61 citations · 88 across the 13 of their papers we have counts for
13 papers
Deep Semi-supervised Learning with Double-Contrast of Features and Semantics
Quan Feng, Jiayu Yao, Zhison Pan +1
In recent years, the field of intelligent transportation systems (ITS) has achieved remarkable success, which is mainly due to the large amount of available annotation data. Howeve…
Provable Acceleration of Nesterov's Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks
Xin Liu, Wei Tao, Wei Li +3
Due to its simplicity and efficiency, the first-order gradient method has been extensively employed in training neural networks. Although the optimization problem of the neural net…
A Convergence Analysis of Nesterov's Accelerated Gradient Method in Training Deep Linear Neural Networks
Xin Liu, Wei Tao, Zhisong Pan
Momentum methods, including heavy-ball~(HB) and Nesterov's accelerated gradient~(NAG), are widely used in training neural networks for their fast convergence. However, there is a l…
Adversarial Attack via Dual-Stage Network Erosion
Yexin Duan, Junhua Zou, Xingyu Zhou +3
Deep neural networks are vulnerable to adversarial examples, which can fool deep models by adding subtle perturbations. Although existing attacks have achieved promising results, i…
Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting
Junhua Zou, Zhisong Pan, Junyang Qiu +3
We introduce a three stage pipeline: resized-diverse-inputs (RDIM), diversity-ensemble (DEM) and region fitting, that work together to generate transferable adversarial examples. W…
Learning Coated Adversarial Camouflages for Object Detectors
Yexin Duan, Jialin Chen, Xingyu Zhou +5
An adversary can fool deep neural network object detectors by generating adversarial noises. Most of the existing works focus on learning local visible noises in an adversarial "pa…
Provable Convergence of Nesterov's Accelerated Gradient Method for Over-Parameterized Neural Networks
Xin Liu, Zhisong Pan, Wei Tao
Momentum methods, such as heavy ball method~(HB) and Nesterov's accelerated gradient method~(NAG), have been widely used in training neural networks by incorporating the history of…
Gradient Descent Averaging and Primal-dual Averaging for Strongly Convex Optimization
Wei Tao, Wei Li, Zhisong Pan +1
Averaging scheme has attracted extensive attention in deep learning as well as traditional machine learning. It achieves theoretically optimal convergence and also improves the emp…
Weakness Analysis of Cyberspace Configuration Based on Reinforcement Learning
Lei Zhang, Wei Bai, Shize Guo +3
In this work, we present a learning-based approach to analysis cyberspace configuration. Unlike prior methods, our approach has the ability to learn from past experience and improv…
Making Adversarial Examples More Transferable and Indistinguishable
Junhua Zou, Yexin Duan, Boyu Li +3
Fast gradient sign attack series are popular methods that are used to generate adversarial examples. However, most of the approaches based on fast gradient sign attack series canno…
The Strength of Nesterov's Extrapolation in the Individual Convergence of Nonsmooth Optimization
W. Tao, Z. Pan, G. Wu +1
The extrapolation strategy raised by Nesterov, which can accelerate the convergence rate of gradient descent methods by orders of magnitude when dealing with smooth convex objectiv…
MODA: MOdule Differential Analysis for weighted gene co-expression network
Dong Li, James B. Brown, Luisa Orsini +3
Gene co-expression network differential analysis is designed to help biologists understand gene expression patterns under different condition. By comparing different gene co-expres…
Multi-task Feature Selection based Anomaly Detection
Longqi Yang, Yibing Wang, Zhisong Pan +1
Network anomaly detection is still a vibrant research area. As the fast growth of network bandwidth and the tremendous traffic on the network, there arises an extremely challengeab…