Zobrazeno 1 - 10
of 184
pro vyhledávání: '"McKenna, Ryan"'
Autor:
Charles, Zachary, Ganesh, Arun, McKenna, Ryan, McMahan, H. Brendan, Mitchell, Nicole, Pillutla, Krishna, Rush, Keith
We investigate practical and scalable algorithms for training large language models (LLMs) with user-level differential privacy (DP) in order to provably safeguard all the examples contributed by each user. We study two variants of DP-SGD with: (1) e
Externí odkaz:
http://arxiv.org/abs/2407.07737
Autor:
Bian, Christopher, Cheu, Albert, Guzman, Yannis, Gruteser, Marco, Kairouz, Peter, McKenna, Ryan, Roth, Edo
Environmental Insights Explorer (EIE) is a Google product that reports aggregate statistics about human mobility, including various methods of transit used by people across roughly 50,000 regions globally. These statistics are used to estimate carbon
Externí odkaz:
http://arxiv.org/abs/2407.03496
Autor:
McKenna, Ryan
Correlated noise mechanisms such as DP Matrix Factorization (DP-MF) have proven to be effective alternatives to DP-SGD in large-epsilon few-epoch training regimes. Significant work has been done to find the best correlated noise strategies, and the c
Externí odkaz:
http://arxiv.org/abs/2405.15913
Mechanisms for generating differentially private synthetic data based on marginals and graphical models have been successful in a wide range of settings. However, one limitation of these methods is their inability to incorporate public data. Initiali
Externí odkaz:
http://arxiv.org/abs/2403.07797
Autor:
Choquette-Choo, Christopher A., Ganesh, Arun, McKenna, Ryan, McMahan, H. Brendan, Rush, Keith, Thakurta, Abhradeep, Xu, Zheng
Matrix factorization (MF) mechanisms for differential privacy (DP) have substantially improved the state-of-the-art in privacy-utility-computation tradeoffs for ML applications in a variety of scenarios, but in both the centralized and federated sett
Externí odkaz:
http://arxiv.org/abs/2306.08153
We study gradient descent under linearly correlated noise. Our work is motivated by recent practical methods for optimization with differential privacy (DP), such as DP-FTRL, which achieve strong performance in settings where privacy amplification te
Externí odkaz:
http://arxiv.org/abs/2302.01463
We propose AIM, a new algorithm for differentially private synthetic data generation. AIM is a workload-adaptive algorithm within the paradigm of algorithms that first selects a set of queries, then privately measures those queries, and finally gener
Externí odkaz:
http://arxiv.org/abs/2201.12677
This work presents a systematic benchmark of differentially private synthetic data generation algorithms that can generate tabular data. Utility of the synthetic data is evaluated by measuring whether the synthetic data preserve the distribution of i
Externí odkaz:
http://arxiv.org/abs/2112.09238
Many differentially private algorithms for answering database queries involve a step that reconstructs a discrete data distribution from noisy measurements. This provides consistent query answers and reduces error, but often requires space that grows
Externí odkaz:
http://arxiv.org/abs/2109.06153
We propose a general approach for differentially private synthetic data generation, that consists of three steps: (1) select a collection of low-dimensional marginals, (2) measure those marginals with a noise addition mechanism, and (3) generate synt
Externí odkaz:
http://arxiv.org/abs/2108.04978