Search Results for author:
Found 36 papers, 4 papers with code
Hadamard Response: Estimating Distributions Privately, Efficiently, and with Little Communication
All previously known sample optimal algorithms require linear (in $k$) communication from each user in the high privacy regime $(\varepsilon=O(1))$, and run in time that grows as $n\cdot k$, which can be prohibitive for large domain size $k$.
Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
We introduce camouflaged data poisoning attacks, a new attack vector that arises in the context of machine unlearning and other settings when model retraining may be induced.
INSPECTRE: Privately Estimating the Unseen
We develop differentially private methods for estimating various distributional properties.
Learning and Testing Causal Models with Interventions
We consider testing and learning problems on causal Bayesian networks as defined by Pearl (Pearl, 2009).
Distributed Simulation and Distributed Inference
Nonetheless, we present a Las Vegas algorithm that simulates a single sample from the unknown distribution using $O(k/2^\ell)$ samples in expectation.
Differentially Private Testing of Identity and Closeness of Discrete Distributions
We propose a general framework to establish lower bounds on the sample complexity of statistical tasks under differential privacy.
A Unified Maximum Likelihood Approach for Optimal Distribution Property Estimation
The advent of data science has spurred interest in estimating properties of distributions over large alphabets.
Fast Algorithms for Segmented Regression
We study the fixed design segmented regression problem: Given noisy samples from a piecewise linear function $f$, we want to recover $f$ up to a desired accuracy in mean-squared error.
Estimating Renyi Entropy of Discrete Distributions
It was recently shown that estimating the Shannon entropy $H({\rm p})$ of a discrete $k$-symbol distribution ${\rm p}$ requires $\Theta(k/\log k)$ samples, a number that grows near-linearly in the support size.
Optimal Testing for Properties of Distributions
Given samples from an unknown distribution $p$, is it possible to distinguish whether $p$ belongs to some class of distributions $\mathcal{C}$ versus $p$ being far from every distribution in $\mathcal{C}$?
Sample-Optimal Density Estimation in Nearly-Linear Time
Let $f$ be the density function of an arbitrary univariate distribution, and suppose that $f$ is $\mathrm{OPT}$-close in $L_1$-distance to an unknown piecewise polynomial function with $t$ interval pieces and degree $d$.
A Chasm Between Identity and Equivalence Testing with Conditional Queries
We answer a question of Chakraborty et al. (ITCS 2013) showing that non-adaptive uniformity testing indeed requires $\Omega(\log n)$ queries in the conditional model.
Testing Poisson Binomial Distributions
We provide a sample near-optimal algorithm for testing whether a distribution $P$ supported on $\{0,..., n\}$ to which we have sample access is a Poisson Binomial distribution, or far from all Poisson Binomial distributions.
Universal Compression of Envelope Classes: Tight Characterization via Poisson Sampling
The Poisson-sampling technique eliminates dependencies among symbol appearances in a random sequence.
Near-optimal-sample estimators for spherical Gaussian mixtures
For mixtures of any $k$ $d$-dimensional spherical Gaussians, we derive an intuitive spectral-estimator that uses $\mathcal{O}_k\bigl(\frac{d\log^2d}{\epsilon^4}\bigr)$ samples and runs in time $\mathcal{O}_{k,\epsilon}(d^3\log^5 d)$, both significantly lower than previously known.
Test without Trust: Optimal Locally Private Distribution Testing
We are concerned with two settings: First, when we insist on using an already deployed, general-purpose locally differentially private mechanism such as the popular RAPPOR or the recently introduced Hadamard Response for collecting data, and must build our tests based on the data collected via this mechanism; and second, when no such restriction is imposed, and we can design a bespoke mechanism specifically for testing.
A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions
Symmetric distribution properties such as support size, support coverage, entropy, and proximity to uniformity, arise in many applications.
Inference under Information Constraints I: Lower Bounds from Chi-Square Contraction
Underlying our bounds is a characterization of the contraction in chi-square distances between the observed distributions of the samples when information constraints are placed.
Distributed Learning with Sublinear Communication
In distributed statistical learning, $N$ samples are split across $m$ machines and a learner wishes to use minimal communication to learn as well as if the examples were on a single machine.
Inference under Information Constraints II: Communication Constraints and Shared Randomness
We propose a general-purpose simulate-and-infer strategy that uses only private-coin communication protocols and is sample-optimal for distribution learning.
Communication Complexity in Locally Private Distribution Estimation and Heavy Hitters
We consider the problems of distribution estimation and heavy hitter (frequency) estimation under privacy and communication constraints.
Domain Compression and its Application to Randomness-Optimal Distributed Goodness-of-Fit
We study goodness-of-fit of discrete distributions in the distributed setting, where samples are divided between multiple users who can only release a limited amount of information about their samples due to various information constraints.
Optimal multiclass overfitting by sequence reconstruction from Hamming queries
A primary concern of excessive reuse of test datasets in machine learning is that it can lead to overfitting.
Context-Aware Local Differential Privacy
Local differential privacy (LDP) is a strong notion of privacy for individual users that often comes at the expense of a significant drop in utility.
Estimating Entropy of Distributions in Constant Space
We consider the task of estimating the entropy of $k$-ary distributions from samples in the streaming model, where space is limited.
Differentially Private Assouad, Fano, and Le Cam
The technical component of our paper relates coupling between distributions to the sample complexity of estimation under differential privacy.
Interactive Inference under Information Constraints
We study the role of interactivity in distributed statistical inference under information constraints, e. g., communication constraints and local differential privacy.
Context Aware Local Differential Privacy
The original definition of LDP assumes that all the elements in the data domain are equally sensitive.
Estimating Sparse Discrete Distributions Under Local Privacy and Communication Constraints
We consider the problem of estimating sparse discrete distributions under local differential privacy (LDP) and communication constraints.
Remember What You Want to Forget: Algorithms for Machine Unlearning
We study the problem of unlearning datapoints from a learnt model.
Robust Testing and Estimation under Manipulation Attacks
We consider both the "centralized setting" and the "distributed setting with information constraints" including communication and local privacy (LDP) constraints.
Principal Bit Analysis: Autoencoding with Schur-Concave Loss
As one application, we consider a strictly Schur-concave constraint that estimates the number of bits needed to represent the latent variables under fixed-rate encoding, a setup that we call \emph{Principal Bit Analysis (PBA)}.
Robust Estimation for Random Graphs
We study the problem of robustly estimating the parameter $p$ of an Erd\H{o}s-R\'enyi random graph on $n$ nodes, where a $\gamma$ fraction of nodes may be adversarially corrupted.
Distributed Estimation with Multiple Samples per User: Sharp Rates and Phase Transition
We obtain tight minimax rates for the problem of distributed estimation of discrete distributions under communication constraints, where $n$ users observing $m $ samples each can broadcast only $\ell$ bits.
The Role of Interactivity in Structured Estimation
Without sparsity assumptions, it has been established that interactivity cannot improve the minimax rates of estimation under these information constraints.
Discrete Distribution Estimation under User-level Local Differential Privacy
Perhaps surprisingly, we show that in suitable parameter regimes, having $m$ samples per user is equivalent to having $m$ times more users, each with only one sample.
