arXiv subjects

Jie Liu

Publications and source records attributed to Jie Liu.

At least 469 records · Page 26Linked to original sources

arXiv2022

An Improved Structured Mesh Generation Method Based on Physics-informed Neural Networks

Mesh generation remains a key technology in many areas where numerical simulations are required. As numerical algorithms become more efficient and computers become more powerful, the percentage of time devoted to mesh generation becomes higher. In this paper, we present an improved structured mesh generation method. The method formulates the meshing problem as a global optimization problem related to a physics-informed neural network. The mesh is obtained by intelligently solving the physical boundary-constrained partial differential equations. To improve the prediction accuracy of the neural network, we also introduce a novel auxiliary line strategy and an efficient network model during meshing. The strategy first employs a priori auxiliary lines to provide ground truth data and then uses these data to construct a loss term to better constrain the convergence of the subsequent training. The experimental results indicate that the proposed method is effective and robust. It can accurately approximate the mapping (transformation) from the computational domain to the physical domain and enable fast high-quality structured mesh generation.

cs.GR↗

arXiv2022

Merlin HugeCTR: GPU-accelerated Recommender System Training and Inference

In this talk, we introduce Merlin HugeCTR. Merlin HugeCTR is an open source, GPU-accelerated integration framework for click-through rate estimation. It optimizes both training and inference, whilst enabling model training at scale with model-parallel embeddings and data-parallel neural networks. In particular, Merlin HugeCTR combines a high-performance GPU embedding cache with an hierarchical storage architecture, to realize low-latency retrieval of embeddings for online model inference tasks. In the MLPerf v1.0 DLRM model training benchmark, Merlin HugeCTR achieves a speedup of up to 24.6x on a single DGX A100 (8x A100) over PyTorch on 4x4-socket CPU nodes (4x4x28 cores). Merlin HugeCTR can also take advantage of multi-node environments to accelerate training even further. Since late 2021, Merlin HugeCTR additionally features a hierarchical parameter server (HPS) and supports deployment via the NVIDIA Triton server framework, to leverage the computational capabilities of GPUs for high-speed recommendation model inference. Using this HPS, Merlin HugeCTR users can achieve a 5~62x speedup (batch size dependent) for popular recommendation models over CPU baseline implementations, and dramatically reduce their end-to-end inference latency.

cs.DC↗

arXiv2022

Intense X-ray laser-induced proton emission from halo nuclei

We investigate the intense X-ray laser-induced proton emission from halo nuclei within the framework of a nonperturbative quantum $S$-matrix approach. We have analytically deduced the angular differential as well as the total multi-photon rates of the proton emissions. For a linearly polarized X-ray laser field, we find that the angular distributions of proton emission sensitively depend on the laser frequency and show an interesting petal structure with increasing the laser frequency as well as the number of absorbed photons. Meanwhile, we find the Coulomb repulsion potential between the proton and the remainder nucleus has a strong hindering effect on the total multi-photon rates of the proton emissions and leads to the blue shifts of the multi-photon transition frequency. Moreover, the polarization effects of laser fields on total rates of proton emission have also been addressed. We find that the polarized ellipticity corresponding to the maximum of the total rates depend on the laser frequency showing a transition from perturbative to nonperturbative proton emission. The underlying mechanism of the above findings is uncovered, and some implications are discussed.

nucl-th↗

arXiv2022

Multi-Scale Wavelet Transformer for Face Forgery Detection

Currently, many face forgery detection methods aggregate spatial and frequency features to enhance the generalization ability and gain promising performance under the cross-dataset scenario. However, these methods only leverage one level frequency information which limits their expressive ability. To overcome these limitations, we propose a multi-scale wavelet transformer framework for face forgery detection. Specifically, to take full advantage of the multi-scale and multi-frequency wavelet representation, we gradually aggregate the multi-scale wavelet representation at different stages of the backbone network. To better fuse the frequency feature with the spatial features, frequency-based spatial attention is designed to guide the spatial feature extractor to concentrate more on forgery traces. Meanwhile, cross-modality attention is proposed to fuse the frequency features with the spatial features. These two attention modules are calculated through a unified transformer block for efficiency. A wide variety of experiments demonstrate that the proposed method is efficient and effective for both within and cross datasets.

cs.CV↗

arXiv2022

Boost CTR Prediction for New Advertisements via Modeling Visual Content

Existing advertisements click-through rate (CTR) prediction models are mainly dependent on behavior ID features, which are learned based on the historical user-ad interactions. Nevertheless, behavior ID features relying on historical user behaviors are not feasible to describe new ads without previous interactions with users. To overcome the limitations of behavior ID features in modeling new ads, we exploit the visual content in ads to boost the performance of CTR prediction models. Specifically, we map each ad into a set of visual IDs based on its visual content. These visual IDs are further used for generating the visual embedding for enhancing CTR prediction models. We formulate the learning of visual IDs into a supervised quantization problem. Due to a lack of class labels for commercial images in advertisements, we exploit image textual descriptions as the supervision to optimize the image extractor for generating effective visual IDs. Meanwhile, since the hard quantization is non-differentiable, we soften the quantization operation to make it support the end-to-end network training. After mapping each image into visual IDs, we learn the embedding for each visual ID based on the historical user-ad interactions accumulated in the past. Since the visual ID embedding depends only on the visual content, it generalizes well to new ads. Meanwhile, the visual ID embedding complements the ad behavior ID embedding. Thus, it can considerably boost the performance of the CTR prediction models previously relying on behavior ID features for both new ads and ads that have accumulated rich user behaviors. After incorporating the visual ID embedding in the CTR prediction model of Baidu online advertising, the average CTR of ads improves by 1.46%, and the total charge increases by 1.10%.

cs.IR↗

arXiv2022

Fishbone resonance structure in the attosecond transient absorption spectroscopy of graphene

We investigate the attosecond transient absorption spectroscopy (ATAS) of graphene by numerically solving four-band density-matrix equations, which demonstrates apparent fish bone resonance structures. To gain insight into these interesting structures, we exploit a simplified model that only considers the electrons of $Γ$ and M points in the Brillouin zone. With the help of this model, we can analytically express the ATAS spectrum as the sum of zeroth- and first-order Bessel functions in the variables of the strength and frequency of the infrared pump field as well as the effective mass of electrons at the $Γ$ and M points. Lorentzian and Fano line shapes in the absorption spectrum are addressed. The fish bone structure consists of periodic V-shaped structure that can be explained by first-order Bessel functions and its tilt angle is solely determined by the frequency of the pump laser. The periodicity of the V-shaped structure in the fish bone originates from the periodic dependence of the Lorentzian and Fano line shapes of the absorption spectrum on the time delay between the pump and probe lasers. Compared with the numerical results, our analytical theory can qualitatively or even quantitatively predict the zeroth- and first-order fringes in the fish bone structures of the ATAS spectrum. The gauge issues in the numerical simulations are also discussed.

cond-mat.mes-hall↗

arXiv2022

Energy transfer, weak resonance, and Fermi's golden rule in Hamiltonian nonlinear Klein-Gordon equations

This paper focuses on a class of nonlinear Klein-Gordon equations in three dimensions, which are Hamiltonian perturbations of the linear Klein-Gordon equation with potential. The unperturbed dynamical system has a bound state with frequency $ω$, a spatially localized and time periodic solution. In quantum mechanics, metastable states, which last longer than expected, have been observed. These metastable states are a consequence of the instability of the bound state under the nonlinear Fermi's Golden Rule. In this study, we explore the underlying mathematical instability mechanism from the bound state to these metastable states. Besides, we derive the sharp energy transfer rate from discrete to continuum modes, when the discrete spectrum was not close to the continuous spectrum of the Schördinger operator $H= -Δ+ V + m^2$, i.e. weak resonance regime $ σ_c(\sqrt{H}) = [m, \infty)$, $0< 3ω< m$. This extends the work of Soffer and Weinstein \cite{SW1999} for resonance regime $3ω> m$ and confirms their conjecture in \cite{SW1999}. Our proof relies on a more refined version of normal form transformation of Bambusi and Cuccagna \cite{BC}, the generalized Fermi's Golden Rule, as well as certain weighted dispersive estimates.

math.AP↗

arXiv2022

Tree-based Text-Vision BERT for Video Search in Baidu Video Advertising

The advancement of the communication technology and the popularity of the smart phones foster the booming of video ads. Baidu, as one of the leading search engine companies in the world, receives billions of search queries per day. How to pair the video ads with the user search is the core task of Baidu video advertising. Due to the modality gap, the query-to-video retrieval is much more challenging than traditional query-to-document retrieval and image-to-image search. Traditionally, the query-to-video retrieval is tackled by the query-to-title retrieval, which is not reliable when the quality of tiles are not high. With the rapid progress achieved in computer vision and natural language processing in recent years, content-based search methods becomes promising for the query-to-video retrieval. Benefited from pretraining on large-scale datasets, some visionBERT methods based on cross-modal attention have achieved excellent performance in many vision-language tasks not only in academia but also in industry. Nevertheless, the expensive computation cost of cross-modal attention makes it impractical for large-scale search in industrial applications. In this work, we present a tree-based combo-attention network (TCAN) which has been recently launched in Baidu's dynamic video advertising platform. It provides a practical solution to deploy the heavy cross-modal attention for the large-scale query-to-video search. After launching tree-based combo-attention network, click-through rate gets improved by 2.29\% and conversion rate get improved by 2.63\%.

cs.CV↗

arXiv2022

Adiabaticity in nonreciprocal Landau-Zener tunneling

We investigate the Landau-Zener tunneling (LZT) of a self-interacting two-level system in which the coupling between the levels is nonreciprocal. In such a non-Hermitian system, when the energy bias between two levels is adjusted very slowly, i.e., in the adiabatic limit, we find that a quantum state can still closely follow the eigenstate solution until it encounters the exceptional points (EPs) at which two eigenvalues and their corresponding eigenvectors coalesce. In the absence of the nonlinear self-interaction, we can obtain explicit expressions for the eigenvectors and eigenvalues and analytically derive the adiabatic LZT probability from invariants at EPs. In the presence of the nonlinear interaction, the dynamics of the adiabatic evolutions are explicitly demonstrated with the help of classical trajectories in the plane of the two canonical variables of the corresponding classical Josephson Hamiltonian. We show that the adiabatic tunneling probabilities can be precisely predicted by the classical action at EPs in the weak nonreciprocal regime. In a certain region of strong nonreciprocity, we find that interestingly, the nonlinear interaction effects can be completely suppressed so that the adiabatic tunneling probabilities are identical to their linear counterparts. We also obtain a phase diagram for large ranges of nonreciprocity and nonlinear interaction parameters to explicitly demonstrate where the adiabaticity can break down, i.e., the emergence of the nonzero tunneling probabilities even in adiabatic limit.

quant-ph↗

arXiv2022

Divide-and-conquer variational quantum algorithms for large-scale electronic structure simulations

Exploring the potential application of quantum computers in material design and drug discovery has attracted a lot of interest in the age of quantum computing. However, the quantum resource requirement for solving practical electronic structure problems are far beyond the capacity of near-term quantum devices. In this work, we integrate the divide-and-conquer (DC) approaches into the variational quantum eigensolver (VQE) for large-scale quantum computational chemistry simulations. Two popular divide-and-conquer schemes, including many-body expansion~(MBE) fragmentation theory and density matrix embedding theory~(DMET), are employed to divide complicated problems into many small parts that are easy to implement on near-term quantum computers. Pilot applications of these methods to systems consisting of tens of atoms are performed with adaptive VQE algorithms. This work should encourage further studies of using the philosophy of DC to solve electronic structure problems on quantum computers.

quant-ph↗

arXiv2022

Weak solutions of the three-dimensional hypoviscous elastodynamics with finite kinetic energy

We construct weak solutions to the 3D hypoviscous incompressible elastodynamics with finite kinetic energy which was unknown in literatures. Our result holds for fractional hypoviscosity $(-Δ)^θ$, where $0\leqθ<1$. The proof {consists of a convex integration scheme with new building blocks of 2D intermittency and suitable temporal correctors, which are motivated by} the inherent geometric structure of the viscoelastic equations.

math.AP↗

arXiv2022

Q$^2$Chemistry: A quantum computation platform for quantum chemistry

Quantum computer provides new opportunities for quantum chemistry. In this article, we present a versatile, extensible, and efficient software package, named Q$^2$Chemistry, for developing quantum algorithms and quantum inspired classical algorithms in the field of quantum chemistry. In Q$^2$Chemistry, wave function and Hamiltonian can be conveniently mapped into the qubit space, then quantum circuits can be generated according to a specific quantum algorithm already implemented in the package or newly developed by the users. The generated circuits can be dispatched to either a physical quantum computer, if available, or to the internal virtual quantum computer realized by simulating quantum circuit on classical supercomputers. As demonstrated by our benchmark simulations with up to 72 qubit, Q$^2$Chemistry achieves excellent performance in simulating medium scale quantum circuits. Application of Q$^2$Chemistry to simulate molecules and periodic systems are given with performance analysis.

quant-ph↗

arXiv2022

Non-Hermiticity stabilized Majorana zero modes in semiconductor-superconductor nanowires

Coupled Majorana zero modes with nonzero energies are generally detrimental to the non-Abelian statistics due to the additional dynamic phase. Nevertheless, we show that a well-connected lead can introduce a local non-Hermitian dissipation term to shift the energies of the both coupled Majorana modes to zero, and surprisingly turn the coupled Majorana mode far from the lead into a dark Majorana mode with exponentially small dissipation. This dark Majorana mode can conquer the drawback of the partially overlapped Majorana zero modes and possess the properties of true Majorana zero mode such as the perfect fractional Josephson effect and the non-Abelian statistics.

cond-mat.mes-hall↗

arXiv2022

Optimizing Irregular-Shaped Matrix-Matrix Multiplication on Multi-Core DSPs

General Matrix Multiplication (GEMM) has a wide range of applications in scientific simulation and artificial intelligence. Although traditional libraries can achieve high performance on large regular-shaped GEMMs, they often behave not well on irregular-shaped GEMMs, which are often found in new algorithms and applications of high-performance computing (HPC). Due to energy efficiency constraints, low-power multi-core digital signal processors (DSPs) have become an alternative architecture in HPC systems. Targeting multi-core DSPs in FT-m7032, a prototype CPU-DSPs heterogeneous processor for HPC, an efficient implementation - ftIMM - for three types of irregular-shaped GEMMs is proposed. FtIMM supports automatic generation of assembly micro-kernels, two parallelization strategies, and auto-tuning of block sizes and parallelization strategies. The experiments show that ftIMM can get better performance than the traditional GEMM implementations on multi-core DSPs in FT-m7032, yielding on up to 7.2x performance improvement, when performing on irregular-shaped GEMMs. And ftIMM on multi-core DSPs can also far outperform the open source library on multi-core CPUs in FT-m7032, delivering up to 3.1x higher efficiency.

cs.DC↗

arXiv2022

KSSOLV 2.0: An efficient MATLAB toolbox for solving the Kohn-Sham equations with plane-wave basis set

KSSOLV (Kohn-Sham Solver) is a MATLAB toolbox for performing Kohn-Sham density functional theory (DFT) calculations with a plane-wave basis set. KSSOLV 2.0 preserves the design features of the original KSSOLV software to allow users and developers to easily set up a problem and perform ground-state calculations as well as to prototype and test new algorithms. Furthermore, it includes new functionalities such as new iterative diagonalization algorithms, k-point sampling for electron band structures, geometry optimization and advanced algorithms for performing DFT calculations with local, semi-local, and hybrid exchange-correlation functionals. It can be used to study the electronic structures of both molecules and solids. We describe these new capabilities in this work through a few use cases. We also demonstrate the numerical accuracy and computational efficiency of KSSOLV on a variety of examples.

physics.comp-ph↗

arXiv2022

$BC_2$ type multivariable matrix functions and matrix spherical functions

Matrix spherical functions associated to the compact symmetric pair $(\mathrm{SU}(m+2), \mathrm{S}(\mathrm{U}(2)\times \mathrm{U}(m))$, having reduced root system of type $\mathrm{BC}_2$, are studied. We consider an irreducible $K$-representation $(π,V)$ arising from the $\mathrm{U}(2)$-part of $K$, and the induced representation $\mathrm{Ind}_K^G π$ splits multiplicity free. The corresponding spherical functions, i.e. $Φ\colon G \to \mathrm{End}(V)$ satisfying $Φ(k_1gk_2)=π(k_1)Φ(g)π(k_2)$ for all $g\in G$, $k_1,k_2\in K$, are studied by studying certain leading coefficients which involve hypergeometric functions. This is done explicitly using the action of the radial part of the Casimir operator on these functions and their leading coefficients. To suitably grouped matrix spherical functions we associate two-variable matrix orthogonal polynomials giving a matrix analogue of Koornwinder's 1970s two-variable orthogonal polynomials, which are Heckman-Opdam polynomials for $\mathrm{BC}_2$. In particular, we find explicit orthogonality relations and the matrix polynomials being eigenfunctions to an explicit second order matrix partial differential operator. The scalar part of the matrix weight is less general than Koornwinder's weight.

math.CA↗

arXiv2022

Large-Scale Simulation of Quantum Computational Chemistry on a New Sunway Supercomputer

Quantum computational chemistry (QCC) is the use of quantum computers to solve problems in computational quantum chemistry. We develop a high performance variational quantum eigensolver (VQE) simulator for simulating quantum computational chemistry problems on a new Sunway supercomputer. The major innovations include: (1) a Matrix Product State (MPS) based VQE simulator to reduce the amount of memory needed and increase the simulation efficiency; (2) a combination of the Density Matrix Embedding Theory with the MPS-based VQE simulator to further extend the simulation range; (3) A three-level parallelization scheme to scale up to 20 million cores; (4) Usage of the Julia script language as the main programming language, which both makes the programming easier and enables cutting edge performance as native C or Fortran; (5) Study of real chemistry systems based on the VQE simulator, achieving nearly linearly strong and weak scaling. Our simulation demonstrates the power of VQE for large quantum chemistry systems, thus paves the way for large-scale VQE experiments on near-term quantum computers.

quant-ph↗

arXiv2022

Multi-features based Semantic Augmentation Networks for Named Entity Recognition in Threat Intelligence

Extracting cybersecurity entities such as attackers and vulnerabilities from unstructured network texts is an important part of security analysis. However, the sparsity of intelligence data resulted from the higher frequency variations and the randomness of cybersecurity entity names makes it difficult for current methods to perform well in extracting security-related concepts and entities. To this end, we propose a semantic augmentation method which incorporates different linguistic features to enrich the representation of input tokens to detect and classify the cybersecurity names over unstructured text. In particular, we encode and aggregate the constituent feature, morphological feature and part of speech feature for each input token to improve the robustness of the method. More than that, a token gets augmented semantic information from its most similar K words in cybersecurity domain corpus where an attentive module is leveraged to weigh differences of the words, and from contextual clues based on a large-scale general field corpus. We have conducted experiments on the cybersecurity datasets DNRTI and MalwareTextDB, and the results demonstrate the effectiveness of the proposed method.

cs.CR↗