Search Results for author:
Found 41 papers, 10 papers with code
Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
We provide an improved analysis of standard differentially private gradient descent for linear regression under the squared error loss.
Metalearning with Very Few Samples Per Task
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.
A rigorous benchmarking of methods for SARS-CoV-2 lineage abundance estimation in wastewater
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.
SARS-CoV-2 Wastewater Genomic Surveillance: Approaches, Challenges, and Opportunities
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.
Fast, Sample-Efficient, Affine-Invariant Private Mean and Covariance Estimation for Subgaussian Distributions
Our algorithm runs in time $\tilde{O}(nd^{\omega - 1} + nd/\varepsilon)$, where $\omega < 2. 38$ is the matrix multiplication exponent.
Differentially Private Sampling from Distributions
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.
Fully Adaptive Composition for Gaussian Differential Privacy
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.
Instance-Optimal Differentially Private Estimation
In this work, we study local minimax convergence estimation rates subject to $\epsilon$-differential privacy.
Strong Memory Lower Bounds for Learning Natural Models
We give lower bounds on the amount of memory required by one-pass streaming algorithms for solving several natural learning problems.
Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams
Motivated by recent applications requiring differential privacy over adaptive streams, we investigate the question of optimal instantiations of the matrix mechanism in this setting.
Differentially Private Model Personalization
We study personalization of supervised learning with user-level differential privacy.
Covariance-Aware Private Mean Estimation Without Private Covariance Estimation
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.
Non-parametric Differentially Private Confidence Intervals for the Median
Differential privacy is a restriction on data processing algorithms that provides strong confidentiality guarantees for individual records in the data.
Unlocking capacities of viral genomics for the COVID-19 pandemic response
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.
Orthogonal Quantum Many-body Scars
Quantum many-body scars have been put forward as counterexamples to the Eigenstate Thermalization Hypothesis.
Statistical Mechanics Quantum Gases Strongly Correlated Electrons Quantum Physics
When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?
Our problems are simple and fairly natural variants of the next-symbol prediction and the cluster labeling tasks.
The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space
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 $O(\ln(\ln(u)/\gamma)/\gamma^2)$.
Empirical Risk Minimization in the Non-interactive Local Model of Differential Privacy
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 $p$.
Real- and imaginary-time evolution with compressed quantum circuits
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
Differentially Private Simple Linear Regression
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.
Crossing a topological phase transition with a quantum computer
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
Guaranteed Validity for Empirical Approaches to Adaptive Data Analysis
We design a general framework for answering adaptive statistical queries that focuses on providing explicit confidence intervals along with point estimates.
Simulating quantum many-body dynamics on a current digital quantum computer
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
Noninteractive Locally Private Learning of Linear Models via Polynomial Approximations
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 $\alpha$).
The Structure of Optimal Private Tests for Simple Hypotheses
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.
From Soft Classifiers to Hard Decisions: How fair can we be?
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.
The Limits of Post-Selection Generalization
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.
Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization
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.
Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network
This paper trains a GAN to generate levels for Super Mario Bros using a level from the Video Game Level Corpus.
Information, Privacy and Stability in Adaptive Data Analysis
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.
Stability selection for component-wise gradient boosting in multiple dimensions
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.
Max-Information, Differential Privacy, and Post-Selection Hypothesis Testing
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.
When is Nontrivial Estimation Possible for Graphons and Stochastic Block Models?
We provide a lower bound on the accuracy of estimators for block graphons with a large number of blocks.
Algorithmic Stability for Adaptive Data Analysis
Specifically, suppose there is an unknown distribution $\mathbf{P}$ and a set of $n$ independent samples $\mathbf{x}$ is drawn from $\mathbf{P}$.
Local, Private, Efficient Protocols for Succinct Histograms
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.
More General Queries and Less Generalization Error in Adaptive Data Analysis
However, generalization error is typically bounded in a non-adaptive model, where all questions are specified before the dataset is drawn.
Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds
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.
(Nearly) Optimal Algorithms for Private Online Learning in Full-information and Bandit Settings
The technique leads to the first nonprivate algorithms for private online learning in the bandit setting.
What Can We Learn Privately?
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.
Sublinear Algorithms for Approximating String Compressibility
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
Fuzzy Extractors: How to Generate Strong Keys from Biometrics and Other Noisy Data
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
