12 citations · 55 across the 11 of their papers we have counts for
11 papers
Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares
Gavin Brown, Jonathan Hayase, Samuel Hopkins +5
We present a sample- and time-efficient differentially private algorithm for ordinary least squares, with error that depends linearly on the dimension and is independent of the con…
Near Optimal Private and Robust Linear Regression
Xiyang Liu, Prateek Jain, Weihao Kong +2
We study the canonical statistical estimation problem of linear regression from i.i.d.~examples under -differential privacy when some response variables are ad…
Machine Learning-Aided Efficient Decoding of Reed-Muller Subcodes
Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva +3
Reed-Muller (RM) codes achieve the capacity of general binary-input memoryless symmetric channels and are conjectured to have a comparable performance to that of random codes in te…
DP-PCA: Statistically Optimal and Differentially Private PCA
Xiyang Liu, Weihao Kong, Prateek Jain +1
We study the canonical statistical task of computing the principal component from i.i.d.~data in dimensions under -differential privacy. Although extensive…
Differential privacy and robust statistics in high dimensions
Xiyang Liu, Weihao Kong, Sewoong Oh
We introduce a universal framework for characterizing the statistical efficiency of a statistical estimation problem with differential privacy guarantees. Our framework, which we c…
KO codes: Inventing Nonlinear Encoding and Decoding for Reliable Wireless Communication via Deep-learning
Ashok Vardhan Makkuva, Xiyang Liu, Mohammad Vahid Jamali +3
Landmark codes underpin reliable physical layer communication, e.g., Reed-Muller, BCH, Convolution, Turbo, LDPC and Polar codes: each is a linear code and represents a mathematical…
Reed-Muller Subcodes: Machine Learning-Aided Design of Efficient Soft Recursive Decoding
Mohammad Vahid Jamali, Xiyang Liu, Ashok Vardhan Makkuva +3
Reed-Muller (RM) codes are conjectured to achieve the capacity of any binary-input memoryless symmetric (BMS) channel, and are observed to have a comparable performance to that of…
Robust and Differentially Private Mean Estimation
Xiyang Liu, Weihao Kong, Sham Kakade +1
In statistical learning and analysis from shared data, which is increasingly widely adopted in platforms such as federated learning and meta-learning, there are two major concerns:…
MACE: A Flexible Framework for Membership Privacy Estimation in Generative Models
Yixi Xu, Sumit Mukherjee, Xiyang Liu +3
Generative machine learning models are being increasingly viewed as a way to share sensitive data between institutions. While there has been work on developing differentially priva…
Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting
Xiyang Liu, Jie Yang, Wenrui Ding
The crowd counting task aims at estimating the number of people located in an image or a frame from videos. Existing methods widely adopt density maps as the training targets to op…
Minimax Rates of Estimating Approximate Differential Privacy
Xiyang Liu, Sewoong Oh
Differential privacy has become a widely accepted notion of privacy, leading to the introduction and deployment of numerous privatization mechanisms. However, ensuring the privacy…