Private Synthetic Data for Multitask Learning and Marginal Queries

no code implementations • 15 Sep 2022 • Giuseppe Vietri, Cedric Archambeau, Sergul Aydore, William Brown, Michael Kearns, Aaron Roth, Ankit Siva, Shuai Tang, Zhiwei Steven Wu

A key innovation in our algorithm is the ability to directly handle numerical features, in contrast to a number of related prior approaches which require numerical features to be first converted into {high cardinality} categorical features via {a binning strategy}.

Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud

1 code implementation • 7 Sep 2021 • Michaela Hardt, Xiaoguang Chen, Xiaoyi Cheng, Michele Donini, Jason Gelman, Satish Gollaprolu, John He, Pedro Larroy, Xinyu Liu, Nick McCarthy, Ashish Rathi, Scott Rees, Ankit Siva, ErhYuan Tsai, Keerthan Vasist, Pinar Yilmaz, Muhammad Bilal Zafar, Sanjiv Das, Kevin Haas, Tyler Hill, Krishnaram Kenthapadi

We present Amazon SageMaker Clarify, an explainability feature for Amazon SageMaker that launched in December 2020, providing insights into data and ML models by identifying biases and explaining predictions.

Bias Detection BIG-bench Machine Learning +2

Differentially Private Query Release Through Adaptive Projection

1 code implementation • 11 Mar 2021 • Sergul Aydore, William Brown, Michael Kearns, Krishnaram Kenthapadi, Luca Melis, Aaron Roth, Ankit Siva

We propose, implement, and evaluate a new algorithm for releasing answers to very large numbers of statistical queries like $k$-way marginals, subject to differential privacy.