Publications

Publications

Filter Results: (40) Arrow Down

Show Results For

Page 1 of 40 Results →
  • Article

Accuracy First: Selecting a Differential Privacy Level for Accuracy-Constrained ERM

By: Katrina Ligett, Seth Neel, Aaron Leon Roth, Bo Waggoner and Steven Wu
Traditional approaches to differential privacy assume a fixed privacy requirement ϵ for a computation, and attempt to maximize the accuracy of the computation subject to the privacy constraint. As differential privacy is increasingly deployed in practical settings, it... View Details
Keywords: Differential Privacy; Empirical Risk Minimization; Accuracy First
Related
  • Article

How to Use Heuristics for Differential Privacy

By: Seth Neel, Aaron Leon Roth and Zhiwei Steven Wu
We develop theory for using heuristics to solve computationally hard problems in differential privacy. Heuristic approaches have enjoyed tremendous success in machine learning, for which performance can be empirically evaluated. However, privacy guarantees cannot be... View Details
Related
  • Article

The Role of Interactivity in Local Differential Privacy

By: Matthew Joseph, Jieming Mao, Seth Neel and Aaron Leon Roth
We study the power of interactivity in local differential privacy. First, we focus on the difference between fully interactive and sequentially interactive protocols. Sequentially interactive protocols may query users adaptively in sequence, but they cannot return to... View Details
Related
  • Article

Mitigating Bias in Adaptive Data Gathering via Differential Privacy

By: Seth Neel and Aaron Leon Roth
Data that is gathered adaptively—via bandit algorithms, for example—exhibits bias. This is true both when gathering simple numeric valued data—the empirical means kept track of by stochastic bandit algorithms are biased downwards—and when gathering more complicated... View Details
Keywords: Bandit Algorithms; Bias; Analytics and Data Science; Mathematical Methods; Theory
Related

    A New Analysis of Differential Privacy’s Generalization Guarantees

    We give a new proof of the “transfer theorem” underlying adaptive data analysis: that any mechanism for answering adaptively chosen statistical queries that is differentially private and sample-accurate is also accurate out-of-sample. Our new proof is elementary and... View Details
    • Oct 2020
    • Conference Presentation

    Optimal, Truthful, and Private Securities Lending

    By: Emily Diana, Michael J. Kearns, Seth Neel and Aaron Leon Roth
    We consider a fundamental dynamic allocation problem motivated by the problem of securities lending in financial markets, the mechanism underlying the short selling of stocks. A lender would like to distribute a finite number of identical copies of some scarce resource... View Details
    Keywords: Differential Privacy; Mechanism Design; Finance; Mathematical Methods
    Related
    • Mar 2020
    • Conference Presentation

    A New Analysis of Differential Privacy's Generalization Guarantees

    By: Christopher Jung, Katrina Ligett, Seth Neel, Aaron Roth, Saeed Sharifi-Malvajerdi and Moshe Shenfeld
    We give a new proof of the "transfer theorem" underlying adaptive data analysis: that any mechanism for answering adaptively chosen statistical queries that is differentially private and sample-accurate is also accurate out-of-sample. Our new proof is elementary and... View Details
    Keywords: Machine Learning; Transfer Theorem; Mathematical Methods
    Related
    • 2025
    • Working Paper

    Enhancing Treatment Effect Prediction on Privacy-Protected Data: An Honest Post-Processing Approach

    By: Ta-Wei Huang and Eva Ascarza
    As firms increasingly rely on customer data for personalization, concerns over privacy and regulatory compliance have grown. Local Differential Privacy (LDP) offers strong individual-level protection by injecting noise into data before collection. While... View Details
    Keywords: Targeted Intervention; Conditional Average Treatment Effect Estimation; Differential Privacy; Honest Estimation; Post-processing; Analytics and Data Science; Consumer Behavior; Marketing
    Related
    • 19 May 2014
    • Research & Ideas

    Why Companies Should Compete for Your Privacy

    Consumers are increasingly wary about sharing personal information with firms. Yet when they benefit from providing information in exchange for lower prices or better services, many consumers will gladly make the privacy trade-off. But... View Details
    Keywords: by Dina Gerdeman; Consumer Products
    • April 2021 (Revised March 2024)
    • Case

    Social Media War 2021: Snap vs. Facebook vs. TikTok

    By: David B. Yoffie and Daniel Fisher
    This case explores the competitive war between Snap, Facebook, and TikTok in 2021. The strategic focus is on Snapchat: how should it respond to the emergence of TikTok, and how should it compete with the dominant competitor in its space—Facebook. The case examines... View Details
    Keywords: Strategy Development; Competitor Analysis; Strategy; Network Effects; Competitive Strategy; Decision Choices and Conditions; Social Media
    Related
    • Article

    Oracle Efficient Private Non-Convex Optimization

    By: Seth Neel, Aaron Leon Roth, Giuseppe Vietri and Zhiwei Steven Wu
    One of the most effective algorithms for differentially private learning and optimization is objective perturbation. This technique augments a given optimization problem (e.g. deriving from an ERM problem) with a random linear term, and then exactly solves it.... View Details
    Keywords: Machine Learning; Algorithms; Objective Perturbation; Mathematical Methods
    Related
    • Article

    Adaptive Machine Unlearning

    By: Varun Gupta, Christopher Jung, Seth Neel, Aaron Roth, Saeed Sharifi-Malvajerdi and Chris Waites
    Data deletion algorithms aim to remove the influence of deleted data points from trained models at a cheaper computational cost than fully retraining those models. However, for sequences of deletions, most prior work in the non-convex setting gives valid guarantees... View Details
    Keywords: Machine Learning; AI and Machine Learning
    Related
    • 08 May 2007
    • First Look

    First Look: May 8, 2007

    occur relatively quickly when the underlying repugnance changes. Download the paper: http://www.hbs.edu/research/pdf/07-077.pdf An Empirical Approach to Understanding Privacy Valuation Authors:Luc Wathieu and Allan Friedman Abstract The... View Details
    Keywords: Martha Lagace
    • Article

    Assessing the Food and Drug Administration's Risk-Based Framework for Software Precertification with Top Health Apps in the United States: Quality Improvement Study

    By: Noy Alon, Ariel Dora Stern and John Torous
    BACKGROUND: As the development of mobile health apps continues to accelerate, the need to implement a framework that can standardize categorizing these apps to allow for efficient, yet robust regulation grows. However, regulators and researchers are faced with numerous... View Details
    Keywords: Mobile Health; Smartphone; Food And Drug Administration; Risk-based Framework; Health Care and Treatment; Mobile and Wireless Technology; Applications and Software; Framework
    Related
    • 22 Feb 2024
    • Research & Ideas

    How to Make AI 'Forget' All the Private Data It Shouldn't Have

    Europe’s tougher data privacy regulations went into effect in 2018, they have created complications for companies worldwide. Questions around data privacy will likely become thornier as generative artificial... View Details
    Keywords: by Rachel Layne; Technology; Information Technology
    • 09 Oct 2018
    • First Look

    New Research and Ideas, October 9, 2018

    process. Can algorithms, machine learning, and artificial intelligence help Tailor Brands outperform graphic designers and branding agencies in developing brand identities? And, can Tailor Brands differentiate itself from the many other... View Details
    Keywords: Dina Gerdeman
    • Web

    Middle East & North Africa - Global

    strategic choices about offline expansion and globalization. Founded in 2015, Boutiqaat combined social commerce, localized logistics, and private label products to build a differentiated digital platform. Students must evaluate whether... View Details
    • 31 Jan 2022
    • Research & Ideas

    Where Can Digital Transformation Take You? Insights from 1,700 Leaders

    privacy and security. Social responsibility in the broadest sense, roundtable participants said, has become a competitive “must,” essential for attracting talent and building trust with customers. Six qualities of digitally mature... View Details
    Keywords: by Linda A. Hill, Ann Le Cam, Sunand Menon, and Emily Tedards
    • 01 Dec 2023
    • News

    Thinking Ahead

    Lab at the Digital Data Design Institute at Harvard; his research develops tools for machine learning that mitigate bias and enhance privacy. Generative AI poses a greater risk to privacy by its nature, Neel explains. A traditional... View Details
    Keywords: Julia Hanna; Illustrations by Chris Gash; News, Library, Internet, and Other Services; Information
    • 05 Feb 2013
    • First Look

    First Look: Feb. 5

    blended identity; thus, limiting the extent to which such organizations can truly "re-direct" future career choices. Strategic Orientations in a Competitive Context: The Role of Strategic Orientation Differentiation... View Details
    Keywords: Sean Silverthorne