检索结果-内蒙古大学图书馆

Large Language Models as Evolutionary Optimizers 13

学校读者我要写书评

暂无评论

Large Language Models as Evolutionary Optimizers

13th IEEE Congress on Evolutionary computation, CEC 2024

作者： Liu, Shengcai Chen, Caishun Qu, Xinghua Tang, Ke Ong, Yew-Soon Southern University of Science and Technology Centre for Frontier Ai Research A∗star Department of Computer Science and Engineering China Centre for Frontier Ai Research A∗star Singapore Tianqiao & Chrissy Chen Institute China Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering China Nanyang Technological University Centre for Frontier Ai Research A∗star College of Computing and Data Science Singapore

ISBN: (纸本)9798350308365

Evolutionary algorithms (EAs) have achieved remarkable success in tackling complex combinatorial optimization problems. However, EAs often demand carefully-designed operators with the aid of domain expertise to achieve satisfactory performance. In this work, we present the first study on large language models (LLMs) as evolutionary combinatorial optimizers. The main advantage is that it requires minimal domain knowledge and human efforts, as well as no additional training of the model. This approach is referred to as LLM-driven EA (LMEA). Specifically, in each generation of the evolutionary search, LMEA instructs the LLM to select parent solutions from current population, and perform crossover and mutation to generate offspring solutions. Then, LMEA evaluates these new solutions and include them into the population for the next generation. LMEA is equipped with a self-adaptation mechanism that controls the temperature of the LLM. This enables it to balance between exploration and exploitation and prevents the search from getting stuck in local optima. We investigate the power of LMEA on the classical traveling salesman problems (TSPs) widely used in combinatorial optimization research. Notably, the results show that LMEA performs competitively to traditional heuristics in finding high-quality solutions on TSP instances with up to 20 nodes. Additionally, we also study the effectiveness of LLM-driven crossover/mutation and the self- adaptation mechanism in evolutionary search. In summary, our results reveal the great potentials of LLMs as evolutionary optimizers for solving combinatorial problems. We hope our research shall inspire future explorations on LLM-driven EAs for complex optimization challenges. © 2024 IEEE.

关键词： Traveling salesman problem

Efficient tensor networks for control-enhanced quantum metrology

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Qiushi Yang, Yuxiang QICI Quantum Information and Computation Initiative Department of Computer Science School of Computing and Data Science The University of Hong Kong Pokfulam Road Hong Kong

Optimized quantum control can enhance the performance and noise resilience of quantum metrology. However, the optimization quickly becomes intractable when multiple control operations are applied sequentially. In this work, we propose efficient tensor network algorithms for optimizing strategies of quantum metrology enhanced by a long sequence of control operations. Our approach covers a general and practical scenario where the experimenter applies N−1 interleaved control operations between N queries of the channel to estimate and uses no or bounded ancilla. Tailored to different experimental capabilities, these control operations can be generic quantum channels or variational unitary gates. Numerical experiments show that our algorithm has a good performance in optimizing the metrological strategy for as many as N = 100 queries. In particular, our algorithm identifies a strategy that can outperform the state-of-the-art strategy when N is finite but large. © 2024, CC BY.

关键词： Tensors

SIMLOB: LEARNING REPRESENTATIONS OF LIMITED ORDER BOOK FOR FINANCIAL MARKET SIMULATION

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Yuanzhe Wu, Yue Zhong, Muyao Liu, Shengcai Yang, Peng Department of Statistics and Data Science Southern University of Science and Technology China Department of Computer Science and Engineering Southern University of Science and Technology China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Statistics and Data Science Department of Computer Science and Engineering Southern University of Science and Technology China

Financial market simulation (FMS) serves as a promising tool for understanding market anomalies and underlying trading behaviors. To ensure high-fidelity simulations, it is crucial to calibrate the FMS model to generate data closely resembling the observed market data. Previous efforts primarily focused on calibrating merely the mid-price data, leading to essential information loss of the market activities and thus biasing the calibrated model. The Limit Order Book data (LOB) is the fundamental data that fully captures the market microstructure and is adopted by exchanges worldwide. However, LOB is not applicable to existing calibration objective functions due to its unique properties, including high dimensionality, differences in feature scales, and cross-feature constraints. This paper proposes an efficient Transformer-based autoencoder to explicitly learn the vectorized representations of LOB, addressing its unique challenges. The resulted latent vector, which captures the major information of LOB, can then be applied for calibration. Extensive experiments show that the learned latent representation preserves not only the non-linear auto-correlation in the temporal axis but also the precedence between successive price levels of LOB. Besides, we verify that the representation learning aligns with the downstream calibration tasks, making the first advancement in calibrating FMS on LOB. © 2024, CC BY.

关键词： Financial markets

Heisenberg-Limited Quantum Metrology without Ancilla

学校读者我要写书评

暂无评论

arXiv 2024年

Extensive research has been dedicated to the asymptotic theory of quantum metrology, where the goal is to determine the ultimate precision limit of quantum channel estimation when many accesses to the channel are allowed. The ultimate limit has been well established, but in general noiseless and controllable ancilla is required for attaining it. Little is known about the metrological performance without noiseless ancilla, which is more relevant in practical circumstances. In this work, we present a novel theoretical framework to address this problem, bridging quantum metrology and the asymptotic theory of quantum channels. Leveraging this framework, we prove sufficient conditions for achieving the Heisenberg limit with repeated applications of the channel to estimate, both with and without applying interleaved unitary control operations. For the latter case, we design an algorithm to identify explicitly the control operation. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum channel

Reducing idleness in financial cloud services via multi-objective evolutionary reinforcement learning based load balancer

学校读者我要写书评

暂无评论

science China(Information sciences) 2024年第2期67卷 20-40页

作者： Peng YANG Laoming ZHANG Haifeng LIU Guiying LI Department of Statistics and Data Science Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and EngineeringSouthern University of Science and Technology Academy for Advanced Interdisciplinary Studies Southern University of Science and Technology Guangdong OPPO Mobile Telecommunications Corp. Ltd Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology

In recent years, various companies have started to shift their data services from traditional data centers to the cloud. One of the major motivations is to save on operational costs with the aid of cloud elasticity. This paper discusses an emerging need from financial services to reduce the incidence of idle servers retaining very few user connections, without disconnecting them from the server side. This paper considers this need as a bi-objective online load balancing problem. A neural network based scalable policy is designed to route user requests to varied numbers of servers for the required elasticity. An evolutionary multi-objective training framework is proposed to optimize the weights of the policy. Not only is the new objective of idleness reduced by over 130% more than traditional industrial solutions, but the original load balancing objective itself is also slightly improved. Extensive simulations with both synthetic and real-world data help reveal the detailed applicability of the proposed method to the emergent problem of reducing idleness in financial services.

关键词： evolutionary reinforcement learning evolutionary multi-objective optimization load balance cloud computing

A Variant Modified Skew-Normal Splitting Iterative Method for Non-Hermitian Positive Definite Linear Systems

学校读者我要写书评

暂无评论

Numerical Mathematics(Theory,Methods and Applications) 2022年第2期15卷 510-529页

作者： Rui Li Jun-Feng Yin Zhi-Lin Li College of Data Science Jiaxing UniversityZhejiang 314001P.R.China School of Mathematical Sciences Tongji UniversityShanghai 200092P.R.China Center for Research in Scientific Computation and Department of Mathematics North Carolina State UniversityRaleighNC 27695USA

We propose a variant modified skew-normal splitting iterative method to solve a class of large sparse non-Hermitian positive definite linear *** the preconditioning technique we also construct the preconditioned version of the proposed *** analysis shows that the proposed method is unconditionally convergent even when the real part and the imaginary part of the coefficient matrix are ***,when the real part and the imaginary part of the coefficient matrix are symmetric positive definite,we prove that the preconditioned variant modified skew-normal splitting iterative method will also unconditionally *** experiments are presented to illustrate the efficiency of the proposed method and show better performance of it when compared with some other methods.

关键词： Non-Hermitian matrix skew-normal splitting precondition complex linear system

GRADIENT-FREE TRAINING OF RECURRENT NEURAL NETWORKS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bolager, Erik Lien Cukarska, Ana Burak, Iryna Monfared, Zahra Dietrich, Felix School of Computation Information and Technology Germany Munich Data Science Institute Technical University of Munich Germany Germany Department of Mathematics and Computer Science Heidelberg University Germany

Recurrent neural networks are a successful neural architecture for many time-dependent problems, including time series analysis, forecasting, and modeling of dynamical systems. Training such networks with backpropagation through time is a notoriously difficult problem because their loss gradients tend to explode or vanish. In this contribution, we introduce a computational approach to construct all weights and biases of a recurrent neural network without using gradient-based methods. The approach is based on a combination of random feature networks and Koopman operator theory for dynamical systems. The hidden parameters of a single recurrent block are sampled at random, while the outer weights are constructed using extended dynamic mode decomposition. This approach alleviates all problems with backpropagation commonly related to recurrent networks. The connection to Koopman operator theory also allows us to start using results in this area to analyze recurrent neural networks. In computational experiments on time series, forecasting for chaotic dynamical systems, and control problems, as well as on weather data, we observe that the training time and forecasting accuracy of the recurrent neural networks we construct are improved when compared to commonly used gradient-based methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Recurrent neural networks

Energy-Efficient Multi-Trip Routing for Municipal Solid Waste Collection by Contribution-Based Adaptive Particle Swarm Optimization

学校读者我要写书评

暂无评论

Complex System Modeling and Simulation 2023年第3期3卷 202-219页

作者： Xiaoning Shen Hongli Pan Zhongpei Ge Wenyan Chen Liyan Song Shuo Wang Collaborative Innovation Center of Atmospheric Environment and Equipment Technology and also with the Jiangsu Key Laboratory of Big Data Analysis TechnologySchool of AutomationNanjing University of Information Science and TechnologyNanjing 210044China School of Automation Nanjing University of Information Science and TechnologyNanjing 210044China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation the Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China School of Computer Science University of BirminghamBirminghamB152TTUK

Waste collection is an important part of waste management *** costs and carbon emissions can be greatly reduced by proper vehicle ***,each vehicle can work again after achieving its capacity limit and unloading the *** this,an energy-efficient multi-trip vehicle routing model is established for municipal solid waste collection,which incorporates practical factors like the limited capacity,maximum working hours,and multiple trips of each *** both economy and environment,fixed costs,fuel costs,and carbon emission costs are minimized *** solve the formulated model effectively,contribution-based adaptive particle swarm optimization is *** strategies named greedy learning,multi-operator learning,exploring learning,and exploiting learning are specifically designed with their own searching *** assessing the contribution of each learning strategy during the process of evolution,an appropriate one is selected and assigned to each individual adaptively to improve the searching efficiency of the ***,an improved local search operator is performed on the trips with the largest number of waste sites so that both the exploiting ability and the convergence accuracy of the algorithm are *** of the proposed algorithm is tested on ten waste collection instances,which include one real-world case derived from the Green Ring Company of Jiangbei New District,Nanjing,China,and nine synthetic instances with increasing scales generated from the commonly-used capacitated vehicle routing problem benchmark *** with five state-of-the-art algorithms show that the proposed algorithm can obtain a solution with a higher accuracy for the constructed model.

关键词： municipal solid waste collection energy conservation multi-trip contribution particle swarm optimization

Enabling Surrogate-Assisted Evolutionary Reinforcement Learning via Policy Embedding 1

学校读者我要写书评

暂无评论

17th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2022

作者： Tang, Lan Li, Xiaxi Zhang, Jinyuan Li, Guiying Yang, Peng Tang, Ke Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Faculty of Engineering Shenzhen MSU-BIT University Shenzhen518172 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Data Science Southern University of Science and Technology Shenzhen518055 China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

Evolutionary Reinforcement Learning (ERL) that applying Evolutionary Algorithms (EAs) to optimize the weight parameters of Deep Neural Network (DNN) based policies has been widely regarded as an alternative to traditional reinforcement learning methods. However, the evaluation of the iteratively generated population usually requires a large amount of computational time and can be prohibitively expensive, which may potentially restrict the applicability of ERL. Surrogate is often used to reduce the computational burden of evaluation in EAs. Unfortunately, in ERL, each individual of policy usually represents millions of weights parameters of DNN. This high-dimensional representation of policy has introduced a great challenge to the application of surrogates into ERL to speed up training. This paper proposes a PE-SAERL Framework to at the first time enable surrogate-assisted evolutionary reinforcement learning via policy embedding (PE). Empirical results on 5 Atari games show that the proposed method can perform more efficiently than the four state-of-the-art algorithms. The training process is accelerated up to 7x on tested games, comparing to its counterpart without the surrogate and PE. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning