arXiv subjects

Lei Wang

Publications and source records attributed to Lei Wang.

At least 1,135 records · Page 63Linked to original sources

arXiv2017

A Dwarf-based Scalable Big Data Benchmarking Methodology

Different from the traditional benchmarking methodology that creates a new benchmark or proxy for every possible workload, this paper presents a scalable big data benchmarking methodology. Among a wide variety of big data analytics workloads, we identify eight big data dwarfs, each of which captures the common requirements of each class of unit of computation while being reasonably divorced from individual implementations. We implement the eight dwarfs on different software stacks, e.g., OpenMP, MPI, Hadoop as the dwarf components. For the purpose of architecture simulation, we construct and tune big data proxy benchmarks using the directed acyclic graph (DAG)-like combinations of the dwarf components with different weights to mimic the benchmarks in BigDataBench. Our proxy benchmarks preserve the micro-architecture, memory, and I/O characteristics, and they shorten the simulation time by 100s times while maintain the average micro-architectural data accuracy above 90 percentage on both X86 64 and ARMv8 processors. We will open-source the big data dwarf components and proxy benchmarks soon.

cs.AR↗

arXiv2017

Development and validation of a novel dementia of Alzheimer's type (DAT) score based on metabolism FDG-PET imaging

Fluorodeoxyglucose positron emission tomography (FDG-PET) imaging based 3D topographic brain glucose metabolism patterns from normal controls (NC) and individuals with dementia of Alzheimer's type (DAT) are used to train a novel multi-scale ensemble classification model. This ensemble model outputs a FDG-PET DAT score (FPDS) between 0 and 1 denoting the probability of a subject to be clinically diagnosed with DAT based on their metabolism profile. A novel 7 group image stratification scheme is devised that groups images not only based on their associated clinical diagnosis but also on past and future trajectories of the clinical diagnoses, yielding a more continuous representation of the different stages of DAT spectrum that mimics a real-world clinical setting. The potential for using FPDS as a DAT biomarker was validated on a large number of FDG-PET images (N=2984) obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database taken across the proposed stratification, and a good classification AUC (area under the curve) of 0.78 was achieved in distinguishing between images belonging to subjects on a DAT trajectory and those images taken from subjects not progressing to a DAT diagnosis. Further, the FPDS biomarker achieved state-of-the-art performance on the mild cognitive impairment (MCI) to DAT conversion prediction task with an AUC of 0.81, 0.80, 0.77 for the 2, 3, 5 years to conversion windows respectively.

cs.CV↗

arXiv2017

Isolate First, Then Share: a New OS Architecture for Datacenter Computing

This paper presents the "isolate first, then share" OS model in which the processor cores, memory, and devices are divided up between disparate OS instances and a new abstraction, subOS, is proposed to encapsulate an OS instance that can be created, destroyed, and resized on-the-fly. The intuition is that this avoids shared kernel states between applications, which in turn reduces performance loss caused by contention. We decompose the OS into the supervisor and several subOSes running at the same privilege level: a subOS directly manages physical resources, while the supervisor can create, destroy, resize a subOS on-the-fly. The supervisor and subOSes have few state sharing, but fast inter-subOS communication mechanisms are provided on demand. We present the first implementation, RainForest, which supports unmodified Linux binaries. Our comprehensive evaluation shows RainForest outperforms Linux with four different kernels, LXC, and Xen in terms of worst-case and average performance most of time when running a large number of benchmarks. The source code is available soon.

cs.OS↗

arXiv2017

Ultrafast Graphene Light Emitter

Ultrafast electrically driven nanoscale light sources are critical components in nanophotonics. Compound semiconductor-based light sources for the nanophotonic platforms have been extensively investigated over the past decades. However, monolithic ultrafast light sources with a small footprint remain a challenge. Here, we demonstrate electrically driven ultrafast graphene light emitters that achieve light pulse generation with up to 10 GHz bandwidth, across a broad spectral range from the visible to the near-infrared. The fast response results from ultrafast charge carrier dynamics in graphene, and weak electron-acoustic phonon-mediated coupling between the electronic and lattice degrees of freedom. We also find that encapsulating graphene with hexagonal boron nitride (hBN) layers strongly modifies the emission spectrum by changing the local optical density of states, thus providing up to 460 % enhancement compared to the grey-body thermal radiation for a broad peak centered at 720 nm. Furthermore, the hBN encapsulation layers permit stable and bright visible thermal radiation with electronic temperatures up to 2,000 K under ambient conditions, as well as efficient ultrafast electronic cooling via near-field coupling to hybrid polaritonic modes. These high-speed graphene light emitters provide a promising path for on-chip light sources for optical communications and other optoelectronic applications.

cond-mat.mes-hall↗

arXiv2017

Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks

Traditionally, multi-layer neural networks use dot product between the output vector of previous layer and the incoming weight vector as the input to activation function. The result of dot product is unbounded, thus increases the risk of large variance. Large variance of neuron makes the model sensitive to the change of input distribution, thus results in poor generalization, and aggravates the internal covariate shift which slows down the training. To bound dot product and decrease the variance, we propose to use cosine similarity or centered cosine similarity (Pearson Correlation Coefficient) instead of dot product in neural networks, which we call cosine normalization. We compare cosine normalization with batch, weight and layer normalization in fully-connected neural networks as well as convolutional networks on the data sets of MNIST, 20NEWS GROUP, CIFAR-10/100 and SVHN. Experiments show that cosine normalization achieves better performance than other normalization techniques.

cs.LG↗

arXiv2017

Quantum phase transitions of multi-species Dirac fermions

We use the determinant Quantum Monte Carlo method (DQMC) to study the interaction-driven semimetal to antiferromagnetic insulator transition in a $π$-flux Hamiltonian with modulated hoppings, a model which has two species of Dirac fermions. It is found that the critical interaction strength $U_c$ is decreased by reducing the velocity of the outer Dirac cone, while the inner cone velocity fixes the band width. Although $U_c$ is monotonic, at fixed inverse temperature $β$ the antiferromagnetic (AF) structure factor has a maximum as a function of the hopping modulation. We also study the corresponding strong coupling (Heisenberg model) limit, where the sublattice magnetization is enhanced by the alternation of the exchange couplings. The AF order is shown to be non-monotonic, and maximal at an intermediate degree of anisotropy, in qualitative agreement with the Hubbard model. These results quantify the effect of the velocities on the critical interaction strength in Dirac fermion systems and enable an additional degree of control which will be useful in studying strong correlation physics in ultracold atoms in optical lattices.

cond-mat.str-el↗

arXiv2017

When Traffic Flow Prediction Meets Wireless Big Data Analytics

Traffic flow prediction is an important research issue for solving the traffic congestion problem in an Intelligent Transportation System (ITS). Traffic congestion is one of the most serious problems in a city, which can be predicted in advance by analyzing traffic flow patterns. Such prediction is possible by analyzing the real-time transportation data from correlative roads and vehicles. This article first gives a brief introduction to the transportation data, and surveys the state-of-the-art prediction methods. Then, we verify whether or not the prediction performance is able to be improved by fitting actual data to optimize the parameters of the prediction model which is used to predict the traffic flow. Such verification is conducted by comparing the optimized time series prediction model with the normal time series prediction model. This means that in the era of big data, accurate use of the data becomes the focus of studying the traffic flow prediction to solve the congestion problem. Finally, experimental results of a case study are provided to verify the existence of such performance improvement, while the research challenges of this data-analytics-based prediction are presented and discussed.

cs.AI↗

arXiv2017

Universal Boundary Entropies in Conformal Field Theory: A Quantum Monte Carlo Study

Recently, entropy corrections on nonorientable manifolds such as the Klein bottle are proposed as a universal characterization of critical systems with an emergent conformal field theory (CFT). We show that entropy correction on the Klein bottle can be interpreted as a boundary effect via transforming the Klein bottle into an orientable manifold with nonlocal boundary interactions. The interpretation reveals the conceptual connection of the Klein bottle entropy with the celebrated Affleck-Ludwig entropy in boundary CFT. We propose a generic scheme to extract these universal boundary entropies from quantum Monte Carlo calculation of partition function ratios in lattice models. Our numerical results on the Affleck-Ludwig entropy and Klein bottle entropy for the $q$-state quantum Potts chains with $q=2,3$ show excellent agreement with the CFT predictions. For the quantum Potts chain with $q=4$, the Klein bottle entropy slightly deviates from the CFT prediction, which is possibly due to marginally irrelevant terms in the low-energy effective theory.

cond-mat.str-el↗

arXiv2017

Conformal Thermal Tensor Network and Universal Entropy on Topological Manifolds

Partition functions of quantum critical systems, expressed as conformal thermal tensor networks, are defined on various manifolds which can give rise to universal entropy corrections. Through high-precision tensor network simulations of several quantum chains, we identify the universal entropy $S_{\mathcal{K}} = \ln{k}$ on the Klein bottle, where $k$ relates to quantum dimensions of the primary fields in conformal field theory (CFT). Different from the celebrated Affleck-Ludwig boundary entropy $\ln{g}$ ($g$ reflects non-integer groundstate degeneracy), $S_{\mathcal{K}}$ has \textit{no} boundary dependence or surface energy terms accompanied, and can be very conveniently extracted from thermal data. On the Möbius-strip manifold, we uncover an entropy $S_{\mathcal{M}} = \frac{1}{2} (\ln{g} + \ln{k})$ in CFT, where $\frac{1}{2} \ln{g}$ is associated with the only open edge of the Möbius strip, and $\frac{1}{2} \ln{k}$ with the non-orientable topology. We employ $S_{\mathcal{K}}$ to accurately pinpoint the quantum phase transitions, even for those without local order parameters.

cond-mat.str-el↗

arXiv2017

Machine Learning for Large-Scale Quality Control of 3D Shape Models in Neuroimaging

As very large studies of complex neuroimaging phenotypes become more common, human quality assessment of MRI-derived data remains one of the last major bottlenecks. Few attempts have so far been made to address this issue with machine learning. In this work, we optimize predictive models of quality for meshes representing deep brain structure shapes. We use standard vertex-wise and global shape features computed homologously across 19 cohorts and over 7500 human-rated subjects, training kernelized Support Vector Machine and Gradient Boosted Decision Trees classifiers to detect meshes of failing quality. Our models generalize across datasets and diseases, reducing human workload by 30-70\%, or equivalently hundreds of human rater hours for datasets of comparable size, with recall rates approaching inter-rater reliability.

q-bio.QM↗

arXiv2017

On methods to determine bounds on the Q-factor for a given directivity

This paper revisit and extend the interesting case of bounds on the Q-factor for a given directivity for a small antenna of arbitrary shape. A higher directivity in a small antenna is closely connected with a narrow impedance bandwidth. The relation between bandwidth and a desired directivity is still not fully understood, not even for small antennas. Initial investigations in this direction has related the radius of a circumscribing sphere to the directivity, and bounds on the Q-factor has also been derived for a partial directivity in a given direction. In this paper we derive lower bounds on the Q-factor for a total desired directivity for an arbitrarily shaped antenna in a given direction as a convex problem using semi-definite relaxation techniques (SDR). We also show that the relaxed solution is also a solution of the original problem of determining the lower Q-factor bound for a total desired directivity. SDR can also be used to relax a class of other interesting non-convex constraints in antenna optimization such as tuning, losses, front-to-back ratio. We compare two different new methods to determine the lowest Q-factor for arbitrary shaped antennas for a given total directivity. We also compare our results with full EM-simulations of a parasitic element antenna with high directivity.

physics.class-ph↗

arXiv2017

Study of the Magnetizing Relationship of the Kickers for CSNS

The extraction system of CSNS mainly consists of two kinds of magnets: eight kickers and one lambertson magnet. In this paper, firstly, the magnetic test results of the eight kickers were introduced and then the filed uniformity and magnetizing relationship of the kickers were given. Secondly, during the beam commissioning in the future, in order to obtain more accurate magnetizing relationship, a new method to measure the magnetizing coefficients of the kickers by the real extraction beam was given and the data analysis would also be processed.

physics.acc-ph↗

arXiv2017

Ising Antiferromagnet in the 2D Hubbard Model with Mismatched Fermi Surfaces

We study the phase diagram of the two-dimensional repulsive Hubbard model with spin-dependent anisotropic hopping at half-filling. The system develops Ising antiferromagnetic long-range order already at infinitesimal repulsive interaction strength in the ground state. Outside the perturbative regime, unbiased predictions for the critical temperatures of the Ising antiferromagnet are made for representative interaction values by a variety of state-of-the-art quantum Monte Carlo methods, including the diagrammatic Monte Carlo, continuous-time determinantal Monte Carlo and path-integral Monte Carlo methods. Our findings are relevant to ultracold atom experiments in the p-orbital or with spin-dependent optical lattices.

cond-mat.str-el↗

arXiv2017

A Two-element Parasitic Antenna Approaching the Minimum Q-factor at a Given Directivity

In this paper we investigate a super-directive antenna based on a parasitic structure with a circumscribing sphere of diameter 69 mm corresponding to 0.2$λ$@880 MHz. The antenna is modeled, simulated, measured, and it is also evaluated against the new Q-factor bound for small antennas at a given total directivity. A maximum directivity of 7.2 dBi is measured with a radiation efficiency of -6.5 dB at 876 MHz. An intermediate directivity of 6.2 dBi is observed at 880 MHz with 20 dB front-to-back ratio and -7 dB radiation efficiency. The antenna performs well with respect to the developed fundamental bound. The results is promising for applications that require miniaturization and spatial filtering. The above antenna properties are robust and we show with measurements that the antenna preform well also when it is integrated as an autonomous unit.

physics.app-ph↗

arXiv2017

$h\toμτ$ and muon g-2 in the alignment limit of two-Higgs-doublet model

We examine the $h\to μτ$ and muon g-2 in the exact alignment limit of two-Higgs-doublet model. In this case, the couplings of the SM-like Higgs to the SM particles are the same as the Higgs couplings in the SM at the tree level, and the tree-level lepton-flavor-violating coupling $hμτ$ is absent. We assume the lepton-flavor-violating $μτ$ excess observed by CMS to be respectively from the other neutral Higgses, $H$ and $A$, which almost degenerates with the SM-like Higgs at the 125 GeV. After imposing the relevant theoretical constraints and experimental constraints from the precision electroweak data, $B$-meson decays, $τ$ decays and Higgs searches, we find that the muon g-2 anomaly and $μτ$ excess favor the small lepton Yukawa coupling and top Yukawa coupling of the non-SM-like Higgs around 125 GeV, and the lepton-flavor-violating coupling is sensitive to another heavy neutral Higgs mass. In addition, if the $μτ$ excess is from $H$ around 125 GeV, the experimental data of the heavy Higgs decaying into $μτ$ favor $m_A>230$ GeV for a relatively large $H\bar{t}t$ coupling.

hep-ph↗

arXiv2017

Training Triplet Networks with GAN

Triplet networks are widely used models that are characterized by good performance in classification and retrieval tasks. In this work we propose to train a triplet network by putting it as the discriminator in Generative Adversarial Nets (GANs). We make use of the good capability of representation learning of the discriminator to increase the predictive quality of the model. We evaluated our approach on Cifar10 and MNIST datasets and observed significant improvement on the classification performance using the simple k-nn method.

cs.LG↗

arXiv2017

Two-Higgs-doublet model of type-II confronted with the LHC run-I and run-II data

We examine the parameter space of two-Higgs-doublet model of type-II after imposing the relevant theoretical and experimental constraints from the precision electroweak data, $B$-meson decays, the LHC run-I and run-II data. We find that the searches for Higgs via the $τ\barτ,~WW,~ZZ,γγ,~hh,~hZ,~HZ,~AZ$ channels can give strong constraints on the CP-odd Higgs $A$ and heavy CP-even Higgs $H$, and the parameter space excluded by each channel is respectively carved out in detail. The surviving samples are discussed in two different of regions: (i) In the SM-like coupling region of the 125 GeV Higgs, $m_A$ is allowed to be as low as 350 GeV, and $\tanβ$ is imposed a strong upper limit. $m_H$ is allowed to be as low as 200 GeV for the proper $\tanβ$, $\sin(β-α)$ and $m_A$, but is required to be larger than 300 GeV for $m_A=700$ GeV. (ii) In the wrong sign Yukawa coupling of the 125 GeV, $\tanβ$ and $\sin(β-α)$ can be imposed upper limits by $b\bar{b}\to A/H\to τ\barτ$ channel and lower limits by the $A\to hZ$ channel. $m_A$ and $m_H$ are respectively allowed to be as low as 60 GeV and 200 GeV, but 320 GeV $< m_A<$ 500 GeV is excluded for $m_H=$ 700 GeV.

hep-ph↗

arXiv2017

10-millisecond Computing

Despite computation becomes much complex on data with an unprecedented scale, we argue computers or smart devices should and will consistently provide information and knowledge to human being in the order of a few tens milliseconds. We coin a new term 10-millisecond computing to call attention to this class of workloads. 10-millisecond computing raises many challenges for both software and hardware stacks. In this paper, using a typical workload-memcached on a 40-core server (a main-stream server in near future), we quantitatively measure 10-ms computing's challenges to conventional operating systems. For better communication, we propose a simple metric-outlier proportion to measure quality of service: for N completed requests or jobs, if M jobs or requests' latencies exceed the outlier threshold t, the outlier proportion is M/N . For a 1K-scale system running Linux (version 2.6.32), LXC (version 0.7.5) or XEN (version 4.0.0), respectively, we surprisingly find that so as to reduce the service outlier proportion to 10% (10% users will feel QoS degradation), the outlier proportion of a single server has to be reduced by 871X, 2372X, 2372X accordingly. Also, we discuss the possible design spaces of 10-ms computing systems from perspectives of datacenter architectures, networking, OS and scheduling, and benchmarking.

cs.PF↗