• Publications
  • Influence
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
In this paper, we employ adversarial training to improve the performance of randomized smoothing. Expand
Randomized Smoothing of All Shapes and Sizes
We propose a novel framework for devising and analyzing randomized smoothing schemes, and validate its effectiveness in practice. Expand
Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detection
We study two problems in high-dimensional robust statistics: \emph{robust mean estimation} and \emph{outlier detection}. In robust mean estimation the goal is to estimate the mean $\mu$ of aExpand
Quantum communication in distributed wireless sensor networks
In the wireless sensor networks (WSNs), sensor nodes may be deployed in hostile areas. Expand
QSGD: Communication-Optimal Stochastic Gradient Descent, with Applications to Training Neural Networks
We propose Quantized SGD (QSGD), a family of compression schemes which allow the compression of gradient updates at each node, while guaranteeing convergence under standard assumptions. Expand
Development of a GHG-mitigation oriented inexact dynamic model for regional energy system management
Multiple dynamics and uncertainties are involved in regional energy and greenhouse gas management (REGM) system, confronting decision makers during plan/policy makings. In this study, a greenhouseExpand
Learning Structured Distributions From Untrusted Batches: Faster and Simpler
We revisit the problem of learning from untrusted batches introduced by Qiao and Valiant [QV17]. Expand
Improved IPsec performance utilizing transport-layer-aware compression architecture
We propose a transport-layer-aware header/payload compression mechanism for improving the security of UDP/RTP and TCP packets over IPv6 networks whilst simultaneously preserving the network performance. Expand