Arbitrary Decisions are a Hidden Cost of Differentially Private Training

Arbitrary Decisions are a Hidden Cost of Differentially Private Training

28 February 2023

Carmela Troncoso

Flavio du Pin Calmon

Papers citing "Arbitrary Decisions are a Hidden Cost of Differentially Private Training"

13 / 13 papers shown

Title
Regretful Decisions under Label Noise Sujay Nagaraj Yang Liu Flavio du Pin Calmon Berk Ustun NoLa 58 1 0 12 Apr 2025
Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-Time J. Donnelly Zhicheng Guo A. Barnett Hayden McTavish Chaofan Chen Cynthia Rudin 66 0 0 03 Mar 2025
The Curious Case of Arbitrariness in Machine Learning Prakhar Ganesh Afaf Taik G. Farnadi 59 2 0 28 Jan 2025
The Cost of Arbitrariness for Individuals: Examining the Legal and Technical Challenges of Model Multiplicity Prakhar Ganesh Ihsan Ibrahim Daldaban Ignacio Cofone G. Farnadi 54 2 0 28 May 2024
Algorithmic Arbitrariness in Content Moderation Juan Felipe Gomez Caio Vieira Machado Lucas Monteiro Paes Flavio du Pin Calmon 33 9 0 26 Feb 2024
Predictive Churn with the Set of Good Models J. Watson-Daniels Flavio du Pin Calmon Alexander DÁmour Carol Xuan Long David C. Parkes Berk Ustun 83 7 0 12 Feb 2024
On the Impact of Output Perturbation on Fairness in Binary Linear Classification Vitalii Emelianov Michael Perrot FaML 32 0 0 05 Feb 2024
Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation Hsiang Hsu Guihong Li Shaohan Hu Chun-Fu Chen Chen 28 5 0 01 Feb 2024
When Synthetic Data Met Regulation Georgi Ganev 29 2 0 01 Jul 2023
Arbitrariness Lies Beyond the Fairness-Accuracy Frontier Carol Xuan Long Hsiang Hsu Wael Alghamdi Flavio du Pin Calmon FaML 25 6 0 15 Jun 2023
Hyperparameter Tuning with Renyi Differential Privacy Nicolas Papernot Thomas Steinke 135 120 0 07 Oct 2021
Opacus: User-Friendly Differential Privacy Library in PyTorch Ashkan Yousefpour I. Shilov Alexandre Sablayrolles Davide Testuggine Karthik Prasad ... Sayan Gosh Akash Bharadwaj Jessica Zhao Graham Cormode Ilya Mironov VLM 168 350 0 25 Sep 2021
Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data Georgi Ganev Bristena Oprisanu Emiliano De Cristofaro 37 57 0 23 Sep 2021