no code implementations • 16 Feb 2024 • Mark Bun, Aloni Cohen, Rathin Desai
We continue the study of the computational complexity of differentially private PAC learning and how it is situated within the foundations of machine learning.
no code implementations • 13 Feb 2024 • Adam Block, Mark Bun, Rathin Desai, Abhishek Shetty, Steven Wu
Due to statistical lower bounds on the learnability of many function classes under privacy constraints, there has been recent interest in leveraging public data to improve the performance of private learning algorithms.
no code implementations • 1 Feb 2024 • Mark Bun, Gautam Kamath, Argyris Mouzakis, Vikrant Singhal
We give an example of a class of distributions that is learnable in total variation distance with a finite number of samples, but not learnable under $(\varepsilon, \delta)$-differential privacy.
no code implementations • 22 Mar 2023 • Mark Bun, Marco Gaboardi, Max Hopkins, Russell Impagliazzo, Rex Lei, Toniann Pitassi, Satchit Sivakumar, Jessica Sorrell
In particular, we give sample-efficient algorithmic reductions between perfect generalization, approximate differential privacy, and replicability for a broad class of statistical problems.
no code implementations • 9 Jun 2022 • Gavin Brown, Mark Bun, Adam Smith
We give lower bounds on the amount of memory required by one-pass streaming algorithms for solving several natural learning problems.
no code implementations • NeurIPS 2021 • Mark Bun, Marco Gaboardi, Satchit Sivakumar
We show a generic reduction from multiclass differentially private PAC learning to binary private PAC learning.
no code implementations • 17 Feb 2021 • Mark Bun, Marek Eliáš, Janardhan Kulkarni
Correlation clustering is a widely used technique in unsupervised machine learning.
1 code implementation • 11 Dec 2020 • Gavin Brown, Mark Bun, Vitaly Feldman, Adam Smith, Kunal Talwar
Our problems are simple and fairly natural variants of the next-symbol prediction and the cluster labeling tasks.
no code implementations • 24 Jul 2020 • Mark Bun, Jörg Drechsler, Marco Gaboardi, Audra McMillan, Jayshree Sarathy
Sampling schemes are fundamental tools in statistics, survey design, and algorithm design.
no code implementations • NeurIPS 2020 • Mark Bun
A recent line of work has shown a qualitative equivalence between differentially private PAC learning and online learning: A concept class is privately learnable if and only if it is online learnable with a finite mistake bound.
1 code implementation • ICML 2020 • Giuseppe Vietri, Grace Tian, Mark Bun, Thomas Steinke, Zhiwei Steven Wu
We present three new algorithms for constructing differentially private synthetic data---a sanitized version of a sensitive dataset that approximately preserves the answers to a large collection of statistical queries.
no code implementations • 1 Mar 2020 • Mark Bun, Roi Livni, Shay Moran
We prove that every concept class with finite Littlestone dimension can be learned by an (approximate) differentially-private algorithm.
no code implementations • 4 Feb 2020 • Mark Bun, Marco Leandro Carmosino, Jessica Sorrell
To demonstrate our framework, we use it to construct noise-tolerant and private PAC learners for large-margin halfspaces whose sample complexity does not depend on the dimension.
no code implementations • NeurIPS 2019 • Mark Bun, Thomas Steinke
The simplest and most widely applied method for guaranteeing differential privacy is to add instance-independent noise to a statistic of interest that is scaled to its global sensitivity.
Statistics Theory Cryptography and Security Data Structures and Algorithms Statistics Theory
no code implementations • NeurIPS 2019 • Mark Bun, Gautam Kamath, Thomas Steinke, Zhiwei Steven Wu
The sample complexity of our basic algorithm is $O\left(\frac{\log m}{\alpha^2} + \frac{\log m}{\alpha \varepsilon}\right)$, representing a minimal cost for privacy when compared to the non-private algorithm.
no code implementations • ICML 2017 • Marko Mitrovic, Mark Bun, Andreas Krause, Amin Karbasi
Many data summarization applications are captured by the general framework of submodular maximization.
no code implementations • 6 May 2016 • Mark Bun, Thomas Steinke
"Concentrated differential privacy" was recently introduced by Dwork and Rothblum as a relaxation of differential privacy, which permits sharper analyses of many privacy-preserving computations.
no code implementations • 15 Apr 2016 • Mark Bun, Thomas Steinke, Jonathan Ullman
The queries may be chosen adversarially from a larger set Q of allowable queries in one of three ways, which we list in order from easiest to hardest to answer: Offline: The queries are chosen all at once and the differentially private mechanism answers the queries in a single batch.
no code implementations • 27 Nov 2015 • Mark Bun, Kobbi Nissim, Uri Stemmer
We investigate the direct-sum problem in the context of differentially private PAC learning: What is the sample complexity of solving $k$ learning tasks simultaneously under differential privacy, and how does this cost compare to that of solving $k$ learning tasks without privacy?
no code implementations • 3 May 2015 • Mark Bun, Mark Zhandry
An order-revealing encryption scheme gives a public procedure by which two ciphertexts can be compared to reveal the ordering of their underlying plaintexts.
no code implementations • 28 Apr 2015 • Mark Bun, Kobbi Nissim, Uri Stemmer, Salil Vadhan
Our sample complexity upper and lower bounds also apply to the tasks of learning distributions with respect to Kolmogorov distance and of properly PAC learning thresholds with differential privacy.
no code implementations • 8 Dec 2014 • Mark Bun, Thomas Steinke
The power of this algorithm relies on the fact that under log-concave distributions, halfspaces can be approximated arbitrarily well by low-degree polynomials.