no code implementations • 21 Feb 2024 • Gavin Brown, Krishnamurthy Dvijotham, Georgina Evans, Daogao Liu, Adam Smith, Abhradeep Thakurta
We provide an improved analysis of standard differentially private gradient descent for linear regression under the squared error loss.
no code implementations • 21 Dec 2023 • Maryam Aliakbarpour, Konstantina Bairaktari, Gavin Brown, Adam Smith, Nathan Srebro, Jonathan Ullman
In multitask learning, we are given a fixed set of related learning tasks and need to output one accurate model per task, whereas in metalearning we are given tasks that are drawn i. i. d.
no code implementations • 29 Sep 2023 • Viorel Munteanu, Victor Gordeev, Michael Saldana, Eva Aßmann, Justin Maine Su, Nicolae Drabcinski, Oksana Zlenko, Maryna Kit, Felicia Iordachi, Khooshbu Kantibhai Patel, Abdullah Al Nahid, Likhitha Chittampalli, Yidian Xu, Pavel Skums, Shelesh Agrawal, Martin Hölzer, Adam Smith, Alex Zelikovsky, Serghei Mangul
Here, we perform comprehensive benchmarking of 18 bioinformatics methods for estimating the relative abundance of SARS-CoV-2 (sub)lineages in wastewater by using data from 36 in vitro mixtures of synthetic lineage and sublineage genomes.
no code implementations • 23 Sep 2023 • Viorel Munteanu, Michael Saldana, Dumitru Ciorba, Viorel Bostan, Justin Maine Su, Nadiia Kasianchuk, Nitesh Kumar Sharma, Sergey Knyazev, Victor Gordeev, Eva Aßmann, Andrei Lobiuc, Mihai Covasa, Keith A. Crandall, Wenhao O. Ouyang, Nicholas C. Wu, Christopher Mason, Braden T Tierney, Alexander G Lucaci, Alex Zelikovsky, Fatemeh Mohebbi, Pavel Skums, Cynthia Gibas, Jessica Schlueter, Piotr Rzymski, Helena Solo-Gabriele, Martin Hölzer, Adam Smith, Serghei Mangul
The existing bioinformatics tools used to analyze wastewater sequencing data are often based on previously developed methods for quantifying the expression of transcripts or viral diversity.
no code implementations • 28 Jan 2023 • Gavin Brown, Samuel B. Hopkins, Adam Smith
Our algorithm runs in time $\tilde{O}(nd^{\omega - 1} + nd/\varepsilon)$, where $\omega < 2. 38$ is the matrix multiplication exponent.
no code implementations • NeurIPS 2021 • Sofya Raskhodnikova, Satchit Sivakumar, Adam Smith, Marika Swanberg
We demonstrate that, in some parameter regimes, private sampling requires asymptotically fewer observations than learning a description of $P$ nonprivately; in other regimes, however, private sampling proves to be as difficult as private learning.
no code implementations • 31 Oct 2022 • Adam Smith, Abhradeep Thakurta
We show that Gaussian Differential Privacy, a variant of differential privacy tailored to the analysis of Gaussian noise addition, composes gracefully even in the presence of a fully adaptive analyst.
no code implementations • 28 Oct 2022 • Audra McMillan, Adam Smith, Jon Ullman
In this work, we study local minimax convergence estimation rates subject to $\epsilon$-differential privacy.
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.
1 code implementation • 16 Feb 2022 • Sergey Denisov, Brendan Mcmahan, Keith Rush, Adam Smith, Abhradeep Guha Thakurta
Motivated by recent applications requiring differential privacy over adaptive streams, we investigate the question of optimal instantiations of the matrix mechanism in this setting.
no code implementations • NeurIPS 2021 • Prateek Jain, John Rush, Adam Smith, Shuang Song, Abhradeep Guha Thakurta
We study personalization of supervised learning with user-level differential privacy.
no code implementations • NeurIPS 2021 • Gavin Brown, Marco Gaboardi, Adam Smith, Jonathan Ullman, Lydia Zakynthinou
Each of our estimators is based on a simple, general approach to designing differentially private mechanisms, but with novel technical steps to make the estimator private and sample-efficient.
1 code implementation • 18 Jun 2021 • Joerg Drechsler, Ira Globus-Harris, Audra McMillan, Jayshree Sarathy, Adam Smith
Differential privacy is a restriction on data processing algorithms that provides strong confidentiality guarantees for individual records in the data.
no code implementations • 28 Apr 2021 • Sergey Knyazev, Karishma Chhugani, Varuni Sarwal, Ram Ayyala, Harman Singh, Smruthi Karthikeyan, Dhrithi Deshpande, Zoia Comarova, Angela Lu, Yuri Porozov, Aiping Wu, Malak Abedalthagafi, Shivashankar Nagaraj, Adam Smith, Pavel Skums, Jason Ladner, Tommy Tsan-Yuk Lam, Nicholas Wu, Alex Zelikovsky, Rob Knight, Keith Crandall, Serghei Mangul
More than any other infectious disease epidemic, the COVID-19 pandemic has been characterized by the generation of large volumes of viral genomic data at an incredible pace due to recent advances in high-throughput sequencing technologies, the rapid global spread of SARS-CoV-2, and its persistent threat to public health.
no code implementations • 15 Feb 2021 • Hongzheng Zhao, Adam Smith, Florian Mintert, Johannes Knolle
Quantum many-body scars have been put forward as counterexamples to the Eigenstate Thermalization Hypothesis.
Statistical Mechanics Quantum Gases Strongly Correlated Electrons Quantum Physics
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 • NeurIPS 2020 • Adam Smith, Shuang Song, Abhradeep Thakurta
We propose an $(\epsilon,\delta)$-differentially private algorithm that approximates $\dist$ within a factor of $(1\pm\gamma)$, and with additive error of $O(\sqrt{\ln(1/\delta)}/\epsilon)$, using space $O(\ln(\ln(u)/\gamma)/\gamma^2)$.
no code implementations • 11 Nov 2020 • Di Wang, Marco Gaboardi, Adam Smith, Jinhui Xu
In our second attempt, we show that for any $1$-Lipschitz generalized linear convex loss function, there is an $(\epsilon, \delta)$-LDP algorithm whose sample complexity for achieving error $\alpha$ is only linear in the dimensionality $p$.
no code implementations • 24 Aug 2020 • Sheng-Hsuan Lin, Rohit Dilip, Andrew G. Green, Adam Smith, Frank Pollmann
The current generation of noisy intermediate scale quantum computers introduces new opportunities to study quantum many-body systems.
Quantum Physics Mesoscale and Nanoscale Physics Strongly Correlated Electrons
no code implementations • 10 Jul 2020 • Daniel Alabi, Audra McMillan, Jayshree Sarathy, Adam Smith, Salil Vadhan
Economics and social science research often require analyzing datasets of sensitive personal information at fine granularity, with models fit to small subsets of the data.
no code implementations • 11 Oct 2019 • Adam Smith, Bernhard Jobst, Andrew G. Green, Frank Pollmann
The simulation that we perform is easily scalable and is a practical demonstration of the utility of near-term quantum computers for the study of quantum phases of matter and their transitions.
Strongly Correlated Electrons Mesoscale and Nanoscale Physics Quantum Physics
1 code implementation • 21 Jun 2019 • Ryan Rogers, Aaron Roth, Adam Smith, Nathan Srebro, Om Thakkar, Blake Woodworth
We design a general framework for answering adaptive statistical queries that focuses on providing explicit confidence intervals along with point estimates.
1 code implementation • 14 Jun 2019 • Adam Smith, M. S. Kim, Frank Pollmann, Johannes Knolle
Universal quantum computers are potentially an ideal setting for simulating many-body quantum dynamics that is out of reach for classical digital computers.
Quantum Physics Mesoscale and Nanoscale Physics Strongly Correlated Electrons
no code implementations • 17 Dec 2018 • Di Wang, Adam Smith, Jinhui Xu
For the case of \emph{generalized linear losses} (such as hinge and logistic losses), we give an LDP algorithm whose sample complexity is only linear in the dimensionality $p$ and quasipolynomial in other terms (the privacy parameters $\epsilon$ and $\delta$, and the desired excess risk $\alpha$).
no code implementations • 27 Nov 2018 • Clément L. Canonne, Gautam Kamath, Audra McMillan, Adam Smith, Jonathan Ullman
Specifically, we characterize this sample complexity up to constant factors in terms of the structure of $P$ and $Q$ and the privacy level $\varepsilon$, and show that this sample complexity is achieved by a certain randomized and clamped variant of the log-likelihood ratio test.
1 code implementation • 3 Oct 2018 • Ran Canetti, Aloni Cohen, Nishanth Dikkala, Govind Ramnarayan, Sarah Scheffler, Adam Smith
We study the feasibility of achieving various fairness properties by post-processing calibrated scores, and then show that deferring post-processors allow for more fairness conditions to hold on the final decision.
no code implementations • NeurIPS 2018 • Kobbi Nissim, Adam Smith, Thomas Steinke, Uri Stemmer, Jonathan Ullman
While statistics and machine learning offers numerous methods for ensuring generalization, these methods often fail in the presence of adaptivity---the common practice in which the choice of analysis depends on previous interactions with the same dataset.
no code implementations • NeurIPS 2018 • Blake Woodworth, Jialei Wang, Adam Smith, Brendan Mcmahan, Nathan Srebro
We suggest a general oracle-based framework that captures different parallel stochastic optimization settings described by a dependency graph, and derive generic lower bounds in terms of this graph.
3 code implementations • 2 May 2018 • Vanessa Volz, Jacob Schrum, Jialin Liu, Simon M. Lucas, Adam Smith, Sebastian Risi
This paper trains a GAN to generate levels for Super Mario Bros using a level from the Video Game Level Corpus.
no code implementations • 2 Jun 2017 • Adam Smith
This assumption breaks downs when data are re-used across analyses and the analysis to be performed at a given stage depends on the results of earlier stages.
1 code implementation • 30 Nov 2016 • Janek Thomas, Andreas Mayr, Bernd Bischl, Matthias Schmid, Adam Smith, Benjamin Hofner
We apply this new algorithm to a study to estimate abundance of common eider in Massachusetts, USA, featuring excess zeros, overdispersion, non-linearity and spatio-temporal structures.
no code implementations • 13 Apr 2016 • Ryan Rogers, Aaron Roth, Adam Smith, Om Thakkar
In this paper, we initiate a principled study of how the generalization properties of approximate differential privacy can be used to perform adaptive hypothesis testing, while giving statistically valid $p$-value corrections.
no code implementations • 7 Apr 2016 • Audra McMillan, Adam Smith
We provide a lower bound on the accuracy of estimators for block graphons with a large number of blocks.
no code implementations • 8 Nov 2015 • Raef Bassily, Kobbi Nissim, Adam Smith, Thomas Steinke, Uri Stemmer, Jonathan Ullman
Specifically, suppose there is an unknown distribution $\mathbf{P}$ and a set of $n$ independent samples $\mathbf{x}$ is drawn from $\mathbf{P}$.
no code implementations • 18 Apr 2015 • Raef Bassily, Adam Smith
Moreover, we show that this much error is necessary, regardless of computational efficiency, and even for the simple setting where only one item appears with significant frequency in the data set.
no code implementations • 16 Mar 2015 • Raef Bassily, Adam Smith, Thomas Steinke, Jonathan Ullman
However, generalization error is typically bounded in a non-adaptive model, where all questions are specified before the dataset is drawn.
1 code implementation • 27 May 2014 • Raef Bassily, Adam Smith, Abhradeep Thakurta
We provide a separate set of algorithms and matching lower bounds for the setting in which the loss functions are known to also be strongly convex.
no code implementations • NeurIPS 2013 • Abhradeep Guha Thakurta, Adam Smith
The technique leads to the first nonprivate algorithms for private online learning in the bandit setting.
no code implementations • 6 Mar 2008 • Shiva Prasad Kasiviswanathan, Homin K. Lee, Kobbi Nissim, Sofya Raskhodnikova, Adam Smith
Therefore, almost anything learnable is learnable privately: specifically, if a concept class is learnable by a (non-private) algorithm with polynomial sample complexity and output size, then it can be learned privately using a polynomial number of samples.
1 code implementation • 8 Jun 2007 • Sofya Raskhodnikova, Dana Ron, Ronitt Rubinfeld, Adam Smith
We raise the question of approximating the compressibility of a string with respect to a fixed compression scheme, in sublinear time.
Data Structures and Algorithms
no code implementations • 4 Feb 2006 • Yevgeniy Dodis, Rafail Ostrovsky, Leonid Reyzin, Adam Smith
A "secure sketch" produces public information about its input w that does not reveal w, and yet allows exact recovery of w given another value that is close to w. Thus, it can be used to reliably reproduce error-prone biometric inputs without incurring the security risk inherent in storing them.
Cryptography and Security Information Theory Information Theory