检索结果-内蒙古大学图书馆

Genetic and Evolutionary Computation Conference (GECCO)

作者： Lang, Ryan Dieter Engelbrecht, Andries Petrus Stellenbosch Univ Comp Sci Div Stellenbosch South Africa Stellenbosch Univ Dept Ind Engn Stellenbosch South Africa Gulf Univ Sci & Technol Ctr Appl Math & Bioinformat Mubarak Al Abdullah Saudi Arabia

ISBN: (纸本)9798400701207

This paper investigates the effect of hybridising sampling algorithms with population-based meta-heuristics. Recent literature has shown that alternatives to the traditionally used pseudo-random number generators to generate the initial population of metaheuristics can improve performance. However, most studies focus on sample sizes that are limited to the size of the initial populations. In contrast, this paper studies the effect of extended random initialisation, which uses relatively large samples and then initialises the meta-heuristics from the points in the sample with the best-found fitness values. A portfolio of three meta-heuristics, four sampling algorithms and three different sampling budgets are analysed from the fixed budget perspective on the BBOB benchmark suite. Statistical analysis of the results shows that the hybrid algorithms converge to better solutions than their non-hybrid counterparts. The results further indicate that large sample sizes can be used to generate landscape analysis features, ensuring reliable approximations of the investigated functions' properties without lessening the meta-heuristics' performance.

关键词： meta-heuristics evolutionary algorithms sampling algorithms initialization landscape analysis

来源：评论

学校读者我要写书评

暂无评论

Lightweight Feature-based Priority sampling for Industrial IoT Multivariate Time Series 20

Lightweight Feature-based Priority Sampling for Industrial I...

引用

20th ACS/IEEE International Conference on Computer Systems and Applications (AICCSA)

作者： Nemer, Mohammad Ali Azar, Joseph Makhoul, Abdallah Bourgeois, Julien Univ Franche Comte UMR CNRS 6174 Femto St Inst Besancon France

ISBN: (纸本)9798350319439

sampling Industrial IoT data streams aims to generate a sample for future data analysis tasks. Several variables influence the efficacy of the constructed sample, including the sampling algorithm and its complexity, the sampling rate selected, and how the sampled data are processed at the gateway. In this paper, we propose a lightweight feature-based priority sampling technique for optimizing Industrial IoT multivariate time series prior to deep learning model classification. The selection of an effective sampling algorithm and rate, coupled with efficient data processing, poses a significant challenge with a key objective of balancing communication overhead reduction and precision maintenance. Our technique minimizes data transmission at the IoT device level, enhancing energy efficiency and improving classification performance by noise reduction through selective feature sampling. Comparative evaluation with existing sampling techniques using a benchmark dataset indicates superior performance in terms of data reduction and classification accuracy trade-offs. Notably, our approach enhances the accuracy of a ResNet model and reduces its processing time.

关键词： Industrial IoT Data Streams Time Series Classification Industry 4.0 Fault Detection sampling algorithms Data reduction Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Boltzmann distribution on "short" integer partitions with power parts: Limit laws and sampling

引用

ADVANCES IN APPLIED MATHEMATICS 2024年 159卷

作者： Peyen, Jean C. Bogachev, Leonid, V Martin, Paul P. Univ Leeds Sch Math Leeds LS2 9JT England

The paper is concerned with the asymptotic analysis of a family of Boltzmann (multiplicative) distributions over the set Lambda(q) of strict integer partitions (i.e., with unequal parts) into perfect q-th powers. A combinatorial link is provided via a suitable conditioning by fixing the partition weight (the sum of parts) and length (the number of parts), leading to uniform distribution on the corresponding subspaces of partitions. The Boltzmann measure is calibrated through the hyper- parameters (N) and (M) controlling the expected weight and length, respectively. We study "short" partitions, where the parameter (M) is either fixed or grows slower than for typical partitions in Lambda(q). For this model, we obtain a variety of limit theorems including the asymptotics of the cumulative cardinality in the case of fixed (M) and a limit shape result in the case of slow growth of (M). In both cases, we also characterize the joint distribution of the weight and length, as well as the growth of the smallest and largest parts. Using these results we construct suitable sampling algorithms and analyze their performance. (c) 2024 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY license (http:// creativecommons .org /licenses /by /4 .0/).

关键词： Integer partitions Boltzmann distribution Generating functions Young diagrams Limit shape sampling algorithms

来源：评论

学校读者我要写书评

暂无评论

Efficient sampling and Counting of Graph Structures Related to Chordal Graphs

Efficient Sampling and Counting of Graph Structures Related ...

引用

作者： Sun, Wenbo Rochester Institute of Technology

学位级别：Ph.D., Doctor of Philosophy

Counting problems aim to count the number of solutions for a given input, for example, counting the number of variable assignments that satisfy a Boolean formula. sampling problems aim to produce a random object from a desired distribution, for example, producing a variable assignment drawn uniformly at random from all assignments that satisfy a Boolean formula. The problems of counting and sampling of graph structures on different types of graphs have been studied for decades for their great importance in areas like complexity theory and statistical physics. For many graph structures such as independent sets and acyclic orientations, it is widely believed that no exact or approximate (with an arbitrarily small error) polynomial-time algorithms on general graphs exist. Therefore, the research community studies various types of graphs, aiming either to design a polynomial-time counting or sampling algorithm for such inputs, or to prove a corresponding inapproximability result. Chordal graphs have been studied widely in both AI and theoretical computer science, but their study from the counting perspective has been relatively limited. Previous works showed that some graph structures can be counted in polynomial time on chordal graphs, when their counting on general graphs is provably computationally hard. The main objective of this thesis is to design and analyze counting and sampling algorithms for several well-known graph structures, including independent sets and different types of graph orientations, on chordal graphs. Our contributions can be described from two perspectives: evaluating the performances of some well-known sampling techniques, such as Markov chain Monte Carlo, on chordal graphs; and showing that the chordality does make those counting problems polynomial-time solvable.

关键词： Chordal graphs Boolean formula sampling algorithms Graph structures

来源：评论

学校读者我要写书评

暂无评论

Gibbs sampling the posterior of neural networks

引用

JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL 2024年第12期57卷 125002-125002页

作者： Piccioli, Giovanni Troiani, Emanuele Zdeborova, Lenka Ecole Polytech Fed Lausanne EPFL Stat Phys Comp Lab Lausanne Switzerland

In this paper, we study sampling from a posterior derived from a neural network. We propose a new probabilistic model consisting of adding noise at every pre- and post-activation in the network, arguing that the resulting posterior can be sampled using an efficient Gibbs sampler. For small models, the Gibbs sampler attains similar performances as the state-of-the-art Markov chain Monte Carlo methods, such as the Hamiltonian Monte Carlo or the Metropolis adjusted Langevin algorithm, both on real and synthetic data. By framing our analysis in the teacher-student setting, we introduce a thermalization criterion that allows us to detect when an algorithm, when run on data with synthetic labels, fails to sample from the posterior. The criterion is based on the fact that in the teacher-student setting we can initialize an algorithm directly at equilibrium.

关键词： MCMC Bayesian learning neural networks sampling algorithms MCMC thermalization statistical physics

来源：评论

学校读者我要写书评

暂无评论

Learning from mistakes: sampling strategies to efficiently train machine learning models for material property prediction

引用

COMPUTATIONAL MATERIALS SCIENCE 2023年 224卷

作者： Magar, Rishikesh Farimani, Amir Barati Carnegie Mellon Univ Dept Mech Engn Pittsburgh PA 15213 USA

Recent advances in machine learning (ML) based methodologies have accelerated the prediction of the physical properties of materials. These ML models, however, rely on large amounts of simulated or experimental data to make a reliable prediction. This dependence on large amounts of data can be a roadblock to building ML models since collecting the data is prohibitively expensive and time-consuming. In this work, we propose two sampling strategies to reliably train machine learning models in the lowest amounts of data. Our algorithms alleviate the need to generate large datasets to train machine learning models. We demonstrate the effectiveness of these sampling strategies by improving the performance of Crystal Graph Convolutional Neural Network (CGCNN) on four different datasets. Using the proposed strategies, we can reach the benchmark performance of CGCNN models in fewer data samples.

关键词： Machine learning sampling algorithms

来源：评论

学校读者我要写书评

暂无评论

A simulated annealing-based algorithm for selecting balanced samples

引用

COMPUTATIONAL STATISTICS 2022年第1期37卷 491-505页

作者： Benedetti, Roberto Dickson, Maria Michela Espa, Giuseppe Pantalone, Francesco Piersimoni, Federica Univ G dAnnunzio Dept Econ Studies I-65127 Pescara Italy Univ Trento Dept Econ & Management I-38122 Trento Italy Univ Perugia Dept Econ I-06123 Perugia Italy Istat Directorate Methodol & Stat Proc Design I-00184 Rome Italy

Balanced sampling is a random method for sample selection, the use of which is preferable when auxiliary information is available for all units of a population. However, implementing balanced sampling can be a challenging task, and this is due in part to the computational efforts required and the necessity to respect balancing constraints and inclusion probabilities. In the present paper, a new algorithm for selecting balanced samples is proposed. This method is inspired by simulated annealing algorithms, as a balanced sample selection can be interpreted as an optimization problem. A set of simulation experiments and an example using real data shows the efficiency and the accuracy of the proposed algorithm.

关键词： Balanced sampling Auxiliary variables sampling algorithms Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Metropolis Monte Carlo sampling: convergence, localization transition and optimality

引用

JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT 2023年第12期2023卷 123205-123205页

作者： Chepelianskii, Alexei D. Majumdar, Satya N. Schawe, Hendrik Trizac, Emmanuel Univ Paris Saclay CNRS Lab Phys Solides F-91405 Orsay France Univ Paris Saclay CNRS LPTMS F-91405 Orsay France CY Cergy Paris Univ LPTM UMR 8089 CNRS F-95000 Cergy France

Among random sampling methods, Markov chain Monte Carlo (MC) algorithms are foremost. Using a combination of analytical and numerical approaches, we study their convergence properties toward the steady state, within a random walk Metropolis scheme. Analyzing the relaxation properties of some model algorithms sufficiently simple to enable analytic progress, we show that the deviations from the target steady-state distribution can feature a localization transition as a function of the characteristic length of the attempted jumps defining the random walk. While the iteration of the MC algorithm converges to equilibrium for all choices of jump parameters, the localization transition changes drastically the asymptotic shape of the difference between the probability distribution reached after a finite number of steps of the algorithm and the target equilibrium distribution. We argue that the relaxation before and after the localization transition is respectively limited by diffusion and rejection rates.

关键词： classical Monte Carlo simulations sampling algorithms mixing analysis of algorithms Brownian motion

来源：评论

学校读者我要写书评

暂无评论

Is there an analog of Nesterov acceleration for gradient-based MCMC?

引用

BERNOULLI 2021年第3期27卷 1942-1992页

作者： Ma, Yi-An Chatterji, Niladri S. Cheng, Xiang Flammarion, Nicolas Bartlett, Peter L. Jordan, Michael, I Univ Calif San Diego Halicioglu Data Sci Inst San Diego CA 92093 USA Univ Calif Berkeley Dept Phys Berkeley CA 94720 USA Univ Calif Berkeley Dept Elect Engn & Comp Sci Berkeley CA 94720 USA Ecole Polytech Fed Lausanne Sch Comp & Commun Sci Lausanne Switzerland Univ Calif Berkeley Dept Stat Berkeley CA 94720 USA

We formulate gradient-based Markov chain Monte Carlo (MCMC) sampling as optimization on the space of probability measures, with Kullback-Leibler (KL) divergence as the objective functional. We show that an under-damped form of the Langevin algorithm performs accelerated gradient descent in this metric. To characterize the convergence of the algorithm, we construct a Lyapunov functional and exploit hypocoercivity of the underdamped Langevin algorithm. As an application, we show that accelerated rates can be obtained for a class of nonconvex functions with the Langevin algorithm.

关键词： Markov chain Monte Carlo Langevin Monte Carlo accelerated gradient descent sampling algorithms

来源：评论

学校读者我要写书评

暂无评论

Counting and sampling gene family evolutionary histories in the duplication-loss and duplication-loss-transfer models

引用

JOURNAL OF MATHEMATICAL BIOLOGY 2020年第5期80卷 1353-1388页

作者： Chauve, Cedric Ponty, Yann Wallner, Michael Simon Fraser Univ Dept Math Burnaby BC Canada Univ Bordeaux LaBRI Talence France Ecole Polytech LIX Palaiseau France Ecole Polytech CNRS Palaiseau France TU Wien Inst Diskrete Math & Geometrie Vienna Austria

Given a set of species whose evolution is represented by a species tree, a gene family is a group of genes having evolved from a single ancestral gene. A gene family evolves along the branches of a species tree through various mechanisms, including-but not limited to-speciation (S), gene duplication (D), gene loss (L), and horizontal gene transfer (T). The reconstruction of a gene tree representing the evolution of a gene family constrained by a species tree is an important problem in phylogenomics. However, unlike in the multispecies coalescent evolutionary model that considers only speciation and incomplete lineage sorting events, very little is known about the search space for gene family histories accounting for gene duplication, gene loss and horizontal gene transfer (the DLT-model). In this work, we introduce the notion of evolutionary histories defined as a binary ordered rooted tree describing the evolution of a gene family, constrained by a species tree in the DLT-model. We provide formal grammars describing the set of all evolutionary histories that are compatible with a given species tree, whether it is ranked or unranked. These grammars allow us, using either analytic combinatorics or dynamic programming, to efficiently compute the number of histories of a given size, and also to generate random histories of a given size under the uniform distribution. We apply these tools to obtain exact asymptotics for the number of gene family histories for two species trees, the rooted caterpillar and complete binary tree, as well as estimates of the range of the exponential growth factor of the number of histories for random species trees of size up to 25. Our results show that including horizontal gene transfers induce a dramatic increase of the number of evolutionary histories. We also show that, within ranked species trees, the number of evolutionary histories in the DLT-model is almost independent of the species tree topology. These results establish firm founda

关键词： Phylogenetics Enumerative combinatorics Asymptotics sampling algorithms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：