no code implementations • 27 Dec 2023 • Zhaisheng Ding, Haiyan Li, Ruichao Hou, Yanyu Liu, Shidong Xie, Dongming Zhou, Jinde Cao
Learning robust multi-modal feature representations is critical for boosting tracking performance.
no code implementations • 19 Dec 2023 • Luyao Guo, Luqing Wang, Xinli Shi, Jinde Cao
Distributed optimization methods with probabilistic local updates have recently gained attention for their provable ability to communication acceleration.
no code implementations • 12 Oct 2023 • Luyao Guo, Sulaiman A. Alghunaim, Kun Yuan, Laurent Condat, Jinde Cao
We demonstrate that the leading communication complexity of ProxSkip is $\mathcal{O}\left(\frac{p\sigma^2}{n\epsilon^2}\right)$ for non-convex and convex settings, and $\mathcal{O}\left(\frac{p\sigma^2}{n\epsilon}\right)$ for the strongly convex setting, where $n$ represents the number of nodes, $p$ denotes the probability of communication, $\sigma^2$ signifies the level of stochastic noise, and $\epsilon$ denotes the desired accuracy level.
no code implementations • 11 May 2023 • Zhuoxuan Li, Iakov Korovin, Xinli Shi, Sergey Gorbachev, Nadezhda Gorbacheva, Wei Huang, Jinde Cao
Rutting of asphalt pavements is a crucial design criterion in various pavement design guides.
no code implementations • 7 Feb 2023 • Luyao Guo, Xinli Shi, Jinde Cao, ZiHao Wang
The proposed algorithm uses uncoordinated network-independent constant stepsizes and only needs to approximately solve a sequence of proximal mappings, which is advantageous for solving decentralized composite optimization problems where the proximal mappings of the nonsmooth loss functions may not have analytical solutions.
no code implementations • 6 Dec 2022 • Luyao Guo, Jinde Cao, Xinli Shi, Shaofu Yang
In this paper, we propose a novel primal-dual proximal splitting algorithm (PD-PSA), named BALPA, for the composite optimization problem with equality constraints, where the loss function consists of a smooth term and a nonsmooth term composed with a linear mapping.
1 code implementation • 26 Oct 2022 • Jiebao Zhang, Wenhua Qian, Rencan Nie, Jinde Cao, Dan Xu
We study the attack performance and computation cost of the attack method based on the Hessian with a limited number of perturbation pixels.
no code implementations • 5 Sep 2022 • Luyao Guo, Xinli Shi, Shaofu Yang, Jinde Cao
In this paper, we propose a novel Dual Inexact Splitting Algorithm (DISA) for distributed convex composite optimization problems, where the local loss function consists of a smooth term and a possibly nonsmooth term composed with a linear mapping.
1 code implementation • 12 Jul 2022 • Jiebao Zhang, Wenhua Qian, Rencan Nie, Jinde Cao, Dan Xu
Adversarial training is a simple and effective defense method to improve the robustness of CNNs to adversarial examples.
no code implementations • 15 Mar 2022 • Shiyong Zhu, Jianquan Lu, Liangjie Sun, Jinde Cao
In this article, we design the distributed pinning controllers to globally stabilize a Boolean network (BN), specially a sparsely connected large-scale one, towards a preassigned subset of state space through the node-to-node message exchange.
no code implementations • 29 Jun 2021 • Shiyong Zhu, Jianquan Lu, Daniel W. C. Ho, Jinde Cao
Further, two minimum realization strategies are considered to induce an SOG from an arbitrarily given digraph by marking and controlling the minimal vertices, respectively.
no code implementations • 12 Jan 2021 • Shaosheng Xu, Jinde Cao, Yichao Cao, Tong Wang
As gradient descent method in deep learning causes a series of questions, this paper proposes a novel gradient-free deep learning structure.
2 code implementations • 10 Nov 2020 • Yichao Cao, Qingfei Tang, Xiaobo Lu, Fan Li, Jinde Cao
To overcome these problems, a novel Spatio-Temporal Cross Network (STCNet) is proposed to recognize industrial smoke emissions.
no code implementations • 13 Jul 2020 • Paweł Staszewski, Maciej Jaworski, Jinde Cao, Leszek Rutkowski
The idea of neural codes, based on fully connected layers activations, is extended by incorporating the information contained in convolutional layers.
no code implementations • 7 Dec 2019 • Lin Lin, Jinde Cao, Jianquan Lu, Jie Zhong
Owing to the stochasticity, the uniform state feedback controllers, which is independent of switching signal, might be out of work.
no code implementations • 5 Dec 2019 • Shiyong Zhu, Jianquan Lu, Jie Zhong, Yang Liu, Jinde Cao
In this paper, a set of sensors is constructed via the pinning observability approach with the help of observability criteria given in [1] and [2], in order to make the given Boolean network (BN) be observable.