Computer experiments require space-filling designs with good low-dimensional projection *** orthogonal arrays are a type of space-filling design that provides better stratifications in low dimensions than ordinary ort...
详细信息
Computer experiments require space-filling designs with good low-dimensional projection *** orthogonal arrays are a type of space-filling design that provides better stratifications in low dimensions than ordinary orthogonal *** this paper,we address the problem of constructing strong orthogonal arrays and column-orthogonal strong orthogonal arrays of strength two *** methods typically rely on regular designs or specific nonregular designs as base orthogonal arrays,limiting the sizes of the final ***,we propose two general methods that are easy to implement and applicable to a wide range of base orthogonal *** methods produce space-filling designs that can accommodate a large number of factors,provide significant flexibility in terms of run sizes,and possess appealing low-dimensional projection ***,these designs are ideal for computer experiments.
The development of information technology brings diversification of data sources and large-scale data sets and calls for the exploration of distributed learning algorithms. In distributed systems, some local machines ...
详细信息
The development of information technology brings diversification of data sources and large-scale data sets and calls for the exploration of distributed learning algorithms. In distributed systems, some local machines may behave abnormally and send arbitrary information to the central machine(known as Byzantine failures), which can invalidate the distributed algorithms based on the assumption of faultless systems. This paper studies Byzantine-robust distributed algorithms for support vector machines(SVMs) in the context of binary classification. Despite a vast literature on Byzantine problems, much less is known about the theoretical properties of Byzantine-robust SVMs due to their unique challenges. In this paper, we propose two distributed gradient descent algorithms for SVMs. The median and trimmed mean operations in aggregation can effectively defend against Byzantine failures. Theoretically, we show the convergence of the proposed estimators and provide the statistical error rates. After a certain number of iterations, our estimators achieve near-optimal rates. Simulation studies and real data analysis are conducted to demonstrate the performance of the proposed Byzantine-robust distributed algorithms.
We present a novel feature extraction procedure to predict interval-valued time series by combing transfer learning and imaging approaches. Initially, we represent interval-valued time series as a bivariate point-valu...
详细信息
The lamellar microstructure is one of the most typical microstructures of TiAl *** are threeγ/γinterfaces with different microstructures in lamellarγ-TiAl *** this work,we investigated the deformation processes of ...
详细信息
The lamellar microstructure is one of the most typical microstructures of TiAl *** are threeγ/γinterfaces with different microstructures in lamellarγ-TiAl *** this work,we investigated the deformation processes of lamellarγ-TiAl alloys with different interfacial spacing(λ)via uniaxial tensile loading using molecular dynamics simulations,including true twin(TT),pseudo-twin(PT),rotational boundary(RB),and the mixed structure(TT∥PT∥RB).The results show that in all lamellarγ-TiAl samples,the Shockley partial dislocation prefers to nucleate in the region between two neighboring ***,dislocations move towards,crossing theγ/γ***,the dislocation slippage leads to the destruction of the interface,resulting in cracks and structural *** the decrease ofλ,the ultimate strength slightly increases in the TT or PT structure ofγ-TiAl,which follows the Hall-Petch *** in general,the interfacial spacing has a slight effect on the ultimate strengths of these four structures ofγ-TiAl.
Current weakly supervised point cloud semantic segmentation struggles with insufficient utilization of limited annotations in unimodal representation learning due to the sparse and textureless nature of point clouds. ...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
Current weakly supervised point cloud semantic segmentation struggles with insufficient utilization of limited annotations in unimodal representation learning due to the sparse and textureless nature of point clouds. In this work, we leverage cross-modality information by transferring knowledge from image and text sources to the point cloud network. The intuition is that images contribute rich texture, color, and discriminative information, complementing point clouds to boost semantic segmentation performance. To reduce extensive computational resources for cross-modality fusion, we introduce the Multi-Scale Deformable Knowledge Transfer, an innovative training scheme that optimizes and extends the one-to-one mapping to flexible one-to-many relations between multi-modal data. Furthermore, we employ pre-trained image-text models to generate pseudo labels for point clouds and construct positive and negative samples for semantic contrastive regularization, facilitating the full exploitation of unlabeled data. The experimental results evaluated on SemanticKITTI and nuScenes demonstrate substantial improvements, achieving an average gain of 3.8% over the previous weakly supervised methods, and comparable performances to fully supervised approaches.
The V-shaped microcantilever is advantageous for its high sensitivity and low stiffness, making it suitable as an atomic force microscope probe for characterizing the mechanical properties of soft materials. However, ...
详细信息
In this paper, we focus on a class of time-inconsistent stochastic control problems, where the objective function includes the mean and several higher-order central moments of the terminal value of state. To tackle th...
详细信息
In this paper, we introduce a novel high-dimensional Factor-Adjusted sparse Partially Linear regression Model (FAPLM), to integrate the linear effects of high-dimensional latent factors with the nonparametric effects ...
详细信息
The triply periodic minimal surface (TPMS) structures have garnered extensive attention due to their lightweight nature, high strength, vibration and noise reduction capabilities, and exceptional energy absorption per...
详细信息
暂无评论