Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Mcmillan, Audra"'
Estimating the density of a distribution from samples is a fundamental problem in statistics. In many practical settings, the Wasserstein distance is an appropriate error metric for density estimation. For example, when estimating population densitie
Externí odkaz:
http://arxiv.org/abs/2406.19566
A key challenge in many modern data analysis tasks is that user data are heterogeneous. Different users may possess vastly different numbers of data points. More importantly, it cannot be assumed that all users sample from the same underlying distrib
Externí odkaz:
http://arxiv.org/abs/2307.15835
Autor:
Talwar, Kunal, Wang, Shan, McMillan, Audra, Jina, Vojta, Feldman, Vitaly, Bansal, Pansy, Basile, Bailey, Cahill, Aine, Chan, Yi Sheng, Chatzidakis, Mike, Chen, Junye, Chick, Oliver, Chitnis, Mona, Ganta, Suman, Goren, Yusuf, Granqvist, Filip, Guo, Kristine, Jacobs, Frederic, Javidbakht, Omid, Liu, Albert, Low, Richard, Mascenik, Dan, Myers, Steve, Park, David, Park, Wonhee, Parsa, Gianni, Pauly, Tommy, Priebe, Christian, Rishi, Rehan, Rothblum, Guy, Scaria, Michael, Song, Linmao, Song, Congzheng, Tarbe, Karl, Vogt, Sebastian, Winstrom, Luke, Zhou, Shundong
We revisit the problem of designing scalable protocols for private statistics and private federated learning when each device holds its private data. Locally differentially private algorithms require little trust but are (provably) limited in their u
Externí odkaz:
http://arxiv.org/abs/2307.15017
Autor:
Chadha, Karan, Chen, Junye, Duchi, John, Feldman, Vitaly, Hashemi, Hanieh, Javidbakht, Omid, McMillan, Audra, Talwar, Kunal
In this work, we study practical heuristics to improve the performance of prefix-tree based algorithms for differentially private heavy hitter detection. Our model assumes each user has multiple data points and the goal is to learn as many of the mos
Externí odkaz:
http://arxiv.org/abs/2307.11749
Autor:
McMillan, Audra, Javidbakht, Omid, Talwar, Kunal, Briggs, Elliot, Chatzidakis, Mike, Chen, Junye, Duchi, John, Feldman, Vitaly, Goren, Yusuf, Hesse, Michael, Jina, Vojta, Katti, Anil, Liu, Albert, Lyford, Cheney, Meyer, Joey, Palmer, Alex, Park, David, Park, Wonhee, Parsa, Gianni, Pelzl, Paul, Rishi, Rehan, Song, Congzheng, Wang, Shan, Zhou, Shundong
Privately learning statistics of events on devices can enable improved user experience. Differentially private algorithms for such problems can benefit significantly from interactivity. We argue that an aggregation protocol can enable an interactive
Externí odkaz:
http://arxiv.org/abs/2211.10082
In this work, we study local minimax convergence estimation rates subject to $\epsilon$-differential privacy. Unlike worst-case rates, which may be conservative, algorithms that are locally minimax optimal must adapt to easy instances of the problem.
Externí odkaz:
http://arxiv.org/abs/2210.15819
The shuffle model of differential privacy has gained significant interest as an intermediate trust model between the standard local and central models [EFMRTT19; CSUZZ19]. A key result in this model is that randomly shuffling locally randomized data
Externí odkaz:
http://arxiv.org/abs/2208.04591
Differential privacy is a restriction on data processing algorithms that provides strong confidentiality guarantees for individual records in the data. However, research on proper statistical inference, that is, research on properly quantifying the u
Externí odkaz:
http://arxiv.org/abs/2106.10333
Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and Thakurta [EFMRTT19] demonstrates that random shuffling amplifies differential privacy guarantees of locally randomized data. Such amplification implies substantially stronger priva
Externí odkaz:
http://arxiv.org/abs/2012.12803
Sampling schemes are fundamental tools in statistics, survey design, and algorithm design. A fundamental result in differential privacy is that a differentially private mechanism run on a simple random sample of a population provides stronger privacy
Externí odkaz:
http://arxiv.org/abs/2007.12674