arXiv subjects

Wei Peng

Publications and source records attributed to Wei Peng.

At least 181 records · Page 10Linked to original sources

arXiv2020

Observation of Two-dimensional Superconductivity in an Ultrathin Iron-Arsenic Superconductor

Two-dimensional (2D) superconductors supply important platforms for exploring new quantum physics and high-$T_c$ superconductivity. The intrinsic superconducting properties in the 2D iron-arsenic superconductors are still unknown owing to the difficulties in the preparation of ultrathin samples. Here we report the fabrication and physical investigations of the high quality single-crystalline ultrathin films of the iron-arsenic superconductor KCa$_2$Fe$_4$As$_4$F$_2$. For the sample with the thickness of 2.6$\sim$5 nm (1$\sim$2 unit cells), a sharp superconducting transition at around 30 K (onset point) is observed. Compare with the bulk material, the ultrathin sample reveals a relatively lower $T_c$, wider transition width, and broader flux liquid region under the in-plane field. Moreover, the angle dependent upper critical field follows the Tinkham model, demonstrating the two-dimensional superconductivity in ultrathin KCa$_2$Fe$_4$As$_4$F$_2$.

cond-mat.supr-con↗

arXiv2020

Accelerating Physics-Informed Neural Network Training with Prior Dictionaries

Physics-Informed Neural Networks (PINNs) can be regarded as general-purpose PDE solvers, but it might be slow to train PINNs on particular problems, and there is no theoretical guarantee of corresponding error bounds. In this manuscript, we propose a variant called Prior Dictionary based Physics-Informed Neural Networks (PD-PINNs). Equipped with task-dependent dictionaries, PD-PINNs enjoy enhanced representation power on the tasks, which helps to capture features provided by dictionaries so that the proposed neural networks can achieve faster convergence in the process of training. In various numerical simulations, compared with existing PINN methods, combining prior dictionaries can significantly enhance convergence speed. In terms of theory, we obtain the error bounds applicable to PINNs and PD-PINNs for solving elliptic partial differential equations of second order. It is proved that under certain mild conditions, the prediction error made by neural networks can be bounded by expected loss of PDEs and boundary conditions.

cs.LG↗

arXiv2020

Applying Cyclical Learning Rate to Neural Machine Translation

In training deep learning networks, the optimizer and related learning rate are often used without much thought or with minimal tuning, even though it is crucial in ensuring a fast convergence to a good quality minimum of the loss function that can also generalize well on the test dataset. Drawing inspiration from the successful application of cyclical learning rate policy for computer vision related convolutional networks and datasets, we explore how cyclical learning rate can be applied to train transformer-based neural networks for neural machine translation. From our carefully designed experiments, we show that the choice of optimizers and the associated cyclical learning rate policy can have a significant impact on the performance. In addition, we establish guidelines when applying cyclical learning rates to neural machine translation tasks. Thus with our work, we hope to raise awareness of the importance of selecting the right optimizers and the accompanying learning rate policy, at the same time, encourage further research into easy-to-use learning rate policies.

cs.LG↗

arXiv2020

Dictionary-based Data Augmentation for Cross-Domain Neural Machine Translation

Existing data augmentation approaches for neural machine translation (NMT) have predominantly relied on back-translating in-domain (IND) monolingual corpora. These methods suffer from issues associated with a domain information gap, which leads to translation errors for low frequency and out-of-vocabulary terminology. This paper proposes a dictionary-based data augmentation (DDA) method for cross-domain NMT. DDA synthesizes a domain-specific dictionary with general domain corpora to automatically generate a large-scale pseudo-IND parallel corpus. The generated pseudo-IND data can be used to enhance a general domain trained baseline. The experiments show that the DDA-enhanced NMT models demonstrate consistent significant improvements, outperforming the baseline models by 3.75-11.53 BLEU. The proposed method is also able to further improve the performance of the back-translation based and IND-finetuned NMT models. The improvement is associated with the enhanced domain coverage produced by DDA.

cs.CL↗

arXiv2019

Scalable and Efficient Hypothesis Testing with Random Forests

Throughout the last decade, random forests have established themselves as among the most accurate and popular supervised learning methods. While their black-box nature has made their mathematical analysis difficult, recent work has established important statistical properties like consistency and asymptotic normality by considering subsampling in lieu of bootstrapping. Though such results open the door to traditional inference procedures, all formal methods suggested thus far place severe restrictions on the testing framework and their computational overhead precludes their practical scientific use. Here we propose a permutation-style testing approach to formally assess feature significance. We establish asymptotic validity of the test via exchangeability arguments and show that the test maintains high power with orders of magnitude fewer computations. As importantly, the procedure scales easily to big data settings where large training and testing sets may be employed without the need to construct additional models. Simulations and applications to ecological data where random forests have recently shown promise are provided.

stat.ME↗

arXiv2019

Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching

Human action recognition from skeleton data, fueled by the Graph Convolutional Network (GCN), has attracted lots of attention, due to its powerful capability of modeling non-Euclidean structure data. However, many existing GCN methods provide a pre-defined graph and fix it through the entire network, which can loss implicit joint correlations. Besides, the mainstream spectral GCN is approximated by one-order hop, thus higher-order connections are not well involved. Therefore, huge efforts are required to explore a better GCN architecture. To address these problems, we turn to Neural Architecture Search (NAS) and propose the first automatically designed GCN for skeleton-based action recognition. Specifically, we enrich the search space by providing multiple dynamic graph modules after fully exploring the spatial-temporal correlations between nodes. Besides, we introduce multiple-hop modules and expect to break the limitation of representational capacity caused by one-order approximation. Moreover, a sampling- and memory-efficient evolution strategy is proposed to search an optimal architecture for this task. The resulted architecture proves the effectiveness of the higher-order approximation and the dynamic graph modeling mechanism with temporal interactions, which is barely discussed before. To evaluate the performance of the searched model, we conduct extensive experiments on two very large scaled datasets and the results show that our model gets the state-of-the-art results.

cs.CV↗

arXiv2019

Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs

Though state-of-the-art sentence representation models can perform tasks requiring significant knowledge of grammar, it is an open question how best to evaluate their grammatical knowledge. We explore five experimental methods inspired by prior work evaluating pretrained sentence representation models. We use a single linguistic phenomenon, negative polarity item (NPI) licensing in English, as a case study for our experiments. NPIs like "any" are grammatical only if they appear in a licensing environment like negation ("Sue doesn't have any cats" vs. "Sue has any cats"). This phenomenon is challenging because of the variety of NPI licensing environments that exist. We introduce an artificially generated dataset that manipulates key features of NPI licensing for the experiments. We find that BERT has significant knowledge of these features, but its success varies widely across different experimental methods. We conclude that a variety of methods is necessary to reveal all relevant aspects of a model's grammatical knowledge in a given domain.

cs.CL↗

arXiv2019

Proximal-Like Incremental Aggregated Gradient Method with Linear Convergence under Bregman Distance Growth Conditions

We introduce a unified algorithmic framework, called proximal-like incremental aggregated gradient (PLIAG) method, for minimizing the sum of a convex function that consists of additive relatively smooth convex components and a proper lower semi-continuous convex regularization function, over an abstract feasible set whose geometry can be captured by using the domain of a Legendre function. The PLIAG method includes many existing algorithms in the literature as special cases such as the proximal gradient method, the Bregman proximal gradient method (also called NoLips algorithm), the incremental aggregated gradient method, the incremental aggregated proximal method, and the proximal incremental aggregated gradient method. It also includes some novel interesting iteration schemes. First we show the PLIAG method is globally sublinearly convergent without requiring a growth condition, which extends the sublinear convergence result for the proximal gradient algorithm to incremental aggregated type first order methods. Then by embedding a so-called Bregman distance growth condition into a descent-type lemma to construct a special Lyapunov function, we show that the PLIAG method is globally linearly convergent in terms of both function values and Bregman distances to the optimal solution set, provided that the step size is not greater than some positive constant. These convergence results derived in this paper are all established beyond the standard assumptions in the literature (i.e., without requiring the strong convexity and the Lipschitz gradient continuity of the smooth part of the objective). When specialized to many existing algorithms, our results recover or supplement their convergence results under strictly weaker conditions.

math.OC↗

arXiv2019

Remote Heart Rate Measurement from Highly Compressed Facial Videos: an End-to-end Deep Learning Solution with Video Enhancement

Remote photoplethysmography (rPPG), which aims at measuring heart activities without any contact, has great potential in many applications (e.g., remote healthcare). Existing rPPG approaches rely on analyzing very fine details of facial videos, which are prone to be affected by video compression. Here we propose a two-stage, end-to-end method using hidden rPPG information enhancement and attention networks, which is the first attempt to counter video compression loss and recover rPPG signals from highly compressed videos. The method includes two parts: 1) a Spatio-Temporal Video Enhancement Network (STVEN) for video enhancement, and 2) an rPPG network (rPPGNet) for rPPG signal recovery. The rPPGNet can work on its own for robust rPPG measurement, and the STVEN network can be added and jointly trained to further boost the performance especially on highly compressed videos. Comprehensive experiments are performed on two benchmark datasets to show that, 1) the proposed method not only achieves superior performance on compressed videos with high-quality videos pair, 2) it also generalizes well on novel data with only compressed videos available, which implies the promising potential for real world applications.

eess.IV↗

arXiv2019

Epitaxial growth and characterization of high quality Bi2O2Se thin films on SrTiO3 substrates by pulsed laser deposition

Recently, Bi2O2Se is discovered as a promising two-dimensional (2D) semiconductor for next generation electronics, due to its moderate bandgap size, high electron mobility and pronounced ambient stability. Meanwhile, it has been predicted that high quality Bi2O2Se-related heterostructures may possess exotic physical phenomena, such as piezoelectricity and topological superconductivity. Herein, we report the first successful heteroepitaxial growth of Bi2O2Se films on SrTiO3 substrates via pulsed laser deposition (PLD) method. Films obtained under optimal conditions show an epitaxial growth with the c axis perpendicular to the film surface and the a and b axes parallel to the substrate. The growth mode transition to three dimensional (3D) island from quasi-2D layer of the heteroepitaxial Bi2O2Se films on SrTiO3 (001) substrates is observed as prolonging deposition time of films. The maximum value of electron mobility reaches 160 cm2/V-1s-1 at room temperature in a 70nm-thick film. The thickness dependent mobility provides evidence that interface-scattering is likely to be the limiting factor for the relatively low electron mobility at low temperature, implying that the interface engineering as an effective method to tune the low temperature electron mobility. Our work suggests the epitaxial Bi2O2Se films grown by PLD are promising for both fundamental study and practical applications.

cond-mat.mtrl-sci↗

arXiv2019

Video Action Recognition Via Neural Architecture Searching

Deep neural networks have achieved great success for video analysis and understanding. However, designing a high-performance neural architecture requires substantial efforts and expertise. In this paper, we make the first attempt to let algorithm automatically design neural networks for video action recognition tasks. Specifically, a spatio-temporal network is developed in a differentiable space modeled by a directed acyclic graph, thus a gradient-based strategy can be performed to search an optimal architecture. Nonetheless, it is computationally expensive, since the computational burden to evaluate each architecture candidate is still heavy. To alleviate this issue, we, for the video input, introduce a temporal segment approach to reduce the computational cost without losing global video information. For the architecture, we explore in an efficient search space by introducing pseudo 3D operators. Experiments show that, our architecture outperforms popular neural architectures, under the training from scratch protocol, on the challenging UCF101 dataset, surprisingly, with only around one percentage of parameters of its manual-design counterparts.

cs.CV↗

arXiv2019

An Integrated Autoencoder-Based Filter for Sparse Big Data

We propose a novel filter for sparse big data, called an integrated autoencoder (IAE), which utilizes auxiliary information to mitigate data sparsity. The proposed model achieves an appropriate balance between prediction accuracy, convergence speed, and complexity. We implement experiments on a GPS trajectory dataset, and the results demonstrate that the IAE is more accurate and robust than some state-of-the-art methods.

cs.LG↗

arXiv2019

Computational distributed fiber-optic sensing

Ghost imaging allows image reconstruction by correlation measurements between a light beam that interacts with the object without spatial resolution and a spatially resolved light beam that never interacts with the object. The two light beams are copies of each other. Its computational version removes the requirement of a spatially resolved detector when the light intensity pattern is pre-known. Here, we exploit the temporal analogue of computational ghost imaging, and demonstrate a computational distributed fiber-optic sensing technique. Temporal images containing spatially distributed scattering information used for sensing purposes are retrieved through correlating the "integrated" backscattered light and the pre-known binary patterns. The sampling rate required for our technique is inversely proportional to the total time duration of a binary sequence, so that it can be significantly reduced compared to that of the traditional methods. Our experiments demonstrate a 3 orders of magnitude reduction in the sampling rate, offering great simplification and cost reduction in the distributed fiber-optic sensors.

eess.SP↗

arXiv2019

Inertial Bregman Proximal Gradient Algorithm For Nonconvex Problem with Smooth Adaptable Property

In this paper we study the problems of minimizing the sum of two nonconvex functions: one is differentiable and satisfies smooth adaptable property. The smooth adaptable property, also named relatively smooth condition, is weaker than the globally gradient Lipschitz continuity. We analyze an inertial version of the Bregman Proximal Gradient (BPG) algorithm and prove its stationary convergence. Besides, we prove a sublinear convergence of the inertial algorithm. Moreover, if the objective function satisfies Kurdyka--Łojasiewicz (KL) property, its global convergence to a critical point of the objective function can be also guaranteed.

math.OC↗

arXiv2019

Modeling, discretization, and hyperchaos detection of conformable derivative approach to a financial system with market confidence and ethics risk

A new chaotic financial system is proposed by considering ethics involvement in a four-dimensional financial system with market confidence. A five-dimensional conformable derivative financial system is presented by introducing conformable fractional calculus to the integer-order system. A discretization scheme is proposed to calculate numerical solutions of conformable derivative systems. The scheme is illustrated by testing hyperchaos for the system.

q-fin.GN↗

arXiv2019

Single-crystal growth and extremely high H_c2 of 12442-type Fe-based superconductor KCa_2Fe_4As_4F_2

Millimeter sized single crystals of KCa_2Fe_4As_4F_2 were grown using a self-flux method. The chemical compositions and crystal structure were characterized carefully. Superconductivity with the critical transition T_c = 33.5 K was confirmed by both the resistivity and magnetic susceptibility measurements. Moreover, the upper critical field H_c2 was studied by the resistivity measurements under different magnetic fields. A rather steep increase for the in-plane H_c2^ab with cooling, dμ_0H_c2^a/dT|T_c = -50.9 T/K, was observed, indicating an extremely high upper critical field. Possible origins for this behavior were discussed. The findings in our work is a great promotion both for understanding the physical properties and applications of 12442-type Fe-based superconductors.

cond-mat.supr-con↗

arXiv2019

A fractional-order difference Cournot duopoly game with long memory

We reconsider the Cournot duopoly problem in light of the theory for long memory. We introduce the Caputo fractional-order difference calculus to classical duopoly theory to propose a fractional-order discrete Cournot duopoly game model, which allows participants to make decisions while making full use of their historical information. Then we discuss Nash equilibria and local stability by using linear approximation. Finally, we detect the chaos of the model by employing a 0-1 test algorithm.

econ.GN↗

arXiv2019

SPMF: A Social Trust and Preference Segmentation-based Matrix Factorization Recommendation Algorithm

The traditional social recommendation algorithm ignores the following fact: the preferences of users with trust relationships are not necessarily similar, and the consideration of user preference similarity should be limited to specific areas. A social trust and preference segmentation-based matrix factorization (SPMF) recommendation system is proposed to solve the above-mentioned problems. Experimental results based on the Ciao and Epinions datasets show that the accuracy of the SPMF algorithm is significantly higher than that of some state-of-the-art recommendation algorithms. The proposed SPMF algorithm is a more accurate and effective recommendation algorithm based on distinguishing the difference of trust relations and preference domain, which can support commercial activities such as product marketing.

cs.IR↗