551 citations · 1.1k across the 33 of their papers we have counts for
39 papers
The Sample Complexity of Simple Binary Hypothesis Testing
Ankit Pensia, Varun Jog, Po-Ling Loh
The sample complexity of simple binary hypothesis testing is the smallest number of i.i.d.\ samples required to distinguish between two distributions and in either: (i) the…
Robust empirical risk minimization via Newton's method
Eirini Ioannou, Muni Sreenivas Pydi, Po-Ling Loh
A new variant of Newton's method for empirical risk minimization is studied, where at each iteration of the optimization algorithm, the gradient and Hessian of the objective functi…
Simple Binary Hypothesis Testing under Local Differential Privacy and Communication Constraints
Ankit Pensia, Amir R. Asadi, Varun Jog +1
We study simple binary hypothesis testing under both local differential privacy (LDP) and communication constraints. We qualify our results as either minimax optimal or instance op…
Communication-constrained hypothesis testing: Optimality, robustness, and reverse data processing inequalities
Ankit Pensia, Varun Jog, Po-Ling Loh
We study hypothesis testing under communication constraints, where each sample is quantized before being revealed to a statistician. Without communication constraints, it is well k…
On the identifiability of mixtures of ranking models
Xiaomin Zhang, Xucheng Zhang, Po-Ling Loh +1
Mixtures of ranking models are standard tools for ranking problems. However, even the fundamental question of parameter identifiability is not fully understood: the identifiability…
Differentially private inference via noisy optimization
Marco Avella-Medina, Casey Bradshaw, Po-Ling Loh
We propose a general optimization-based framework for computing differentially private M-estimators and a new method for constructing differentially private confidence regions. Fir…
Robust W-GAN-Based Estimation Under Wasserstein Contamination
Zheng Liu, Po-Ling Loh
Robust estimation is an important problem in statistics which aims at providing a reasonable estimator when the data-generating distribution lies within an appropriately defined ba…
Robust regression with covariate filtering: Heavy tails and adversarial contamination
Ankit Pensia, Varun Jog, Po-Ling Loh
We study the problem of linear regression where both covariates and responses are potentially (i) heavy-tailed and (ii) adversarially contaminated. Several computationally efficien…
Provable Training Set Debugging for Linear Regression
Xiaomin Zhang, Xiaojin Zhu, Po-Ling Loh
We investigate problems in penalized -estimation, inspired by applications in machine learning debugging. Data are collected from two pools, one containing data with possibly co…
Boosting Algorithms for Estimating Optimal Individualized Treatment Rules
Duzhe Wang, Haoda Fu, Po-Ling Loh
We present nonparametric algorithms for estimating optimal individualized treatment rules. The proposed algorithms are based on the XGBoost algorithm, which is known as one of the…
Adaptive Estimation and Statistical Inference for High-Dimensional Graph-Based Linear Models
Duzhe Wang, Po-Ling Loh
We consider adaptive estimation and statistical inference for high-dimensional graph-based linear models. In our model, the coordinates of regression coefficients correspond to an…
Extracting robust and accurate features via a robust information bottleneck
Ankit Pensia, Varun Jog, Po-Ling Loh
We propose a novel strategy for extracting features in supervised learning that can be used to construct a classifier which is more robust to small perturbations in the input space…
Robustifying deep networks for image segmentation
Zheng Liu, Jinnian Zhang, Varun Jog +2
Purpose: The purpose of this study is to investigate the robustness of a commonly-used convolutional neural network for image segmentation with respect to visually-subtle adversari…
Estimating location parameters in entangled single-sample distributions
Ankit Pensia, Varun Jog, Po-Ling Loh
We consider the problem of estimating the common mean of independently sampled data, where samples are drawn in a possibly non-identical manner from symmetric, unimodal distributio…
Does Data Augmentation Lead to Positive Margin?
Shashank Rajput, Zhili Feng, Zachary Charles +2
Data augmentation (DA) is commonly used during model training, as it significantly improves test error and model robustness. DA artificially expands the training set by applying ra…
Scale calibration for high-dimensional robust regression
Po-Ling Loh
We present a new method for high-dimensional linear regression when a scale parameter of the additive errors is unknown. The proposed estimator is based on a penalized Huber -es…
Adversarial Risk Bounds via Function Transformation
Justin Khim, Po-Ling Loh
We derive bounds for a notion of adversarial risk, designed to characterize the robustness of linear and neural network classifiers to adversarial perturbations. Specifically, we i…
A theory of maximum likelihood for weighted infection graphs
Justin Khim, Po-Ling Loh
We study the problem of parameter estimation based on infection data from an epidemic outbreak on a graph. We assume that successive infections occur via contagion; i.e., transmiss…
Online learning with graph-structured feedback against adaptive adversaries
Zhili Feng, Po-Ling Loh
We derive upper and lower bounds for the policy regret of -round online learning problems with graph-structured feedback, where the adversary is nonoblivious but assumed to have…
Graph-Based Ascent Algorithms for Function Maximization
Muni Sreenivas Pydi, Varun Jog, Po-Ling Loh
We study the problem of finding the maximum of a function defined on the nodes of a connected graph. The goal is to identify a node where the function obtains its maximum. We focus…
Generalization Error Bounds for Noisy, Iterative Algorithms
Ankit Pensia, Varun Jog, Po-Ling Loh
In statistical learning theory, generalization error is used to quantify the degree to which a supervised machine learning algorithm may overfit to training data. Recent work [Xu a…
Optimal Rates for Community Estimation in the Weighted Stochastic Block Model
Min Xu, Varun Jog, Po-Ling Loh
Community identification in a network is an important problem in fields such as social science, neuroscience, and genetics. Over the past decade, stochastic block models (SBMs) hav…
Permutation Tests for Infection Graphs
Justin Khim, Po-Ling Loh
We formulate and analyze a novel hypothesis testing problem for inferring the edge structure of an infection graph. In our model, a disease spreads over a network via contagion or…
Information and estimation in Fokker-Planck channels
Andre Wibisono, Varun Jog, Po-Ling Loh
We study the relationship between information- and estimation-theoretic quantities in time-evolving systems. We focus on the Fokker-Planck channel defined by a general stochastic d…