of Functions with Low Sensitivity Jeremiah Blocki Elena Grigorescu Tamalika Mukherjee Samson Zhou 63 11 0 07 Oct 2022
Differentially Private Optimization on Large Model at Small Cost Zhiqi Bu Yu-Xiang Wang Sheng Zha George Karypis 38 52 0 30 Sep 2022
Faster Privacy Accounting via Evolving Discretization Badih Ghazi Pritish Kamath Ravi Kumar Pasin Manurangsi 62 14 0 10 Jul 2022
Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions Vadym Doroshenko Badih Ghazi Pritish Kamath Ravi Kumar Pasin Manurangsi 18 40 0 10 Jul 2022
Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger Zhiqi Bu Yu-Xiang Wang Sheng Zha George Karypis 27 69 0 14 Jun 2022
Opacus: User-Friendly Differential Privacy Library in PyTorch Ashkan Yousefpour I. Shilov Alexandre Sablayrolles Davide Testuggine Karthik Prasad ... Sayan Gosh Akash Bharadwaj Jessica Zhao Graham Cormode Ilya Mironov VLM 168 350 0 25 Sep 2021
Efficient Per-Example Gradient Computations Ian Goodfellow 186 74 0 07 Oct 2015