In differentiable search architecture search methods,a more efficient search space design can significantly improve the performance of the searched architecture,thus requiring people to carefully define the search spa...In differentiable search architecture search methods,a more efficient search space design can significantly improve the performance of the searched architecture,thus requiring people to carefully define the search space with different complexity according to various operations.Meanwhile rationalizing the search strategies to explore the well-defined search space will further improve the speed and efficiency of architecture search.With this in mind,we propose a faster and more efficient differentiable architecture search method,AllegroNAS.Firstly,we introduce a more efficient search space enriched by the introduction of two redefined convolution modules.Secondly,we utilize a more efficient architectural parameter regularization method,mitigating the overfitting problem during the search process and reducing the error brought about by gradient approximation.Meanwhile,we introduce a natural exponential cosine annealing method to make the learning rate of the neural network training process more suitable for the search procedure.Moreover,group convolution and data augmentation are employed to reduce the computational cost.Finally,through extensive experiments on several public datasets,we demonstrate that our method can more swiftly search for better-performing neural network architectures in a more efficient search space,thus validating the effectiveness of our approach.展开更多
The state space explosion problem is still the key obstacle for applying model checking to systems of industrial size. Abstraction-based methods have been particularly successful in this regard. This paper presents an...The state space explosion problem is still the key obstacle for applying model checking to systems of industrial size. Abstraction-based methods have been particularly successful in this regard. This paper presents an approach based on refinement of search space partition and abstraction which combines these two techniques for reducing the complexity of model checking. The refinement depends on the representation of each portion of search space. Especially, search space can be refined stepwise to get a better reduction. As reported in the case study, the integration of search space partition and abstraction improves the efficiency of verification with respect to the requirement of memory and obtains significant advantage over the use of each of them in isolation.展开更多
A multi-input multi-output(MIMO)detection scheme that requires considerable low complexity but still achieves the near optimal performance is proposed.The fundamental idea of the proposed MIMO detection scheme consist...A multi-input multi-output(MIMO)detection scheme that requires considerable low complexity but still achieves the near optimal performance is proposed.The fundamental idea of the proposed MIMO detection scheme consists of two points:1)the computational complexity is restrained by a complexity limit in low signal-to-noise ratio(SNR)region;2)while in high SNR region,the complexity is significantly reduced by the proposed search space method.Comparing with existing fixed-complexity techniques of MIMO detection(e.g.,K-best sphere detector and reduced-search maximum-likelihood(RS ML)detection),the significant benefit of proposed detection scheme is that less computational power will be spent for the given data rate,or the throughput of detector can be increased for high SNR cases.According to the simulation results,the near optimal performance can be obtained while the detection complexity is kept considerable small.展开更多
In this paper, we use the global search characteristics of genetic algorithms to help search the weight space of the neurons in the cascade-correlation architecture. The cascade-correlation learning architecture is a ...In this paper, we use the global search characteristics of genetic algorithms to help search the weight space of the neurons in the cascade-correlation architecture. The cascade-correlation learning architecture is a technique of training and building neural networks that starts with a simple network of neurons and adds additional neurons as they are needed to suit a particular problem. In our approach, instead ofmodifying the genetic algorithm to account for convergence problems, we search the weight-space using the genetic algorithm and then apply the gradient technique of Quickprop to optimize the weights. This hybrid algorithm which is a combination of genetic algorithms and cascade-correlation is applied to the two spirals problem. We also use our algorithm in the prediction of the cyclic oxidation resistance of Ni- and Co-base superalloys.展开更多
By extending the Levy wavefunction constrained search to Fock Space,one can define a wavefunction constrained search for electron densities in systems having noninteger number of electrons.For pure-state v-representab...By extending the Levy wavefunction constrained search to Fock Space,one can define a wavefunction constrained search for electron densities in systems having noninteger number of electrons.For pure-state v-representable densities,the results are equivalent to what one would obtain with the zero-temperature grand canonical ensemble.In other cases,the wavefunction constrained search in Fock space presents an upper bound to the grand canonical ensemble functional.One advantage of the Fock-space wavefunction constrained search functional over the zero-temperature grand-canonical ensemble constrained search functional is that certain specific excited states(i.e.,those that are not ground-statev-representable) are the stationary points of the Fock-space functional.However,a potential disadvantage of the Fock-space constrained search functional is that it is not convex.展开更多
基金This work was supported in part by the National Natural Science Foundation of China under Grant 61305001the Natural Science Foundation of Heilongjiang Province of China under Grant F201222.
文摘In differentiable search architecture search methods,a more efficient search space design can significantly improve the performance of the searched architecture,thus requiring people to carefully define the search space with different complexity according to various operations.Meanwhile rationalizing the search strategies to explore the well-defined search space will further improve the speed and efficiency of architecture search.With this in mind,we propose a faster and more efficient differentiable architecture search method,AllegroNAS.Firstly,we introduce a more efficient search space enriched by the introduction of two redefined convolution modules.Secondly,we utilize a more efficient architectural parameter regularization method,mitigating the overfitting problem during the search process and reducing the error brought about by gradient approximation.Meanwhile,we introduce a natural exponential cosine annealing method to make the learning rate of the neural network training process more suitable for the search procedure.Moreover,group convolution and data augmentation are employed to reduce the computational cost.Finally,through extensive experiments on several public datasets,we demonstrate that our method can more swiftly search for better-performing neural network architectures in a more efficient search space,thus validating the effectiveness of our approach.
基金Supported by the National Natural Science Foundation of China (Grant Nos. 60573012 and 60421001) the National Grand FundamentalResearch 973 Program of China (Grant No. 2002cb312200)
文摘The state space explosion problem is still the key obstacle for applying model checking to systems of industrial size. Abstraction-based methods have been particularly successful in this regard. This paper presents an approach based on refinement of search space partition and abstraction which combines these two techniques for reducing the complexity of model checking. The refinement depends on the representation of each portion of search space. Especially, search space can be refined stepwise to get a better reduction. As reported in the case study, the integration of search space partition and abstraction improves the efficiency of verification with respect to the requirement of memory and obtains significant advantage over the use of each of them in isolation.
基金supported by the National Basic Research Program of China (No.2007CB310602).
文摘A multi-input multi-output(MIMO)detection scheme that requires considerable low complexity but still achieves the near optimal performance is proposed.The fundamental idea of the proposed MIMO detection scheme consists of two points:1)the computational complexity is restrained by a complexity limit in low signal-to-noise ratio(SNR)region;2)while in high SNR region,the complexity is significantly reduced by the proposed search space method.Comparing with existing fixed-complexity techniques of MIMO detection(e.g.,K-best sphere detector and reduced-search maximum-likelihood(RS ML)detection),the significant benefit of proposed detection scheme is that less computational power will be spent for the given data rate,or the throughput of detector can be increased for high SNR cases.According to the simulation results,the near optimal performance can be obtained while the detection complexity is kept considerable small.
文摘In this paper, we use the global search characteristics of genetic algorithms to help search the weight space of the neurons in the cascade-correlation architecture. The cascade-correlation learning architecture is a technique of training and building neural networks that starts with a simple network of neurons and adds additional neurons as they are needed to suit a particular problem. In our approach, instead ofmodifying the genetic algorithm to account for convergence problems, we search the weight-space using the genetic algorithm and then apply the gradient technique of Quickprop to optimize the weights. This hybrid algorithm which is a combination of genetic algorithms and cascade-correlation is applied to the two spirals problem. We also use our algorithm in the prediction of the cyclic oxidation resistance of Ni- and Co-base superalloys.
文摘By extending the Levy wavefunction constrained search to Fock Space,one can define a wavefunction constrained search for electron densities in systems having noninteger number of electrons.For pure-state v-representable densities,the results are equivalent to what one would obtain with the zero-temperature grand canonical ensemble.In other cases,the wavefunction constrained search in Fock space presents an upper bound to the grand canonical ensemble functional.One advantage of the Fock-space wavefunction constrained search functional over the zero-temperature grand-canonical ensemble constrained search functional is that certain specific excited states(i.e.,those that are not ground-statev-representable) are the stationary points of the Fock-space functional.However,a potential disadvantage of the Fock-space constrained search functional is that it is not convex.
