71 citations · 114 across the 8 of their papers we have counts for
9 papers
FedFetch: Faster Federated Learning with Adaptive Downstream Prefetching
Qifan Yan, Andrew Liu, Shiqi He +2
Federated learning (FL) is a machine learning paradigm that facilitates massively distributed model training with end-user data on edge devices directed by a central server. Howeve…
Turbo: Effective Caching in Differentially-Private Databases
Kelly Kostopoulou, Pierre Tholoniat, Asaf Cidon +2
Differentially-private (DP) databases allow for privacy-preserving analytics over sensitive datasets or data streams. In these systems, user privacy is a limited resource that must…
Fast Optimization of Weighted Sparse Decision Trees for use in Optimal Treatment Regimes and Optimal Policy Design
Ali Behrouz, Mathias Lecuyer, Cynthia Rudin +1
Sparse decision trees are one of the most common forms of interpretable models. While recent advances have produced algorithms that fully optimize sparse decision trees for predict…
Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments
Jinkun Lin, Anqi Zhang, Mathias Lecuyer +3
We develop a new, principled algorithm for estimating the contribution of training data points to the behavior of a deep learning model, such as a specific prediction it makes. Our…
Sayer: Using Implicit Feedback to Optimize System Policies
Mathias Lécuyer, Sang Hoon Kim, Mihir Nanavati +4
We observe that many system policies that make threshold decisions involving a resource (e.g., time, memory, cores) naturally reveal additional, or implicit feedback. For example,…
Privacy Accounting and Quality Control in the Sage Differentially Private ML Platform
Mathias Lecuyer, Riley Spahn, Kiran Vodrahalli +2
Companies increasingly expose machine learning (ML) models trained over sensitive user data to untrusted domains, such as end-user devices and wide-access model stores. We present…
Certified Robustness to Adversarial Examples with Differential Privacy
Mathias Lecuyer, Vaggelis Atlidakis, Roxana Geambasu +2
Adversarial examples that fool machine learning models, particularly deep neural networks, have been a topic of intense research interest, with attacks and defenses being developed…
Pyramid: Enhancing Selectivity in Big Data Protection with Count Featurization
Mathias Lecuyer, Riley Spahn, Roxana Geambasu +2
Protecting vast quantities of data poses a daunting challenge for the growing number of organizations that collect, stockpile, and monetize it. The ability to distinguish data that…
XRay: Enhancing the Web's Transparency with Differential Correlation
Mathias Lecuyer, Guillaume Ducoffe, Francis Lan +5
Today's Web services - such as Google, Amazon, and Facebook - leverage user data for varied purposes, including personalizing recommendations, targeting advertisements, and adjusti…