arXiv subjects

Wei Wei

Publications and source records attributed to Wei Wei.

At least 487 records · Page 27Linked to original sources

arXiv2019

Deep Learning for Multi-Messenger Astrophysics: A Gateway for Discovery in the Big Data Era

This report provides an overview of recent work that harnesses the Big Data Revolution and Large Scale Computing to address grand computational challenges in Multi-Messenger Astrophysics, with a particular emphasis on real-time discovery campaigns. Acknowledging the transdisciplinary nature of Multi-Messenger Astrophysics, this document has been prepared by members of the physics, astronomy, computer science, data science, software and cyberinfrastructure communities who attended the NSF-, DOE- and NVIDIA-funded "Deep Learning for Multi-Messenger Astrophysics: Real-time Discovery at Scale" workshop, hosted at the National Center for Supercomputing Applications, October 17-19, 2018. Highlights of this report include unanimous agreement that it is critical to accelerate the development and deployment of novel, signal-processing algorithms that use the synergy between artificial intelligence (AI) and high performance computing to maximize the potential for scientific discovery with Multi-Messenger Astrophysics. We discuss key aspects to realize this endeavor, namely (i) the design and exploitation of scalable and computationally efficient AI algorithms for Multi-Messenger Astrophysics; (ii) cyberinfrastructure requirements to numerically simulate astrophysical sources, and to process and interpret Multi-Messenger Astrophysics data; (iii) management of gravitational wave detections and triggers to enable electromagnetic and astro-particle follow-ups; (iv) a vision to harness future developments of machine and deep learning and cyberinfrastructure resources to cope with the scale of discovery in the Big Data Era; (v) and the need to build a community that brings domain experts together with data scientists on equal footing to maximize and accelerate discovery in the nascent field of Multi-Messenger Astrophysics.

astro-ph.IM↗

arXiv2018

Towards Effective Deep Embedding for Zero-Shot Learning

Zero-shot learning (ZSL) can be formulated as a cross-domain matching problem: after being projected into a joint embedding space, a visual sample will match against all candidate class-level semantic descriptions and be assigned to the nearest class. In this process, the embedding space underpins the success of such matching and is crucial for ZSL. In this paper, we conduct an in-depth study on the construction of embedding space for ZSL and posit that an ideal embedding space should satisfy two criteria: intra-class compactness and inter-class separability. While the former encourages the embeddings of visual samples of one class to distribute tightly close to the semantic description embedding of this class, the latter requires embeddings from different classes to be well separated from each other. Towards this goal, we present a simple but effective two-branch network to simultaneously map semantic descriptions and visual samples into a joint space, on which visual embeddings are forced to regress to their class-level semantic embeddings and the embeddings crossing classes are required to be distinguishable by a trainable classifier. Furthermore, we extend our method to a transductive setting to better handle the model bias problem in ZSL (i.e., samples from unseen classes tend to be categorized into seen classes) with minimal extra supervision. Specifically, we propose a pseudo labeling strategy to progressively incorporate the testing samples into the training process and thus balance the model between seen and unseen classes. Experimental results on five standard ZSL datasets show the superior performance of the proposed method and its transductive extension.

cs.CV↗

arXiv2018

MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning

Recent studies on neural architecture search have shown that automatically designed neural networks perform as good as expert-crafted architectures. While most existing works aim at finding architectures that optimize the prediction accuracy, these architectures may have complexity and is therefore not suitable being deployed on certain computing environment (e.g., with limited power budgets). We propose MONAS, a framework for Multi-Objective Neural Architectural Search that employs reward functions considering both prediction accuracy and other important objectives (e.g., power consumption) when searching for neural network architectures. Experimental results showed that, compared to the state-ofthe-arts, models found by MONAS achieve comparable or better classification accuracy on computer vision applications, while satisfying the additional objectives such as peak power.

cs.LG↗

arXiv2018

Miura-ori tube metamaterial with tunable dynamic property

Structures and/or materials with engineered functionality, capable of achieving targeted mechanical responses reacting to changes in external excitation, have various potential engineering applications, e.g. aerospace, oceanographic engineering, soft robot, and several others. Yet tunable mechanical performance is normally realized through carefully designing the architecture of structures, which is usually porous, leading to the complexity of the fabrication of the structures even using the recently emerged 3D printing technique. In this study we show that origami technique can provide an alternative solution to achieving the aim by carefully stacking the classical Miura sheets into the Miura-ori tube metamaterial and tuning the geometric parameters of the origami metamaterial. By combining numerical and experimental methods, we have demonstrated that an extremely broad range of natural frequency and dynamic response of the metamaterial can be achieved. The proposed structure can be easily fabricated from a single thin sheet made of one material and simultaneously owns better mechanical properties than the Miura sheet.

physics.app-ph↗

arXiv2018

Accurate Spectral Super-resolution from Single RGB Image Using Multi-scale CNN

Different from traditional hyperspectral super-resolution approaches that focus on improving the spatial resolution, spectral super-resolution aims at producing a high-resolution hyperspectral image from the RGB observation with super-resolution in spectral domain. However, it is challenging to accurately reconstruct a high-dimensional continuous spectrum from three discrete intensity values at each pixel, since too much information is lost during the procedure where the latent hyperspectral image is downsampled (e.g., with x10 scaling factor) in spectral domain to produce an RGB observation. To address this problem, we present a multi-scale deep convolutional neural network (CNN) to explicitly map the input RGB image into a hyperspectral image. Through symmetrically downsampling and upsampling the intermediate feature maps in a cascading paradigm, the local and non-local image information can be jointly encoded for spectral representation, ultimately improving the spectral reconstruction accuracy. Extensive experiments on a large hyperspectral dataset demonstrate the effectiveness of the proposed method.

cs.CV↗

arXiv2018

Lifting the Veil on Quark Matter in Compact Stars with Core g-mode Oscillations

Compact stars containing quark matter may masquerade as neutron stars in the range of measured mass and radius, making it difficult to draw firm conclusions on the phase of matter inside the star. The sensitivity of core $g$-mode oscillations to the presence of a mixed phase may alleviate this difficulty. In hybrid stars that admit quark matter in a mixed phase, the $g$-mode frequency rises sharply due to a marked decrease in the equilibrium sound speed. Resonant excitation of $g$-modes can leave an imprint on the waveform of coalescing binary compact stars. We present some analytic and numeric results to assess the sensitivity displayed by $g$-mode oscillations to quark matter in a homogeneous or mixed phase and find that the $g$-mode can probe the fraction of quark matter inside the star.

nucl-th↗

arXiv2018

AI Matrix - Synthetic Benchmarks for DNN

Deep neural network (DNN) architectures, such as convolutional neural networks (CNN), involve heavy computation and require hardware, such as CPU, GPU, and AI accelerators, to provide the massive computing power. With the many varieties of AI hardware prevailing on the market, it is often hard to decide which one is the best to use. Thus, benchmarking AI hardware effectively becomes important and is of great help to select and optimize AI hardware. Unfortunately, there are few AI benchmarks available in both academia and industry. Examples are BenchNN[1], DeepBench[2], and Dawn Bench[3], which are usually a collection of typical real DNN applications. While these benchmarks provide performance comparison across different AI hardware, they suffer from a number of drawbacks. First, they cannot adapt to the emerging changes of DNN algorithms and are fixed once selected. Second, they contain tens to hundreds of applications and take very long time to finish running. Third, they are mainly selected from open sources, which are restricted by copyright and are not representable to proprietary applications. In this work, a synthetic benchmarks framework is firstly proposed to address the above drawbacks of AI benchmarks. Instead of pre-selecting a set of open-sourced benchmarks and running all of them, the synthetic approach generates only a one or few benchmarks that best represent a broad range of applications using profiled workload characteristics data of these applications. Thus, it can adapt to emerging changes of new DNN algorithms by re-profiling new applications and updating itself, greatly reduce benchmark count and running time, and strongly represent DNN applications of interests. The generated benchmarks are called AI Matrix, serving as a performance benchmarks matching the statistical workload characteristics of a combination of applications of interests.

cs.CV↗

arXiv2018

Camouflage of the Phase Transition to Quark Matter in Neutron Stars

It has been known for some time that compact stars containing quark matter can masquerade as neutron stars in the range of measured mass and radius, making it difficult to draw firm conclusions on the phases of matter present inside the star. Using the vector-enhanced Bag model (vBag), we examine mass-radius and mass-compactness relations with Maxwell and Gibbs construction for hybrid stars with transitions from nuclear matter to two or three-flavor quark matter, including sequential transitions. Not only can stable hybrid stars with either two or three-flavor quark matter mimic neutron stars (the traditional masquerade), it appears as well difficult to distinguish two-flavor from three-flavor quark matter even in cases where a phase transition can be said to have occurred, as in the presence of a distinct kink in the mass-radius relation. Furthermore, allowing for sequential flavor transitions, we find that the transition into an unstable branch can be caused by either a transition from a nuclear to unstable quark matter or the sequential transition from nuclear to stable but "masquerading" two-flavor to unstable three-flavor quark matter. Addressing chiral restoration as well as quark deconfinement in a model of the phase transition, as the vBag does, adds further flexibility to the high-density equation of state, motivating caution in using even high-precision $M$-$R$ data to draw firm conclusions on the nature of phases and phase transitions in neutron stars.

nucl-th↗

arXiv2018

Core Influence Mechanism on Vertex-Cover Problem through Leaf-Removal-Core Breaking

Leaf-Removal process has been widely researched and applied in many mathematical and physical fields to help understand the complex systems, and a lot of problems including the minimal vertex-cover are deeply related to this process and the Leaf-Removal cores. In this paper, based on the structural features of the Leaf-Removal cores, a method named Core Influence is proposed to break the graphs into No-Leaf-Removal-Core ones, which takes advantages of identifying some significant nodes by localized and greedy strategy. By decomposing the minimal vertex-cover problem into the Leaf-Removal cores breaking process and maximal matching of the remained graphs, it is proved that any minimal vertex-covers of the whole graph can be located into these two processes, of which the latter one is a P problem, and the best boundary is achieved at the transition point. Compared with other node importance indices, the Core Influence method could break down the Leaf-Removal cores much faster and get the no-core graphs by removing fewer nodes from the graphs. Also, the vertex-cover numbers resulted from this method are lower than existing node importance measurements, and compared with the exact minimal vertex-cover numbers, this method performs appropriate accuracy and stability at different scales. This research provides a new localized greedy strategy to break the hard Leaf-Removal Cores efficiently and heuristic methods could be constructed to help understand some NP problems.

cs.SI↗

arXiv2018

Searching Toward Pareto-Optimal Device-Aware Neural Architectures

Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performance in many tasks such as image classification and language understanding. However, most existing works only optimize for model accuracy and largely ignore other important factors imposed by the underlying hardware and devices, such as latency and energy, when making inference. In this paper, we first introduce the problem of NAS and provide a survey on recent works. Then we deep dive into two recent advancements on extending NAS into multiple-objective frameworks: MONAS and DPP-Net. Both MONAS and DPP-Net are capable of optimizing accuracy and other objectives imposed by devices, searching for neural architectures that can be best deployed on a wide spectrum of devices: from embedded systems and mobile devices to workstations. Experimental results are poised to show that architectures found by MONAS and DPP-Net achieves Pareto optimality w.r.t the given objectives for various devices.

cs.LG↗

arXiv2018

Escaping from Collapsing Modes in a Constrained Space

Generative adversarial networks (GANs) often suffer from unpredictable mode-collapsing during training. We study the issue of mode collapse of Boundary Equilibrium Generative Adversarial Network (BEGAN), which is one of the state-of-the-art generative models. Despite its potential of generating high-quality images, we find that BEGAN tends to collapse at some modes after a period of training. We propose a new model, called \emph{BEGAN with a Constrained Space} (BEGAN-CS), which includes a latent-space constraint in the loss function. We show that BEGAN-CS can significantly improve training stability and suppress mode collapse without either increasing the model complexity or degrading the image quality. Further, we visualize the distribution of latent vectors to elucidate the effect of latent-space constraint. The experimental results show that our method has additional advantages of being able to train on small datasets and to generate images similar to a given real image yet with variations of designated attributes on-the-fly.

cs.LG↗

arXiv2018

DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures

Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performances in applications such as image classification and language modeling. However, these techniques typically ignore device-related objectives such as inference time, memory usage, and power consumption. Optimizing neural architecture for device-related objectives is immensely crucial for deploying deep networks on portable devices with limited computing resources. We propose DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures, optimizing for both device-related (e.g., inference time and memory usage) and device-agnostic (e.g., accuracy and model size) objectives. DPP-Net employs a compact search space inspired by current state-of-the-art mobile CNNs, and further improves search efficiency by adopting progressive search (Liu et al. 2017). Experimental results on CIFAR-10 are poised to demonstrate the effectiveness of Pareto-optimal networks found by DPP-Net, for three different devices: (1) a workstation with Titan X GPU, (2) NVIDIA Jetson TX1 embedded system, and (3) mobile phone with ARM Cortex-A53. Compared to CondenseNet and NASNet (Mobile), DPP-Net achieves better performances: higher accuracy and shorter inference time on various devices. Additional experimental results show that models found by DPP-Net also achieve considerably-good performance on ImageNet as well.

cs.CV↗

arXiv2018

Thoracic Disease Identification and Localization with Limited Supervision

Accurate identification and localization of abnormalities from radiology images play an integral part in clinical diagnosis and treatment planning. Building a highly accurate prediction model for these tasks usually requires a large number of images manually annotated with labels and finding sites of abnormalities. In reality, however, such annotated data are expensive to acquire, especially the ones with location annotations. We need methods that can work well with only a small amount of location annotations. To address this challenge, we present a unified approach that simultaneously performs disease identification and localization through the same underlying model for all images. We demonstrate that our approach can effectively leverage both class information as well as limited location annotation, and significantly outperforms the comparative reference baseline in both classification and localization tasks.

cs.CV↗

arXiv2018

Adaptive Importance Learning for Improving Lightweight Image Super-resolution Network

Deep neural networks have achieved remarkable success in single image super-resolution (SISR). The computing and memory requirements of these methods have hindered their application to broad classes of real devices with limited computing power, however. One approach to this problem has been lightweight network architectures that bal- ance the super-resolution performance and the computation burden. In this study, we revisit this problem from an orthog- onal view, and propose a novel learning strategy to maxi- mize the pixel-wise fitting capacity of a given lightweight network architecture. Considering that the initial capacity of the lightweight network is very limited, we present an adaptive importance learning scheme for SISR that trains the network with an easy-to-complex paradigm by dynam- ically updating the importance of image pixels on the basis of the training loss. Specifically, we formulate the network training and the importance learning into a joint optimization problem. With a carefully designed importance penalty function, the importance of individual pixels can be gradu- ally increased through solving a convex optimization problem. The training process thus begins with pixels that are easy to reconstruct, and gradually proceeds to more complex pixels as fitting improves.

cs.CV↗

arXiv2018

Exploring the Node Importance Based on von Neumann Entropy

When analyzing the statistical and topological characteristics of complex networks, an effective and convenient way is to compute the centralities for recognizing influential and significant nodes or structures, yet most of them are restricted to local environment or some specific configurations. In this paper we propose a new centrality for nodes based on the von Neumann entropy, which allows us to investigate the importance of nodes in the view of spectrum eigenvalues distribution. By presenting the performances of this centrality with network examples in reality, it is shown that the von Neumann entropy node centrality is an excellent index for selecting crucial nodes as well as classical ones. Then to lower down the computational complexity, an approximation calculation to this centrality is given which only depends on its first and second neighbors. Furthermore, in the optimal spreader problem and reducing average clustering coefficients, this entropy centrality presents excellent efficiency and unveil topological structure features of networks accurately. The entropy centrality could reduce the scales of giant connected components fastly in Erdos-Renyi and scale-free networks, and break down the cluster structures efficiently in random geometric graphs. This new methodology reveals the node importance in the perspective of spectrum, which provides a new insight into networks research and performs great potentials to discover essential structural features in networks.

cs.SI↗

arXiv2018

Image Registration Based Flicker Solving in Video Face Replacement and Analysis Based Sub-pixel Image Registration

In this paper, a framework of video face replacement is proposed and it deals with the flicker of swapped face in video sequence. This framework contains two main innovations: 1) the technique of image registration is exploited to align the source and target video faces for eliminating the flicker or jitter of the segmented video face sequence; 2) a fast subpixel image registration method is proposed for farther accuracy and efficiency. Unlike the priori works, it minimizes the overlapping region and takes spatiotemporal coherence into account. Flicker in resulted videos is usually caused by the frequently changed bound of the blending target face and unregistered faces between and along video sequences. The subpixel image registration method is proposed to solve the flicker problem. During the alignment process, integer pixel registration is formulated by maximizing the similarity of images with down sampling strategy speeding up the process and sub-pixel image registration is a single-step image match via analytic method. Experimental results show the proposed algorithm reduces the computation time and gets a high accuracy when conducting experiments on different data sets.

cs.CV↗

arXiv2018

Locating All Real Solutions of Power Flow Equations: A Convex Optimization Based Method

This paper proposes a convex optimization based method that either locates all real roots of a set of power flow equations or declares no real solution exists in the given area. In the proposed method, solving the power flow equations is reformulated as a global optimization problem (GPF for short) that minimizes the sum of slack variables. All the global minima of GPF with a zero objective value have a one-to-one correspondence to the real roots of power flow equations. By solving a relaxed version of GPF over a hypercube, if the optimal value is strictly positive, there is no solution in this area and the hypercube is discarded. Otherwise the hypercube is further divided into smaller ones. This procedure repeats recursively until all the real roots are located in small enough hypercubes through the successive refinement of the feasible region embedded in a bisection paradigm. This method is desired in a number of power system security assessment applications, for instance, the transient stability analysis as well as voltage stability analysis, where the closest unstable equilibrium and all Type-I unstable equilibrium is required, respectively. The effectiveness of the proposed method is verified by analyzing several test systems.

math.OC↗

arXiv2018

Stabilization of self-mode-locked quantum dash lasers by symmetric dual-loop optical feedback

We report experimental studies of the influence of symmetric dual-loop optical feedback on the RF linewidth and timing jitter of self-mode-locked two-section quantum dash lasers emitting at 1550 nm. Various feedback schemes were investigated and optimum levels determined for narrowest RF linewidth and low timing jitter, for single-loop and symmetric dual-loop feedback. Two symmetric dual-loop configurations, with balanced and unbalanced feedback ratios, were studied. We demonstrate that unbalanced symmetric dual loop feedback, with the inner cavity resonant and fine delay tuning of the outer loop, gives narrowest RF linewidth and reduced timing jitter over a wide range of delay, unlike single and balanced symmetric dual-loop configurations. This configuration with feedback lengths 80 and 140 m narrows the RF linewidth by 4-67x and 10-100x, respectively, across the widest delay range, compared to free-running. For symmetric dual-loop feedback, the influence of different power split ratios through the feedback loops was determined. Our results show that symmetric dual-loop feedback is markedly more effective than single-loop feedback in reducing RF linewidth and timing jitter, and is much less sensitive to delay phase, making this technique ideal for applications where robustness and alignment tolerance are essential.

physics.ins-det↗