检索结果-内蒙古大学图书馆

Convergent analysis of algebraic multigrid method with data-driven parameter learning for non-selfadjoint elliptic problems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Juan Luo, Junyue Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

In this paper, we apply the practical GADI-HS iteration as a smoother in algebraic multigrid (AMG) method for solving second-order non-selfadjoint elliptic problem. Additionally, we prove the convergence of the derived algorithm and introduce a data-driven parameter learing method called Gaussian process regression (GPR) to predict optimal parameters. Numerical experimental results show that using GPR to predict parameters can save a significant amount of time cost and approach the optimal parameters accurately. © 2024, CC BY.

关键词： Algebra

Decision mamba: reinforcement learning via hybrid selective sequence modeling 24

学校读者我要写书评

暂无评论

Decision mamba: reinforcement learning via hybrid selective ...

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Sili Huang Jifeng Hu Zhejian Yang Liwei Yang Tao Luo Hechang Chen Lichao Sun Bo Yang Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education and School of Artificial Intelligence Jilin University China School of Artificial Intelligence Jilin University China Institute of High Performance Computing Agency for Science Technology and Research Singapore Lehigh University Bethlehem Pennsylvania Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education

ISBN: (纸本)9798331314385

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement in online environments by providing task contexts, such as multiple trajectories, called in-context RL. However, due to the quadratic computation complexity of attention in transformers, current in-context RL methods suffer from huge computational costs as the task horizon increases. In contrast, the Mamba model is renowned for its efficient ability to process long-term dependencies, which provides an opportunity for in-context RL to solve tasks that require long-term memory. To this end, we first implement Decision Mamba (DM) by replacing the backbone of Decision Transformer (DT). Then, we propose a Decision Mamba-Hybrid (DM-H) with the merits of transformers and Mamba in high-quality prediction and long-term memory. Specifically, DM-H first generates high-value sub-goals from long-term memory through the Mamba model. Then, we use sub-goals to prompt the transformer, establishing high-quality predictions. Experimental results demonstrate that DM-H achieves state-of-the-art in long and short-term tasks, such as D4RL, Grid World, and Tmaze benchmarks. Regarding efficiency, the online testing of DM-H in the long-term task is 28× times faster than the transformer-based baselines.

关键词：

iManip: Skill-Incremental Learning for Robotic Manipulation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zheng, Zexin Cai, Jia-Feng Wu, Xiao-Ming Wei, Yi-Lin Tang, Yu-Ming Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The development of a generalist agent with adaptive multiple manipulation skills has been a long-standing goal in the robotics community. In this paper, we explore a crucial task, skill-incremental learning, in robotic manipulation, which is to endow the robots with the ability to learn new manipulation skills based on the previous learned knowledge without re-training. First, we build a skill-incremental environment based on the RLBench benchmark, and explore how traditional incremental methods perform in this setting. We find that they suffer from severe catastrophic forgetting due to the previous methods on classification overlooking the characteristics of temporality and action complexity in robotic manipulation tasks. Towards this end, we propose an incremental Manipulation framework, termed iManip, to mitigate the above issues. We firstly design a temporal replay strategy to maintain the integrity of old skills when learning new skill. Moreover, we propose the extendable PerceiverIO, consisting of an action prompt with extendable weight to adapt to new action primitives in new skill. Extensive experiments show that our framework performs well in Skill-Incremental Learning. Codes of the skill-incremental environment with our framework will be open-source. Copyright © 2025, The Authors. All rights reserved.

关键词： Robot learning

TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering 38

学校读者我要写书评

暂无评论

TFGDA: Exploring Topology and Feature Alignment in Semi-supe...

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Dan, Jun Liu, Weiming Xie, Chunfeng Yu, Hua Dong, Shunjie Tan, Yanchao Zhejiang University China Queen Mary University of London United Kingdom Dalian University of Technology China Shanghai Jiao Tong University China Fuzhou University China Engineering Research Center of Big Data Intelligence Ministry of Education China Fujian Key Laboratory of Network Computing and Intelligent Information Processing China

Semi-supervised graph domain adaptation, as a branch of graph transfer learning, aims to annotate unlabeled target graph nodes by utilizing transferable knowledge learned from a label-scarce source graph. However, most existing studies primarily concentrate on aligning feature distributions directly to extract domain-invariant features, while ignoring the utilization of the intrinsic structure information in graphs. Inspired by the significance of data structure information in enhancing models' generalization performance, this paper aims to investigate how to leverage the structure information to assist graph transfer learning. To this end, we propose an innovative framework called TFGDA. Specially, TFGDA employs a structure alignment strategy named STSA to encode graphs' topological structure information into the latent space, greatly facilitating the learning of transferable features. To achieve a stable alignment of feature distributions, we also introduce a SDA strategy to mitigate domain discrepancy on the sphere. Moreover, to address the overfitting issue caused by label scarcity, a simple but effective RNC strategy is devised to guide the discriminative clustering of unlabeled nodes. Experiments on various benchmarks demonstrate the superiority of TFGDA over SOTA methods. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

A virtual element method with IMEX-SAV scheme for the incompressible magnetohydrodynamics equations

学校读者我要写书评

暂无评论

arXiv 2024年

This paper proposes a virtual element method (VEM) combined with a second-order implicit-explicit scheme based on the scalar auxiliary variable (SAV) method for the incompressible magnetohydrodynamics (MHD) equations. We employ the BDF2 scheme for time discretization and a conservative VEM for spatial discretization, in which the mass conservation in the velocity field is kept by taking advantage of the virtual element method’s adaptability and its divergence-free characteristics. In our scheme, the nonlinear terms are handled explicitly using the SAV method, and the magnetic field is decoupled from the velocity and pressure. This decoupling only requires solving a sequence of linear systems with constant coefficient at each time step. The stability estimate of the fully discrete scheme is developed, demonstrating the scheme is unconditionally stable. Moreover, rigorous error estimates for the velocity and magnetic field are provided. Finally, numerical experiments are presented to verify the valid of theoretical analysis. © 2024, CC BY-NC-ND.

关键词： Discrete element methods

An Instance-Level Motion-Aware Graph Model for Multi-target Multi-camera Tracking

学校读者我要写书评

暂无评论

An Instance-Level Motion-Aware Graph Model for Multi-target ...

International Joint Conference on Neural Networks (IJCNN)

作者： Xiaotong Fan Huicheng Zheng School of Computer Science and Engineering Sun Yat-sen University China Guangdong Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Multi-target multi-camera tracking (MTMCT), focusing on inferring trajectory across multiple surveillance videos, is holding significant practical utility. While numerous studies aim to learn visual features robust to illumination variation, occlusions, and other issues, the spatio-temporal information within a multi-camera system is not explored sufficiently. Existing methods generally exploit coarse-grained spatio-temporal information by modeling the distribution of time intervals between cameras. However, they tend to neglect the specific motion state of individual objects, which may hinder accurate cross-camera association. In this paper, we introduce a novel motionaware graph (MAG) model designed to extract instance-level spatio-temporal information that aligns with visual features and seamlessly aggregate these two kinds of information within a unified graph framework for MTMCT. Specifically, we propose a motion encoder-decoder module that predicts spatio-temporal consistency scores between objects based on their instance-level motion states. These scores are then integrated with visual similarity scores to generate discriminative feature representations for data association via a graph attention mechanism. Experimental evaluations and ablation studies on the large-scale MTA dataset demonstrate the superiority of our proposed model.

关键词： Visualization Attention mechanisms Tracking Surveillance Neural networks Lighting Predictive models

BMDP:Blockchain-Based Multi-Cloud Storage Data Provenance 26

学校读者我要写书评

暂无评论

BMDP:Blockchain-Based Multi-Cloud Storage Data Provenance

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Wang, Feiyu Zhou, Jian-Tao Guo, Xu Inner Mongolia University College of Computer Science Inner Mongolia Hohhot China Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Engineering Research Center of Ecological Big Data Ministry of Education Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software China

ISBN: (纸本)9798350331684

In a multi-cloud storage system, provenance data records all operations and ownership during its lifecycle, which is critical for data security and audibility. However, recording provenance data also poses some challenging security and storage issues. In this paper, we present a secure and efficient multi-cloud storage data source scheme, BMDP. We use blockchain technology to ensure the secure storage of provenance data and design a smart contract to utilize the provenance data to ensure the proper operation of the multi-cloud storage system. Finally, we analyze the scheme's safety and do simulation experiments to show that the scheme has practicality. © 2023 IEEE.

关键词： Smart contract

Performance Verification of State Feedback H∞ State Molecular Controller Via Chemical Reaction Networks 5

学校读者我要写书评

暂无评论

Performance Verification of State Feedback H∞ State Molecul...

5th International Conference on Industrial Artificial Intelligence, IAI 2023

作者： Yao, Jingwang Wang, Xing'An Lv, Hui Li, Yang Zhang, Wujie Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China Dalian University College of Environmental and Chemical Engineering Dalian116622 China Dalian Chivy Biotechnology Co. Ltd Dalian116023 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110004 China

ISBN: (纸本)9798350325294

An important goal in synthetic biology is in the design and implementation of control strategies embedded in biochemical reaction systems to enable control of the process at the molecular level. The problem of set-point tracking and perturbation disturbances in the biochemical reaction process can be solved by a state feedback control strategy and a more stable and better dynamic performance of synthetic controllers. First, it is shown how a set of CRNs can provide state feedback to the biomolecular implementation of the H∞ controller. Then, to facilitate the modularity of biochemical process design, CRNs of trigonometric functions and repetitive sequence step signals are defined for the first time as input signals to the controller. Finally, numerical simulation experiments are designed to verify the effectiveness of the whole scheme from several perspectives, such as setpoint tracking and external perturbations. The results show that the state feedback H∞ molecular controller outperforms the conventional linear controller because it has a faster tracking response and better perturbation rejection performance. © 2023 IEEE.

关键词： Controllers

A NEURAL MULTIGRID SOLVER FOR HELMHOLTZ EQUATIONS WITH HIGH WAVENUMBER AND HETEROGENEOUS MEDIA

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cui, Chen Jiang, Kai Shu, Shi Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

Solving high-wavenumber and heterogeneous Helmholtz equations presents a longstanding challenge in scientific computing. In this paper, we introduce a deep learning-enhanced multigrid solver to address this issue. By conducting error analysis on standard multigrid applied to a discrete Helmholtz equation, we devise a strategy to handle errors with different frequencies separately. For error components with frequencies distant from the wavenumber, we perform simple smoothing based on local operations at different levels to eliminate them. On the other hand, to address error components with frequencies near the wavenumber, we utilize another multigrid V-cycle to solve an advection-diffusion-reaction (ADR) equation at a coarse scale. The resulting solver, named Wave-ADR-NS, involves parameters learned through unsupervised training. Numerical results demonstrate that Wave-ADR-NS effectively resolves heterogeneous 2D Helmholtz equation with wavenumber up to 2000. Comparative experiments against classical multigrid preconditioners and existing deep learning-based multigrid preconditioners reveals the superior performance of *** Codes 65N22, 65N55, 68T07 Copyright © 2024, The Authors. All rights reserved.

关键词： Helmholtz equation