arXiv subjects

Jinhu Lu

Publications and source records attributed to Jinhu Lu.

11 recordsLinked to original sources

arXiv2025

Composite Learning Adaptive Control under Non-Persistent Partial Excitation

This paper focuses on relaxing the excitation conditions for the adaptive control of uncertain nonlinear systems. By adopting the spectral decomposition technique, a linear regression equation (LRE) is constructed to quantitatively collect historical excitation information, based on which the parameter estimation error is decomposed into the excited component and the unexcited component. By sufficiently utilizing the collected excitation information, the composite learning and μ-modification terms are designed and incorporated into the "Lyapunov-based" parameter update law. By developing a novel Lyapunov function, it is demonstrated that under non-persistent partial excitation, the control error and the excited parameter estimation error component converge to zero, while the unexcited component remains bounded. Furthermore, the proposed adaptive control scheme can effectively eliminate the effects of parametric uncertainties and enhance the robustness of the closed-loop systems. Simulation results are provided to verify the theoretical findings.

eess.SY↗

arXiv2025

Bidirectional Task-Motion Planning Based on Hierarchical Reinforcement Learning for Strategic Confrontation

In swarm robotics, confrontation scenarios, including strategic confrontations, require efficient decision-making that integrates discrete commands and continuous actions. Traditional task and motion planning methods separate decision-making into two layers, but their unidirectional structure fails to capture the interdependence between these layers, limiting adaptability in dynamic environments. Here, we propose a novel bidirectional approach based on hierarchical reinforcement learning, enabling dynamic interaction between the layers. This method effectively maps commands to task allocation and actions to path planning, while leveraging cross-training techniques to enhance learning across the hierarchical framework. Furthermore, we introduce a trajectory prediction model that bridges abstract task representations with actionable planning goals. In our experiments, it achieves over 80% in confrontation win rate and under 0.01 seconds in decision time, outperforming existing approaches. Demonstrations through large-scale tests and real-world robot experiments further emphasize the generalization capabilities and practical applicability of our method.

cs.RO↗

arXiv2024

DELRec: Distilling Sequential Pattern to Enhance LLMs-based Sequential Recommendation

Sequential recommendation (SR) tasks aim to predict users' next interaction by learning their behavior sequence and capturing the connection between users' past interactions and their changing preferences. Conventional SR models often focus solely on capturing sequential patterns within the training data, neglecting the broader context and semantic information embedded in item titles from external sources. This limits their predictive power and adaptability. Large language models (LLMs) have recently shown promise in SR tasks due to their advanced understanding capabilities and strong generalization abilities. Researchers have attempted to enhance LLMs-based recommendation performance by incorporating information from conventional SR models. However, previous approaches have encountered problems such as 1) limited textual information leading to poor recommendation performance, 2) incomplete understanding and utilization of conventional SR model information by LLMs, and 3) excessive complexity and low interpretability of LLMs-based methods. To improve the performance of LLMs-based SR, we propose a novel framework, Distilling Sequential Pattern to Enhance LLMs-based Sequential Recommendation (DELRec), which aims to extract knowledge from conventional SR models and enable LLMs to easily comprehend and utilize the extracted knowledge for more effective SRs. DELRec consists of two main stages: 1) Distill Pattern from Conventional SR Models, focusing on extracting behavioral patterns exhibited by conventional SR models using soft prompts through two well-designed strategies; 2) LLMs-based Sequential Recommendation, aiming to fine-tune LLMs to effectively use the distilled auxiliary information to perform SR tasks. Extensive experimental results conducted on four real datasets validate the effectiveness of the DELRec framework.

cs.IR↗

arXiv2024

Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence

The semi-supervised learning (SSL) strategy in lightweight models requires reducing annotated samples and facilitating cost-effective inference. However, the constraint on model parameters, imposed by the scarcity of training labels, limits the SSL performance. In this paper, we introduce PS-NET, a novel framework tailored for semi-supervised text mining with lightweight models. PS-NET incorporates online distillation to train lightweight student models by imitating the Teacher model. It also integrates an ensemble of student peers that collaboratively instruct each other. Additionally, PS-NET implements a constant adversarial perturbation schema to further self-augmentation by progressive generalizing. Our PS-NET, equipped with a 2-layer distilled BERT, exhibits notable performance enhancements over SOTA lightweight SSL frameworks of FLiText and DisCo in SSL text classification with extremely rare labelled data.

cs.CL↗

arXiv2023

Q-DETR: An Efficient Low-Bit Quantized Detection Transformer

The recent detection transformer (DETR) has advanced object detection, but its application on resource-constrained devices requires massive computation and memory resources. Quantization stands out as a solution by representing the network in low-bit parameters and operations. However, there is a significant performance drop when performing low-bit quantized DETR (Q-DETR) with existing quantization methods. We find that the bottlenecks of Q-DETR come from the query information distortion through our empirical analyses. This paper addresses this problem based on a distribution rectification distillation (DRD). We formulate our DRD as a bi-level optimization problem, which can be derived by generalizing the information bottleneck (IB) principle to the learning of Q-DETR. At the inner level, we conduct a distribution alignment for the queries to maximize the self-information entropy. At the upper level, we introduce a new foreground-aware query matching scheme to effectively transfer the teacher information to distillation-desired features to minimize the conditional information entropy. Extensive experimental results show that our method performs much better than prior arts. For example, the 4-bit Q-DETR can theoretically accelerate DETR with ResNet-50 backbone by 6.6x and achieve 39.4% AP, with only 2.6% performance gaps than its real-valued counterpart on the COCO dataset.

cs.CV↗

arXiv2022

A Nesterov's Accelerated Projected Gradient Method for Monotone Variational Inequalities

In this technical note, we are concerned with the problem of solving variational inequalities with improved convergence rates. Motivated by Nesterov's accelerated gradient method for convex optimization, we propose a Nesterov's accelerated projected gradient algorithm for variational inequality problems. We prove convergence of the proposed algorithm with at least linear rate under the common assumption of Lipschitz continuity and strongly monotonicity. To the best of our knowledge, this is the first time that convergence of the Nesterov's accelerated protocol is proved for variational inequalities, other than the convex optimization or monotone inclusion problems. Simulation results are given to demonstrate the outperformance of the proposed algorithms over the well-known projected gradient approach, the reflected projected approach, and the golden ratio method. It is shown that the required number of iterations to reach the solution is greatly reduced in our proposed algorithm.

math.OC↗

arXiv2021

Learning to Optimize Industry-Scale Dynamic Pickup and Delivery Problems

The Dynamic Pickup and Delivery Problem (DPDP) is aimed at dynamically scheduling vehicles among multiple sites in order to minimize the cost when delivery orders are not known a priori. Although DPDP plays an important role in modern logistics and supply chain management, state-of-the-art DPDP algorithms are still limited on their solution quality and efficiency. In practice, they fail to provide a scalable solution as the numbers of vehicles and sites become large. In this paper, we propose a data-driven approach, Spatial-Temporal Aided Double Deep Graph Network (ST-DDGN), to solve industry-scale DPDP. In our method, the delivery demands are first forecast using spatial-temporal prediction method, which guides the neural network to perceive spatial-temporal distribution of delivery demand when dispatching vehicles. Besides, the relationships of individuals such as vehicles are modelled by establishing a graph-based value function. ST-DDGN incorporates attention-based graph embedding with Double DQN (DDQN). As such, it can make the inference across vehicles more efficiently compared with traditional methods. Our method is entirely data driven and thus adaptive, i.e., the relational representation of adjacent vehicles can be learned and corrected by ST-DDGN from data periodically. We have conducted extensive experiments over real-world data to evaluate our solution. The results show that ST-DDGN reduces 11.27% number of the used vehicles and decreases 13.12% total transportation cost on average over the strong baselines, including the heuristic algorithm deployed in our UAT (User Acceptance Test) environment and a variety of vanilla DRL methods. We are due to fully deploy our solution into our online logistics system and it is estimated that millions of USD logistics cost can be saved per year.

cs.AI↗

arXiv2019

Network analysis of chaotic dynamics in fixed-precision digital domain

When implemented in the digital domain with time, space and value discretized in the binary form, many good dynamical properties of chaotic systems in continuous domain may be degraded or even diminish. To measure the dynamic complexity of a digital chaotic system, the dynamics can be transformed to the form of a state-mapping network. Then, the parameters of the network are verified by some typical dynamical metrics of the original chaotic system in infinite precision, such as Lyapunov exponent and entropy. This article reviews some representative works on the network-based analysis of digital chaotic dynamics and presents a general framework for such analysis, unveiling some intrinsic relationships between digital chaos and complex networks. As an example for discussion, the dynamics of a state-mapping network of the Logistic map in a fixed-precision computer is analyzed and discussed.

nlin.CD↗

arXiv2018

Random Asynchronous Iterations in Distributed Coordination Algorithms

Distributed coordination algorithms (DCA) carry out information processing processes among a group of networked agents without centralized information fusion. Though it is well known that DCA characterized by an SIA (stochastic, indecomposable, aperiodic) matrix generate consensus asymptotically via synchronous iterations, the dynamics of DCA with asynchronous iterations have not been studied extensively, especially when viewed as stochastic processes. This paper aims to show that for any given irreducible stochastic matrix, even non-SIA, the corresponding DCA lead to consensus successfully via random asynchronous iterations under a wide range of conditions on the transition probability. Particularly, the transition probability is neither required to be independent and identically distributed, nor characterized by a Markov chain.

math.OC↗

arXiv2006

Adaptive Synchronization of An Uncertain Complex Dynamical Network

This brief paper further investigates the locally and globally adaptive synchronization of an uncertain complex dynamical network. Several network synchronization criteria are deduced. Especially, our hypotheses and designed adaptive controllers for network synchronization are rather simple in form. It is very useful for future practical engineering design. Moreover, numerical simulations are also given to show the effectiveness of our synchronization approaches.

nlin.AO↗

arXiv2004

A Time-Varying Complex Dynamical Network Model And Its Controlled Synchronization Criteria

Today, complex networks have attracted increasing attention from various fields of science and engineering. It has been demonstrated that many complex networks display various synchronization phenomena. In this paper, we introduce a time-varying complex dynamical network model. We then further investigate its synchronization phenomenon and prove several network synchronization theorems. Especially, we show that synchronization of such a time-varying dynamical network is completely determined by the inner-coupling matrix, and the eigenvalues and the corresponding eigenvectors of the coupling configuration matrix of the network.

nlin.AO↗