arXiv subjects

Yan Wang

Publications and source records attributed to Yan Wang.

At least 865 records · Page 48Linked to original sources

arXiv2021

Resilient quantum gates on periodically driven Rydberg atoms

Fault-tolerant implementation of quantum gates is one of preconditions for realizing quantum computation. The platform of Rydberg atoms is one of the most promising candidates for achieving quantum computation. We propose to implement a controlled-$Z$ gate on Rydberg atoms where an amplitude-modulated field is employed to induce Rydberg antiblockade. Gate robustness against the fluctuations in the Rydberg-Rydberg interaction can be largely enhanced by adjusting amplitude-modulated field. Furthermore, we introduce a Landau-Zener-Stückelberg transition on the target atom so as to improve the gate resilience to the deviation in the gate time and the drift in the pulse amplitude. With feasible experimental parameters, one can achieve the gate with low fidelity errors caused by atomic decay, interatomic dipole-dipole force, and Doppler effects. Finally, we generalize the gate scheme into multiqubit cases, where resilient multiqubit phase gates can be obtained in one step with an unchanged gate time as the number of qubits increases.

quant-ph↗

arXiv2021

A Two Sub-problem Decomposition for the Optimal Design of Filterless Optical Networks

Filterless optical transport networks relies on passive optical interconnections between nodes, i.e., on splitters/couplers and amplifiers. While different studies have investigated their design, none of them offer a solution for an optimal design. We propose a one step solution scheme, which combines network provisioning, i.e., routing and wavelength assignment within a single mathematical model. Decomposition into two different types sub-problems is then used in order to conceive an exact solution scheme. The first type of subproblem relies on the generation of filterless subnetworks while the second one takes care of their wavelength assignment. Numerical experiments demonstrate the improved performance of the proposed optimization model and algorithm over the state of the art, with the improvement of the solution for several open source data sets.

cs.NI↗

arXiv2021

Sub-Gaussian Error Bounds for Hypothesis Testing

We interpret likelihood-based test functions from a geometric perspective where the Kullback-Leibler (KL) divergence is adopted to quantify the distance from a distribution to another. Such a test function can be seen as a sub-Gaussian random variable, and we propose a principled way to calculate its corresponding sub-Gaussian norm. Then an error bound for binary hypothesis testing can be obtained in terms of the sub-Gaussian norm and the KL divergence, which is more informative than Pinsker's bound when the significance level is prescribed. For $M$-ary hypothesis testing, we also derive an error bound which is complementary to Fano's inequality by being more informative when the number of hypotheses or the sample size is not large.

cs.IT↗

arXiv2021

A Dual-Dimer Method for Training Physics-Constrained Neural Networks with Minimax Architecture

Data sparsity is a common issue to train machine learning tools such as neural networks for engineering and scientific applications, where experiments and simulations are expensive. Recently physics-constrained neural networks (PCNNs) were developed to reduce the required amount of training data. However, the weights of different losses from data and physical constraints are adjusted empirically in PCNNs. In this paper, a new physics-constrained neural network with the minimax architecture (PCNN-MM) is proposed so that the weights of different losses can be adjusted systematically. The training of the PCNN-MM is searching the high-order saddle points of the objective function. A novel saddle point search algorithm called Dual-Dimer method is developed. It is demonstrated that the Dual-Dimer method is computationally more efficient than the gradient descent ascent method for nonconvex-nonconcave functions and provides additional eigenvalue information to verify search results. A heat transfer example also shows that the convergence of PCNN-MMs is faster than that of traditional PCNNs.

cs.LG↗

arXiv2020

DSU-net: Dense SegU-net for automatic head-and-neck tumor segmentation in MR images

Precise and accurate segmentation of the most common head-and-neck tumor, nasopharyngeal carcinoma (NPC), in MRI sheds light on treatment and regulatory decisions making. However, the large variations in the lesion size and shape of NPC, boundary ambiguity, as well as the limited available annotated samples conspire NPC segmentation in MRI towards a challenging task. In this paper, we propose a Dense SegU-net (DSU-net) framework for automatic NPC segmentation in MRI. Our contribution is threefold. First, different from the traditional decoder in U-net using upconvolution for upsamling, we argue that the restoration from low resolution features to high resolution output should be capable of preserving information significant for precise boundary localization. Hence, we use unpooling to unsample and propose SegU-net. Second, to combat the potential vanishing-gradient problem, we introduce dense blocks which can facilitate feature propagation and reuse. Third, using only cross entropy (CE) as loss function may bring about troubles such as miss-prediction, therefore we propose to use a loss function comprised of both CE loss and Dice loss to train the network. Quantitative and qualitative comparisons are carried out extensively on in-house datasets, the experimental results show that our proposed architecture outperforms the existing state-of-the-art segmentation networks.

eess.IV↗

arXiv2020

A multi-objective optimization framework for on-line ridesharing systems

The ultimate goal of ridesharing systems is to matchtravelers who do not have a vehicle with those travelers whowant to share their vehicle. A good match can be found amongthose who have similar itineraries and time schedules. In thisway each rider can be served without any delay and also eachdriver can earn as much as possible without having too muchdeviation from their original route. We propose an algorithmthat leverages biogeography-based optimization to solve a multi-objective optimization problem for online ridesharing. It isnecessary to solve the ridesharing problem as a multi-objectiveproblem since there are some important objectives that must beconsidered simultaneously. We test our algorithm by evaluatingperformance on the Beijing ridesharing dataset. The simulationresults indicate that BBO provides competitive performancerelative to state-of-the-art ridesharing optimization algorithms.

math.OC↗

arXiv2020

Optimizing orbits for TianQin

TianQin is a geocentric space-based gravitational-wave observatory mission consisting of three drag-free controlled satellites in an equilateral triangle with an orbital radius of $ 10^{5}$ km. The constellation faces the white-dwarf binary RX J0806.3+1527 located slightly below the ecliptic plane, and is subject to gravitational perturbations that can distort the formation. In this study, we present combined methods to optimize the TianQin orbits so that a set of 5-year stability requirements can be met. Moreover, we discuss slow long-term drift of the detector pointing due to orbital precession, and put forward stable orbits with six other pointings along the lunar orbital plane. Some implications of the findings are pointed out.

gr-qc↗

arXiv2020

Inter-slice Context Residual Learning for 3D Medical Image Segmentation

Automated and accurate 3D medical image segmentation plays an essential role in assisting medical professionals to evaluate disease progresses and make fast therapeutic schedules. Although deep convolutional neural networks (DCNNs) have widely applied to this task, the accuracy of these models still need to be further improved mainly due to their limited ability to 3D context perception. In this paper, we propose the 3D context residual network (ConResNet) for the accurate segmentation of 3D medical images. This model consists of an encoder, a segmentation decoder, and a context residual decoder. We design the context residual module and use it to bridge both decoders at each scale. Each context residual module contains both context residual mapping and context attention mapping, the formal aims to explicitly learn the inter-slice context information and the latter uses such context as a kind of attention to boost the segmentation accuracy. We evaluated this model on the MICCAI 2018 Brain Tumor Segmentation (BraTS) dataset and NIH Pancreas Segmentation (Pancreas-CT) dataset. Our results not only demonstrate the effectiveness of the proposed 3D context residual learning scheme but also indicate that the proposed ConResNet is more accurate than six top-ranking methods in brain tumor segmentation and seven top-ranking methods in pancreas segmentation. Code is available at https://git.io/ConResNet

eess.IV↗

arXiv2020

Deep Learning Analysis and Age Prediction from Shoeprints

Human walking and gaits involve several complex body parts and are influenced by personality, mood, social and cultural traits, and aging. These factors are reflected in shoeprints, which in turn can be used to predict age, a problem not systematically addressed using any computational approach. We collected 100,000 shoeprints of subjects ranging from 7 to 80 years old and used the data to develop a deep learning end-to-end model ShoeNet to analyze age-related patterns and predict age. The model integrates various convolutional neural network models together using a skip mechanism to extract age-related features, especially in pressure and abrasion regions from pair-wise shoeprints. The results show that 40.23% of the subjects had prediction errors within 5-years of age and the prediction accuracy for gender classification reached 86.07%. Interestingly, the age-related features mostly reside in the asymmetric differences between left and right shoeprints. The analysis also reveals interesting age-related and gender-related patterns in the pressure distributions on shoeprints; in particular, the pressure forces spread from the middle of the toe toward outside regions over age with gender-specific variations on heel regions. Such statistics provide insight into new methods for forensic investigations, medical studies of gait-pattern disorders, biometrics, and sport studies.

cs.CV↗

arXiv2020

Gravitational waveforms from the quasicircular inspiral of compact binaries in massive Brans-Dicke theory

We study the gravitational waves emitted by an inspiralling compact binary system in massive Brans-Dicke theory. In addition to the two tensor polarizations, which have been obtained in the previous work, we calculate explicitly and analytically the expressions for the time-domain waveforms of the two scalar polarizations. With the stationary phase approximations, we obtain the Fourier transforms of the two tensor polarizations. We find that when the scalar field is light, the waveforms can be mapped to the parametrized post-Einsteinian (ppE) framework and we identify the ppE parameters. However, when the scalar field is heavy, the ppE framework is not applicable. We also obtain the projected constraints on the parameters of this theory by gravitational wave observations of future ground-based detectors. Finally, we apply our result to the model proposed by Damour and Esposito-Farèse, $f(R)$ gravity, and screened modified gravity.

gr-qc↗

arXiv2020

Sub-Gaussian and subexponential fluctuation-response inequalities

Sub-Gaussian and subexponential distributions are introduced and applied to study the fluctuation-response relation out of equilibrium. A bound on the difference in expected values of an arbitrary sub-Gaussian or subexponential physical quantity is established in terms of its sub-Gaussian or subexponential norm. Based on that, we find that the entropy difference between two states is bounded by the energy fluctuation in these states. Moreover, we obtain generalized versions of the thermodynamic uncertainty relation in different regimes. Operational issues concerning the application of our results in an experimental setting are also addressed, and nonasymptotic bounds on the errors incurred by using the sample mean instead of the expected value in our fluctuation-response inequalities are derived.

cond-mat.stat-mech↗

arXiv2020

Rotated Binary Neural Network

Binary Neural Network (BNN) shows its predominance in reducing the complexity of deep neural networks. However, it suffers severe performance degradation. One of the major impediments is the large quantization error between the full-precision weight vector and its binary vector. Previous works focus on compensating for the norm gap while leaving the angular bias hardly touched. In this paper, for the first time, we explore the influence of angular bias on the quantization error and then introduce a Rotated Binary Neural Network (RBNN), which considers the angle alignment between the full-precision weight vector and its binarized version. At the beginning of each training epoch, we propose to rotate the full-precision weight vector to its binary vector to reduce the angular bias. To avoid the high complexity of learning a large rotation matrix, we further introduce a bi-rotation formulation that learns two smaller rotation matrices. In the training stage, we devise an adjustable rotated weight vector for binarization to escape the potential local optimum. Our rotation leads to around 50% weight flips which maximize the information gain. Finally, we propose a training-aware approximation of the sign function for the gradient backward. Experiments on CIFAR-10 and ImageNet demonstrate the superiorities of RBNN over many state-of-the-arts. Our source code, experimental settings, training logs and binary models are available at https://github.com/lmbxmu/RBNN.

cs.CV↗

arXiv2020

ASMFS: Adaptive-Similarity-based Multi-modality Feature Selection for Classification of Alzheimer's Disease

With the increasing amounts of high-dimensional heterogeneous data to be processed, multi-modality feature selection has become an important research direction in medical image analysis. Traditional methods usually depict the data structure using fixed and predefined similarity matrix for each modality separately, without considering the potential relationship structure across different modalities. In this paper, we propose a novel multi-modality feature selection method, which performs feature selection and local similarity learning simultaniously. Specially, a similarity matrix is learned by jointly considering different imaging modalities. And at the same time, feature selection is conducted by imposing sparse l_{2, 1} norm constraint. The effectiveness of our proposed joint learning method can be well demonstrated by the experimental results on Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, which outperforms existing the state-of-the-art multi-modality approaches.

cs.CV↗

arXiv2020

The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection

Response selection plays a vital role in building retrieval-based conversation systems. Despite that response selection is naturally a learning-to-rank problem, most prior works take a point-wise view and train binary classifiers for this task: each response candidate is labeled either relevant (one) or irrelevant (zero). On the one hand, this formalization can be sub-optimal due to its ignorance of the diversity of response quality. On the other hand, annotating grayscale data for learning-to-rank can be prohibitively expensive and challenging. In this work, we show that grayscale data can be automatically constructed without human effort. Our method employs off-the-shelf response retrieval models and response generation models as automatic grayscale data generators. With the constructed grayscale data, we propose multi-level ranking objectives for training, which can (1) teach a matching model to capture more fine-grained context-response relevance difference and (2) reduce the train-test discrepancy in terms of distractor strength. Our method is simple, effective, and universal. Experiments on three benchmark datasets and four state-of-the-art matching models show that the proposed approach brings significant and consistent performance improvements.

cs.CL↗

arXiv2020

Stratified and Time-aware Sampling based Adaptive Ensemble Learning for Streaming Recommendations

Recommender systems have played an increasingly important role in providing users with tailored suggestions based on their preferences. However, the conventional offline recommender systems cannot handle the ubiquitous data stream well. To address this issue, Streaming Recommender Systems (SRSs) have emerged in recent years, which incrementally train recommendation models on newly received data for effective real-time recommendations. Focusing on new data only benefits addressing concept drift, i.e., the changing user preferences towards items. However, it impedes capturing long-term user preferences. In addition, the commonly existing underload and overload problems should be well tackled for higher accuracy of streaming recommendations. To address these problems, we propose a Stratified and Time-aware Sampling based Adaptive Ensemble Learning framework, called STS-AEL, to improve the accuracy of streaming recommendations. In STS-AEL, we first devise stratified and time-aware sampling to extract representative data from both new data and historical data to address concept drift while capturing long-term user preferences. Also, incorporating the historical data benefits utilizing the idle resources in the underload scenario more effectively. After that, we propose adaptive ensemble learning to efficiently process the overloaded data in parallel with multiple individual recommendation models, and then effectively fuse the results of these models with a sequential adaptive mechanism. Extensive experiments conducted on three real-world datasets demonstrate that STS-AEL, in all the cases, significantly outperforms the state-of-the-art SRSs.

cs.IR↗

arXiv2020

A Deep Framework for Cross-Domain and Cross-System Recommendations

Cross-Domain Recommendation (CDR) and Cross-System Recommendations (CSR) are two of the promising solutions to address the long-standing data sparsity problem in recommender systems. They leverage the relatively richer information, e.g., ratings, from the source domain or system to improve the recommendation accuracy in the target domain or system. Therefore, finding an accurate mapping of the latent factors across domains or systems is crucial to enhancing recommendation accuracy. However, this is a very challenging task because of the complex relationships between the latent factors of the source and target domains or systems. To this end, in this paper, we propose a Deep framework for both Cross-Domain and Cross-System Recommendations, called DCDCSR, based on Matrix Factorization (MF) models and a fully connected Deep Neural Network (DNN). Specifically, DCDCSR first employs the MF models to generate user and item latent factors and then employs the DNN to map the latent factors across domains or systems. More importantly, we take into account the rating sparsity degrees of individual users and items in different domains or systems and use them to guide the DNN training process for utilizing the rating data more effectively. Extensive experiments conducted on three real-world datasets demonstrate that DCDCSR framework outperforms the state-of-the-art CDR and CSR approaches in terms of recommendation accuracy.

cs.LG↗

arXiv2020

Double-Wing Mixture of Experts for Streaming Recommendations

Streaming Recommender Systems (SRSs) commonly train recommendation models on newly received data only to address user preference drift, i.e., the changing user preferences towards items. However, this practice overlooks the long-term user preferences embedded in historical data. More importantly, the common heterogeneity in data stream greatly reduces the accuracy of streaming recommendations. The reason is that different preferences (or characteristics) of different types of users (or items) cannot be well learned by a unified model. To address these two issues, we propose a Variational and Reservoir-enhanced Sampling based Double-Wing Mixture of Experts framework, called VRS-DWMoE, to improve the accuracy of streaming recommendations. In VRS-DWMoE, we first devise variational and reservoir-enhanced sampling to wisely complement new data with historical data, and thus address the user preference drift issue while capturing long-term user preferences. After that, we propose a Double-Wing Mixture of Experts (DWMoE) model to first effectively learn heterogeneous user preferences and item characteristics, and then make recommendations based on them. Specifically, DWMoE contains two Mixture of Experts (MoE, an effective ensemble learning model) to learn user preferences and item characteristics, respectively. Moreover, the multiple experts in each MoE learn the preferences (or characteristics) of different types of users (or items) where each expert specializes in one underlying type. Extensive experiments demonstrate that VRS-DWMoE consistently outperforms the state-of-the-art SRSs.

cs.IR↗

arXiv2020

Developing and Improving Risk Models using Machine-learning Based Algorithms

The objective of this study is to develop a good risk model for classifying business delinquency by simultaneously exploring several machine learning based methods including regularization, hyper-parameter optimization, and model ensembling algorithms. The rationale under the analyses is firstly to obtain good base binary classifiers (include Logistic Regression ($LR$), K-Nearest Neighbors ($KNN$), Decision Tree ($DT$), and Artificial Neural Networks ($ANN$)) via regularization and appropriate settings of hyper-parameters. Then two model ensembling algorithms including bagging and boosting are performed on the good base classifiers for further model improvement. The models are evaluated using accuracy, Area Under the Receiver Operating Characteristic Curve (AUC of ROC), recall, and F1 score via repeating 10-fold cross-validation 10 times. The results show the optimal base classifiers along with the hyper-parameter settings are $LR$ without regularization, $KNN$ by using 9 nearest neighbors, $DT$ by setting the maximum level of the tree to be 7, and $ANN$ with three hidden layers. Bagging on $KNN$ with $K$ valued 9 is the optimal model we can get for risk classification as it reaches the average accuracy, AUC, recall, and F1 score valued 0.90, 0.93, 0.82, and 0.89, respectively.

cs.LG↗