Search results for "Mathematical optimization"

showing 10 items of 1300 documents

Randomized Block Frank–Wolfe for Convergent Large-Scale Learning

2017

Owing to their low-complexity iterations, Frank-Wolfe (FW) solvers are well suited for various large-scale learning tasks. When block-separable constraints are present, randomized block FW (RB-FW) has been shown to further reduce complexity by updating only a fraction of coordinate blocks per iteration. To circumvent the limitations of existing methods, the present work develops step sizes for RB-FW that enable a flexible selection of the number of blocks to update per iteration while ensuring convergence and feasibility of the iterates. To this end, convergence rates of RB-FW are established through computational bounds on a primal sub-optimality measure and on the duality gap. The novel b…

FOS: Computer and information sciencesMathematical optimization0102 computer and information sciences02 engineering and technology01 natural sciencesMeasure (mathematics)Machine Learning (cs.LG)Convergence (routing)FOS: Mathematics0202 electrical engineering electronic engineering information engineeringFraction (mathematics)Electrical and Electronic EngineeringMathematics - Optimization and ControlMathematicsSequenceDuality gapComputer Science - Numerical Analysis020206 networking & telecommunicationsNumerical Analysis (math.NA)Stationary pointSupport vector machineComputer Science - LearningOptimization and Control (math.OC)010201 computation theory & mathematicsIterated functionSignal ProcessingAlgorithmIEEE Transactions on Signal Processing
researchProduct

Adaptive independent sticky MCMC algorithms

2018

In this work, we introduce a novel class of adaptive Monte Carlo methods, called adaptive independent sticky MCMC algorithms, for efficient sampling from a generic target probability density function (pdf). The new class of algorithms employs adaptive non-parametric proposal densities which become closer and closer to the target as the number of iterations increases. The proposal pdf is built using interpolation procedures based on a set of support points which is constructed iteratively based on previously drawn samples. The algorithm's efficiency is ensured by a test that controls the evolution of the set of support points. This extra stage controls the computational cost and the converge…

FOS: Computer and information sciencesMathematical optimizationAdaptive Markov chain Monte Carlo (MCMC)Monte Carlo methodBayesian inferenceHASettore SECS-P/05 - Econometrialcsh:TK7800-8360Machine Learning (stat.ML)02 engineering and technologyBayesian inference01 natural sciencesStatistics - Computationlcsh:Telecommunication010104 statistics & probabilitysymbols.namesakeAdaptive Markov chain Monte Carlo (MCMC); Adaptive rejection Metropolis sampling (ARMS); Bayesian inference; Gibbs sampling; Hit and run algorithm; Metropolis-within-Gibbs; Monte Carlo methods; Signal Processing; Hardware and Architecture; Electrical and Electronic EngineeringGibbs samplingStatistics - Machine Learninglcsh:TK5101-67200202 electrical engineering electronic engineering information engineeringComputational statisticsMetropolis-within-GibbsHit and run algorithm0101 mathematicsElectrical and Electronic EngineeringGaussian processComputation (stat.CO)MathematicsSignal processinglcsh:Electronics020206 networking & telecommunicationsMarkov chain Monte CarloMonte Carlo methodsHardware and ArchitectureSignal ProcessingSettore SECS-S/03 - Statistica EconomicasymbolsSettore SECS-S/01 - StatisticaStatistical signal processingGibbs samplingAdaptive rejection Metropolis sampling (ARMS)EURASIP Journal on Advances in Signal Processing
researchProduct

Consistent Regression of Biophysical Parameters with Kernel Methods

2020

This paper introduces a novel statistical regression framework that allows the incorporation of consistency constraints. A linear and nonlinear (kernel-based) formulation are introduced, and both imply closed-form analytical solutions. The models exploit all the information from a set of drivers while being maximally independent of a set of auxiliary, protected variables. We successfully illustrate the performance in the estimation of chlorophyll content.

FOS: Computer and information sciencesMathematical optimizationComputer Science - Machine Learning010504 meteorology & atmospheric sciences0211 other engineering and technologiesRegression analysisMachine Learning (stat.ML)02 engineering and technology01 natural sciencesRegressionData modelingMachine Learning (cs.LG)Set (abstract data type)Methodology (stat.ME)Nonlinear systemKernel methodConsistency (statistics)Statistics - Machine LearningKernel (statistics)Statistics - Methodology021101 geological & geomatics engineering0105 earth and related environmental sciencesMathematicsIGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium
researchProduct

Bayesian Unification of Gradient and Bandit-based Learning for Accelerated Global Optimisation

2017

Bandit based optimisation has a remarkable advantage over gradient based approaches due to their global perspective, which eliminates the danger of getting stuck at local optima. However, for continuous optimisation problems or problems with a large number of actions, bandit based approaches can be hindered by slow learning. Gradient based approaches, on the other hand, navigate quickly in high-dimensional continuous spaces through local optimisation, following the gradient in fine grained steps. Yet, apart from being susceptible to local optima, these schemes are less suited for online learning due to their reliance on extensive trial-and-error before the optimum can be identified. In this…

FOS: Computer and information sciencesMathematical optimizationComputer scienceComputer Science - Artificial IntelligenceBayesian probability02 engineering and technologyMachine learningcomputer.software_genreMachine Learning (cs.LG)symbols.namesakeLocal optimumMargin (machine learning)0202 electrical engineering electronic engineering information engineeringGaussian processFlexibility (engineering)business.industry020206 networking & telecommunicationsFunction (mathematics)Computer Science - LearningArtificial Intelligence (cs.AI)symbols020201 artificial intelligence & image processingAlgorithm designLinear approximationArtificial intelligencebusinesscomputer
researchProduct

Online shortest paths with confidence intervals for routing in a time varying random network

2018

International audience; The increase in the world's population and rising standards of living is leading to an ever-increasing number of vehicles on the roads, and with it ever-increasing difficulties in traffic management. This traffic management in transport networks can be clearly optimized by using information and communication technologies referred as Intelligent Transport Systems (ITS). This management problem is usually reformulated as finding the shortest path in a time varying random graph. In this article, an online shortest path computation using stochastic gradient descent is proposed. This routing algorithm for ITS traffic management is based on the online Frank-Wolfe approach.…

FOS: Computer and information sciencesMathematical optimizationComputer sciencePopulation02 engineering and technology[INFO.INFO-SE]Computer Science [cs]/Software Engineering [cs.SE][INFO.INFO-IU]Computer Science [cs]/Ubiquitous Computing[SPI]Engineering Sciences [physics][INFO.INFO-CR]Computer Science [cs]/Cryptography and Security [cs.CR]0502 economics and business11. SustainabilityComputer Science - Data Structures and Algorithms0202 electrical engineering electronic engineering information engineeringFOS: MathematicsData Structures and Algorithms (cs.DS)educationIntelligent transportation systemMathematics - Optimization and ControlRandom graph050210 logistics & transportationeducation.field_of_studyStochastic process[SPI.PLASMA]Engineering Sciences [physics]/Plasmas05 social sciencesApproximation algorithm[INFO.INFO-MO]Computer Science [cs]/Modeling and SimulationStochastic gradient descentOptimization and Control (math.OC)[INFO.INFO-MA]Computer Science [cs]/Multiagent Systems [cs.MA]Shortest path problem020201 artificial intelligence & image processing[INFO.INFO-ET]Computer Science [cs]/Emerging Technologies [cs.ET]Routing (electronic design automation)[INFO.INFO-DC]Computer Science [cs]/Distributed Parallel and Cluster Computing [cs.DC]
researchProduct

Scalability of using Restricted Boltzmann Machines for Combinatorial Optimization

2014

Abstract Estimation of Distribution Algorithms (EDAs) require flexible probability models that can be efficiently learned and sampled. Restricted Boltzmann Machines (RBMs) are generative neural networks with these desired properties. We integrate an RBM into an EDA and evaluate the performance of this system in solving combinatorial optimization problems with a single objective. We assess how the number of fitness evaluations and the CPU time scale with problem size and complexity. The results are compared to the Bayesian Optimization Algorithm (BOA), a state-of-the-art multivariate EDA, and the Dependency Tree Algorithm (DTA), which uses a simpler probability model requiring less computati…

FOS: Computer and information sciencesMathematical optimizationInformation Systems and ManagementOptimization problemGeneral Computer SciencePopulationComputer Science::Neural and Evolutionary Computation0211 other engineering and technologiesBoltzmann machine02 engineering and technologyManagement Science and Operations ResearchIndustrial and Manufacturing EngineeringEvolutionary computation0202 electrical engineering electronic engineering information engineeringNeural and Evolutionary Computing (cs.NE)educationMathematicseducation.field_of_study021103 operations researchArtificial neural networkI.2.6I.2.8Computer Science - Neural and Evolutionary ComputingEstimation of distribution algorithmModeling and SimulationScalabilityCombinatorial optimization020201 artificial intelligence & image processingI.2.6; I.2.8Algorithm
researchProduct

An LP-based hyperparameter optimization model for language modeling

2018

In order to find hyperparameters for a machine learning model, algorithms such as grid search or random search are used over the space of possible values of the models hyperparameters. These search algorithms opt the solution that minimizes a specific cost function. In language models, perplexity is one of the most popular cost functions. In this study, we propose a fractional nonlinear programming model that finds the optimal perplexity value. The special structure of the model allows us to approximate it by a linear programming model that can be solved using the well-known simplex algorithm. To the best of our knowledge, this is the first attempt to use optimization techniques to find per…

FOS: Computer and information sciencesMathematical optimizationPerplexityLinear programmingComputer scienceMachine Learning (stat.ML)02 engineering and technology010501 environmental sciences01 natural sciencesTheoretical Computer ScienceNonlinear programmingMachine Learning (cs.LG)Random searchSimplex algorithmSearch algorithmStatistics - Machine Learning0202 electrical engineering electronic engineering information engineeringFOS: MathematicsMathematics - Optimization and Control0105 earth and related environmental sciencesHyperparameterComputer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)Computer Science - LearningHardware and ArchitectureOptimization and Control (math.OC)Hyperparameter optimization020201 artificial intelligence & image processingLanguage modelSoftwareInformation Systems
researchProduct

Structural bias in population-based algorithms

2014

Abstract Challenging optimisation problems are abundant in all areas of science and industry. Since the 1950s, scientists have responded to this by developing ever-diversifying families of ‘black box’ optimisation algorithms. The latter are designed to be able to address any optimisation problem, requiring only that the quality of any candidate solution can be calculated via a ‘fitness function’ specific to the problem. For such algorithms to be successful, at least three properties are required: (i) an effective informed sampling strategy, that guides the generation of new candidates on the basis of the fitnesses and locations of previously visited candidates; (ii) mechanisms to ensure eff…

FOS: Computer and information sciencesQA75Mathematical optimizationInformation Systems and ManagementPopulation-based algorithmsFitness landscapemedia_common.quotation_subjectPopulationStructural biasEvolutionary computationPopulation-based algorithmEvolutionary computationTheoretical Computer ScienceArtificial IntelligenceBlack boxEconometricsQuality (business)OptimisationAlgorithmic designNeural and Evolutionary Computing (cs.NE)educationMathematicsmedia_commonta113education.field_of_studyFitness functionPopulation sizeComputer Science - Neural and Evolutionary ComputingComputer Science ApplicationsControl and Systems EngineeringAlgorithmSoftwarePopulation variance
researchProduct

Random Interruptions in Cooperation for Spectrum Sensing in Cognitive Radio Networks

2015

In this paper, a new cooperation structure for spectrum sensing in cognitive radio networks is proposed which outperforms the existing commonly-used ones in terms of energy efficiency. The efficiency is achieved in the proposed design by introducing random interruptions in the cooperation process between the sensing nodes and the fusion center, along with a compensation process at the fusion center. Regarding the hypothesis testing problem concerned, first, the proposed system behavior is thoroughly analyzed and its associated likelihood-ratio test (LRT) is provided. Next, based on a general linear fusion rule, statistics of the global test summary are derived and the sensing quality is cha…

FOS: Computer and information sciencesSemidefinite programmingMathematical optimizationta213Computer scienceInformation Theory (cs.IT)Computer Science - Information Theory010401 analytical chemistrydecision/data fusion020206 networking & telecommunications02 engineering and technology01 natural sciencesStatistical power0104 chemical sciencescooperative spectrum sensingCognitive radionon-ideal reporting channelsefficiency0202 electrical engineering electronic engineering information engineeringcognitive radio (CR)False alarmElectrical and Electronic EngineeringStatistical hypothesis testingEfficient energy use
researchProduct

Thresholding projection estimators in functional linear models

2008

We consider the problem of estimating the regression function in functional linear regression models by proposing a new type of projection estimators which combine dimension reduction and thresholding. The introduction of a threshold rule allows to get consistency under broad assumptions as well as minimax rates of convergence under additional regularity hypotheses. We also consider the particular case of Sobolev spaces generated by the trigonometric basis which permits to get easily mean squared error of prediction as well as estimators of the derivatives of the regression function. We prove these estimators are minimax and rates of convergence are given for some particular cases.

FOS: Computer and information sciencesStatistics and ProbabilityMathematical optimizationStatistics::TheoryMean squared error of predictionMean squared errorMathematics - Statistics TheoryStatistics Theory (math.ST)Projection (linear algebra)Methodology (stat.ME)FOS: MathematicsApplied mathematicsStatistics - MethodologyMathematicsLinear inverse problemNumerical AnalysisLinear modelEstimatorRegression analysisMinimaxSobolev spaceThresholdingOptimal rate of convergenceDerivatives estimationRate of convergenceHilbert scaleStatistics Probability and UncertaintyGalerkin methodJournal of Multivariate Analysis
researchProduct