Po-Ling Loh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Po-Ling Loh has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Ankit Pensia
Carnegie Mellon University
9 shared publications - Varun Jog
Department of Pure Mathematics and Mathematical Statistics, University of Cambridge, Cambridge, U.K.
9 shared publications Varun Jog
Department of Pure Mathematics and Mathematical Statistics, University of Cambridge
5 shared publications- Varun Jog
Department of Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA
4 shared publications - Varun Jog
Department of Electrical & Computer Engineering University of Wisconsin -Madison 53706 Madison WI
3 shared publications - Xiaomin Zhang
Department of Computer Sciences, University of Wisconsin-Madison, Madison, USA
3 shared publications
Latest Publications
- Open Access
On the Benefits of Accelerated Optimization in Robust and Private Estimation
We study the advantages of accelerated gradient methods, specifically based on the Frank-Wolfe method and projected gradient descent, for privacy and heavy-tailed robustness. Our approaches are as follows: For the Frank-Wolfe method, our technique is based on a tailored learning rate and a uniform lower bound on the gradient of the $\ell_2$-norm over the constraint set. For accelerating projected gradient descent, we use the popular variant based on Nesterov's momentum, and we optimize our objective over $\mathbb{R}^p$. These accelerations reduce iteration complexity, translating into stronger statistical guarantees for empirical and population risk minimization. Our analysis covers three settings: non-random data, random model-free data, and parametric models (linear regression and generalized linear models). Methodologically, we approach both privacy and robustness based on noisy gradients. We ensure differential privacy via the Gaussian mechanism and advanced composition, and we achieve heavy-tailed robustness using a geometric median-of-means estimator, which also sharpens the dependency on the dimension of the covariates. Finally, we compare our rates to existing bounds and identify scenarios where our methods attain optimal convergence.Open AccessOn the Benefits of Accelerated Optimization in Robust and Private Estimation
We study the advantages of accelerated gradient methods, specifically based on the Frank-Wolfe method and projected gradient descent, for privacy and heavy-tailed robustness. Our approaches are as follows: For the Frank-Wolfe method, our technique is based on a tailored learning rate and a uniform lower bound on the gradient of the $\ell_2$-norm over the constraint set. For accelerating projected gradient descent, we use the popular variant based on Nesterov's momentum, and we optimize our objective over $\mathbb{R}^p$. These accelerations reduce iteration complexity, translating into stronger statistical guarantees for empirical and population risk minimization. Our analysis covers three settings: non-random data, random model-free data, and parametric models (linear regression and generalized linear models). Methodologically, we approach both privacy and robustness based on noisy gradients. We ensure differential privacy via the Gaussian mechanism and advanced composition, and we achieve heavy-tailed robustness using a geometric median-of-means estimator, which also sharpens the dependency on the dimension of the covariates. Finally, we compare our rates to existing bounds and identify scenarios where our methods attain optimal convergence. - Top Cited PapersOpen Access
- 7 March 2025
- Published by Annual Reviews in Annual Review of Statistics and Its Application
- Vol. 12 (1) , 477-496
A Theoretical Review of Modern Robust Statistics
Robust statistics is a fairly mature field that dates back to the early 1960s, with many foundational concepts having been developed in the ensuing decades. However, the field has drawn a new surge of attention in the past decade, largely due to a desire to recast robust statistical principles in the context of high-dimensional statistics. In this article, we begin by reviewing some of the central ideas in classical robust statistics. We then discuss the need for new theory in high dimensions, using recent work in high-dimensional M -estimation as an illustrative example. Next, we highlight a variety of interesting recent topics that have drawn a flurry of research activity from both statisticians and theoretical computer scientists, demonstrating the need for further research in robust estimation that embraces new estimation and contamination settings, as well as a greater emphasis on computational tractability in high dimensions.
- 7 March 2025
- Published by Annual Reviews in Annual Review of Statistics and Its Application
- Vol. 12 (1) , 477-496
Top Cited PapersOpen AccessA Theoretical Review of Modern Robust Statistics
Robust statistics is a fairly mature field that dates back to the early 1960s, with many foundational concepts having been developed in the ensuing decades. However, the field has drawn a new surge of attention in the past decade, largely due to a desire to recast robust statistical principles in the context of high-dimensional statistics. In this article, we begin by reviewing some of the central ideas in classical robust statistics. We then discuss the need for new theory in high dimensions, using recent work in high-dimensional M -estimation as an illustrative example. Next, we highlight a variety of interesting recent topics that have drawn a flurry of research activity from both statisticians and theoretical computer scientists, demonstrating the need for further research in robust estimation that embraces new estimation and contamination settings, as well as a greater emphasis on computational tractability in high dimensions.
- Top Cited Papers
- 8 October 2024
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 120 (550) , 1002-1013
Robust Regression with Covariate Filtering: Heavy Tails and Adversarial Contamination
- 8 October 2024
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 120 (550) , 1002-1013
Top Cited PapersRobust Regression with Covariate Filtering: Heavy Tails and Adversarial Contamination
- 16 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 71 (1) , 592-617
Simple Binary Hypothesis Testing Under Local Differential Privacy and Communication Constraints
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 optimal: the former hold for the set of distribution pairs with prescribed Hellinger divergence and total variation distance, whereas the latter hold for specific distribution pairs. For the sample complexity of simple hypothesis testing under pure LDP constraints, we establish instance-optimal bounds for distributions with binary support; minimax-optimal bounds for general distributions; and (approximately) instance-optimal, computationally efficient algorithms for general distributions. When both privacy and communication constraints are present, we develop instance-optimal, computationally efficient algorithms that achieve the minimum possible sample complexity (up to universal constants). Our results on instance-optimal algorithms hinge on identifying the extreme points of the joint range set $\mathcal {A}$ of two distributions p and q , defined as $\mathcal {A}:= \{(\vec {T} p, \vec {T} q) | \vec {T}\in \mathcal {C}\}$ , where $\mathcal {C}$ is the set of channels characterizing the constraints.
- 16 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 71 (1) , 592-617
Simple Binary Hypothesis Testing Under Local Differential Privacy and Communication Constraints
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 optimal: the former hold for the set of distribution pairs with prescribed Hellinger divergence and total variation distance, whereas the latter hold for specific distribution pairs. For the sample complexity of simple hypothesis testing under pure LDP constraints, we establish instance-optimal bounds for distributions with binary support; minimax-optimal bounds for general distributions; and (approximately) instance-optimal, computationally efficient algorithms for general distributions. When both privacy and communication constraints are present, we develop instance-optimal, computationally efficient algorithms that achieve the minimum possible sample complexity (up to universal constants). Our results on instance-optimal algorithms hinge on identifying the extreme points of the joint range set $\mathcal {A}$ of two distributions p and q , defined as $\mathcal {A}:= \{(\vec {T} p, \vec {T} q) | \vec {T}\in \mathcal {C}\}$ , where $\mathcal {C}$ is the set of channels characterizing the constraints.
- Open Access
- 13 August 2024
- Published by IOP Publishing in Biomedical Physics & Engineering Express
- Vol. 10 (5) , 055029
RobMedNAS: searching robust neural network architectures for medical image synthesis
Investigating U-Net model robustness in medical image synthesis against adversarial perturbations, this study introduces RobMedNAS, a neural architecture search strategy for identifying resilient U-Net configurations. Through retrospective analysis of synthesized CT from MRI data, employing Dice coefficient and mean absolute error metrics across critical anatomical areas, the study evaluates traditional U-Net models and RobMedNAS-optimized models under adversarial attacks. Findings demonstrate RobMedNAS’s efficacy in enhancing U-Net resilience without compromising on accuracy, proposing a novel pathway for robust medical image processing.
- 13 August 2024
- Published by IOP Publishing in Biomedical Physics & Engineering Express
- Vol. 10 (5) , 055029
Open AccessRobMedNAS: searching robust neural network architectures for medical image synthesis
Investigating U-Net model robustness in medical image synthesis against adversarial perturbations, this study introduces RobMedNAS, a neural architecture search strategy for identifying resilient U-Net configurations. Through retrospective analysis of synthesized CT from MRI data, employing Dice coefficient and mean absolute error metrics across critical anatomical areas, the study evaluates traditional U-Net models and RobMedNAS-optimized models under adversarial attacks. Findings demonstrate RobMedNAS’s efficacy in enhancing U-Net resilience without compromising on accuracy, proposing a novel pathway for robust medical image processing.
- Open Access
On Differentially Private U Statistics
We consider the problem of privately estimating a parameter $\mathbb{E}[h(X_1,\dots,X_k)]$, where $X_1$, $X_2$, $\dots$, $X_k$ are i.i.d. data from some distribution and $h$ is a permutation-invariant function. Without privacy constraints, standard estimators are U-statistics, which commonly arise in a wide range of problems, including nonparametric signed rank tests, symmetry testing, uniformity testing, and subgraph counts in random networks, and can be shown to be minimum variance unbiased estimators under mild conditions. Despite the recent outpouring of interest in private mean estimation, privatizing U-statistics has received little attention. While existing private mean estimation algorithms can be applied to obtain confidence intervals, we show that they can lead to suboptimal private error, e.g., constant-factor inflation in the leading term, or even $Θ(1/n)$ rather than $O(1/n^2)$ in degenerate settings. To remedy this, we propose a new thresholding-based approach using \emph{local Hájek projections} to reweight different subsets of the data. This leads to nearly optimal private error for non-degenerate U-statistics and a strong indication of near-optimality for degenerate U-statistics.Open AccessOn Differentially Private U Statistics
We consider the problem of privately estimating a parameter $\mathbb{E}[h(X_1,\dots,X_k)]$, where $X_1$, $X_2$, $\dots$, $X_k$ are i.i.d. data from some distribution and $h$ is a permutation-invariant function. Without privacy constraints, standard estimators are U-statistics, which commonly arise in a wide range of problems, including nonparametric signed rank tests, symmetry testing, uniformity testing, and subgraph counts in random networks, and can be shown to be minimum variance unbiased estimators under mild conditions. Despite the recent outpouring of interest in private mean estimation, privatizing U-statistics has received little attention. While existing private mean estimation algorithms can be applied to obtain confidence intervals, we show that they can lead to suboptimal private error, e.g., constant-factor inflation in the leading term, or even $Θ(1/n)$ rather than $O(1/n^2)$ in degenerate settings. To remedy this, we propose a new thresholding-based approach using \emph{local Hájek projections} to reweight different subsets of the data. This leads to nearly optimal private error for non-degenerate U-statistics and a strong indication of near-optimality for degenerate U-statistics. - Open Access
- 4 June 2024
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 86 (4)
Proposers of the vote of thanks to Crane and Xu and contribution to the discussion of “Root and community inference on the latent growth process of a network”
Varun Jog, Po-Ling Loh; Proposers of the vote of thanks to Crane and Xu and contribution to the discussion of “Root and community inference on the latent g
- 4 June 2024
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 86 (4)
Open AccessProposers of the vote of thanks to Crane and Xu and contribution to the discussion of “Root and community inference on the latent growth process of a network”
Varun Jog, Po-Ling Loh; Proposers of the vote of thanks to Crane and Xu and contribution to the discussion of “Root and community inference on the latent g
- Open Access
Differentially Private Synthetic Data with Private Density Estimation
The need to analyze sensitive data, such as medical records or financial data, has created a critical research challenge in recent years. In this paper, we adopt the framework of differential privacy, and explore mechanisms for generating an entire dataset which accurately captures characteristics of the original data. We build upon the work of Boedihardjo et al, which laid the foundations for a new optimization-based algorithm for generating private synthetic data. Importantly, we adapt their algorithm by replacing a uniform sampling step with a private distribution estimator; this allows us to obtain better computational guarantees for discrete distributions, and develop a novel algorithm suitable for continuous distributions. We also explore applications of our work to several statistical tasks.
Open AccessDifferentially Private Synthetic Data with Private Density Estimation
The need to analyze sensitive data, such as medical records or financial data, has created a critical research challenge in recent years. In this paper, we adopt the framework of differential privacy, and explore mechanisms for generating an entire dataset which accurately captures characteristics of the original data. We build upon the work of Boedihardjo et al, which laid the foundations for a new optimization-based algorithm for generating private synthetic data. Importantly, we adapt their algorithm by replacing a uniform sampling step with a private distribution estimator; this allows us to obtain better computational guarantees for discrete distributions, and develop a novel algorithm suitable for continuous distributions. We also explore applications of our work to several statistical tasks.
- Open Access
- 16 April 2024
- Published by Elsevier in Journal of Statistical Planning and Inference
- Vol. 233
Entropic regularization of neural networks: Self-similar approximations
- 16 April 2024
- Published by Elsevier in Journal of Statistical Planning and Inference
- Vol. 233
Open AccessEntropic regularization of neural networks: Self-similar approximations