Zobrazeno 1 - 10
of 69
pro vyhledávání: '"Varadarajan, Avinash"'
Autor:
Chua, Lynn, Cui, Qiliang, Ghazi, Badih, Harrison, Charlie, Kamath, Pritish, Krichene, Walid, Kumar, Ravi, Manurangsi, Pasin, Narra, Krishna Giri, Sinha, Amer, Varadarajan, Avinash, Zhang, Chiyuan
Motivated by problems arising in digital advertising, we introduce the task of training differentially private (DP) machine learning models with semi-sensitive features. In this setting, a subset of the features is known to the attacker (and thus nee
Externí odkaz:
http://arxiv.org/abs/2401.15246
Autor:
Badanidiyuru, Ashwinkumar, Ghazi, Badih, Kamath, Pritish, Kumar, Ravi, Leeman, Ethan, Manurangsi, Pasin, Varadarajan, Avinash V, Zhang, Chiyuan
We propose a new family of label randomizers for training regression models under the constraint of label differential privacy (DP). In particular, we leverage the trade-offs between bias and variance to construct better label randomizers depending o
Externí odkaz:
http://arxiv.org/abs/2312.05659
Autor:
Aksu, Hidayet, Ghazi, Badih, Kamath, Pritish, Kumar, Ravi, Manurangsi, Pasin, Sealfon, Adam, Varadarajan, Avinash V
The Privacy Sandbox Attribution Reporting API has been recently deployed by Google Chrome to support the basic advertising functionality of attribution reporting (aka conversion measurement) after deprecation of third-party cookies. The API implement
Externí odkaz:
http://arxiv.org/abs/2311.13586
Autor:
Ghazi, Badih, Kamath, Pritish, Kumar, Ravi, Leeman, Ethan, Manurangsi, Pasin, Varadarajan, Avinash V, Zhang, Chiyuan
We study the task of training regression models with the guarantee of label differential privacy (DP). Based on a global prior distribution on label values, which could be obtained privately, we derive a label DP randomization mechanism that is optim
Externí odkaz:
http://arxiv.org/abs/2212.06074
Autor:
Denison, Carson, Ghazi, Badih, Kamath, Pritish, Kumar, Ravi, Manurangsi, Pasin, Narra, Krishna Giri, Sinha, Amer, Varadarajan, Avinash V, Zhang, Chiyuan
A well-known algorithm in privacy-preserving ML is differentially private stochastic gradient descent (DP-SGD). While this algorithm has been evaluated on text and image data, it has not been previously applied to ads data, which are notorious for th
Externí odkaz:
http://arxiv.org/abs/2211.11896
Autor:
Babenko, Boris, Traynis, Ilana, Chen, Christina, Singh, Preeti, Uddin, Akib, Cuadros, Jorge, Daskivich, Lauren P., Maa, April Y., Kim, Ramasamy, Kang, Eugene Yu-Chuan, Matias, Yossi, Corrado, Greg S., Peng, Lily, Webster, Dale R., Semturs, Christopher, Krause, Jonathan, Varadarajan, Avinash V., Hammel, Naama, Liu, Yun
External eye photos were recently shown to reveal signs of diabetic retinal disease and elevated HbA1c. In this paper, we evaluate if external eye photos contain information about additional systemic medical conditions. We developed a deep learning s
Externí odkaz:
http://arxiv.org/abs/2207.08998
Autor:
Babenko, Boris, Mitani, Akinori, Traynis, Ilana, Kitade, Naho, Singh, Preeti, Maa, April, Cuadros, Jorge, Corrado, Greg S., Peng, Lily, Webster, Dale R., Varadarajan, Avinash, Hammel, Naama, Liu, Yun
Publikováno v:
Nature Biomedical Engineering 2022
Diabetes-related retinal conditions can be detected by examining the posterior of the eye. By contrast, examining the anterior of the eye can reveal conditions affecting the front of the eye, such as changes to the eyelids, cornea, or crystalline len
Externí odkaz:
http://arxiv.org/abs/2011.11732
Autor:
Bora, Ashish, Balasubramanian, Siva, Babenko, Boris, Virmani, Sunny, Venugopalan, Subhashini, Mitani, Akinori, Marinho, Guilherme de Oliveira, Cuadros, Jorge, Ruamviboonsuk, Paisan, Corrado, Greg S, Peng, Lily, Webster, Dale R, Varadarajan, Avinash V, Hammel, Naama, Liu, Yun, Bavishi, Pinal
Publikováno v:
The Lancet Digital Health (2021)
Diabetic retinopathy (DR) screening is instrumental in preventing blindness, but faces a scaling challenge as the number of diabetic patients rises. Risk stratification for the development of DR may help optimize screening intervals to reduce costs w
Externí odkaz:
http://arxiv.org/abs/2008.04370
Autor:
Narayanaswamy, Arunachalam, Venugopalan, Subhashini, Webster, Dale R., Peng, Lily, Corrado, Greg, Ruamviboonsuk, Paisan, Bavishi, Pinal, Sayres, Rory, Huang, Abigail, Balasubramanian, Siva, Brenner, Michael, Nelson, Philip, Varadarajan, Avinash V.
Publikováno v:
MICCAI 2020
Model explanation techniques play a critical role in understanding the source of a model's performance and making its decisions transparent. Here we investigate if explanation techniques can also be used as a mechanism for scientific discovery. We ma
Externí odkaz:
http://arxiv.org/abs/2007.05500
Autor:
Mitani, Akinori, Liu, Yun, Huang, Abigail, Corrado, Greg S., Peng, Lily, Webster, Dale R., Hammel, Naama, Varadarajan, Avinash V.
Publikováno v:
Nature Biomedical Engineering (2019)
Despite its high prevalence, anemia is often undetected due to the invasiveness and cost of screening and diagnostic tests. Though some non-invasive approaches have been developed, they are less accurate than invasive methods, resulting in an unmet n
Externí odkaz:
http://arxiv.org/abs/1904.06435