arXiv subjects

Lu Zhang

Publications and source records attributed to Lu Zhang.

At least 397 records · Page 22Linked to original sources

arXiv2020

High-dimensional Multivariate Geostatistics: A Bayesian Matrix-Normal Approach

Joint modeling of spatially-oriented dependent variables is commonplace in the environmental sciences, where scientists seek to estimate the relationships among a set of environmental outcomes accounting for dependence among these outcomes and the spatial dependence for each outcome. Such modeling is now sought for massive data sets with variables measured at a very large number of locations. Bayesian inference, while attractive for accommodating uncertainties through hierarchical structures, can become computationally onerous for modeling massive spatial data sets because of its reliance on iterative estimation algorithms. This manuscript develops a conjugate Bayesian framework for analyzing multivariate spatial data using analytically tractable posterior distributions that obviate iterative algorithms. We discuss differences between modeling the multivariate response itself as a spatial process and that of modeling a latent process in a hierarchical model. We illustrate the computational and inferential benefits of these models using simulation studies and analysis of a Vegetation Index data set with spatially dependent observations numbering in the millions.

stat.ME↗

arXiv2020

Synergistic saliency and depth prediction for RGB-D saliency detection

Depth information available from an RGB-D camera can be useful in segmenting salient objects when figure/ground cues from RGB channels are weak. This has motivated the development of several RGB-D saliency datasets and algorithms that use all four channels of the RGB-D data for both training and inference. Unfortunately, existing RGB-D saliency datasets are small, which may lead to overfitting and limited generalization for diverse scenarios. Here we propose a semi-supervised system for RGB-D saliency detection that can be trained on smaller RGB-D saliency datasets without saliency ground truth, while also make effective joint use of a large RGB saliency dataset with saliency ground truth together. To generalize our method on RGB-D saliency datasets, a novel prediction-guided cross-refinement module which jointly estimates both saliency and depth by mutual refinement between two respective tasks, and an adversarial learning approach are employed. Critically, our system does not require saliency ground-truth for the RGB-D datasets, which saves the massive human labor for hand labeling, and does not require the depth data for inference, allowing the method to be used for the much broader range of applications where only RGB data are available. Evaluation on seven RGB-D datasets demonstrates that even without saliency ground truth for RGB-D datasets and using only the RGB data of RGB-D datasets at inference, our semi-supervised system performs favorable against state-of-the-art fully-supervised RGB-D saliency detection methods that use saliency ground truth for RGB-D datasets at training and depth data at inference on two largest testing datasets. Our approach also achieves comparable results on other popular RGB-D saliency benchmarks.

cs.CV↗

arXiv2020

High Area/Energy Efficiency RRAM CNN Accelerator with Kernel-Reordering Weight Mapping Scheme Based on Pattern Pruning

Resistive Random Access Memory (RRAM) is an emerging device for processing-in-memory (PIM) architecture to accelerate convolutional neural network (CNN). However, due to the highly coupled crossbar structure in the RRAM array, it is difficult to exploit the sparsity of the network in RRAM-based CNN accelerator. To optimize the weight mapping of sparse network in the RRAM array and achieve high area and energy efficiency, we propose a novel weight mapping scheme and corresponding RRAM-based CNN accelerator architecture based on pattern pruning and Operation Unit(OU) mechanism. Experimental results show that our work can achieve 4.16x-5.20x crossbar area efficiency, 1.98x-2.15x energy efficiency, and 1.15x-1.35x performance speedup in comparison with the traditional weight mapping method.

cs.AR↗

arXiv2020

MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning

Multi-hop reasoning approaches over knowledge graphs infer a missing relationship between entities with a multi-hop rule, which corresponds to a chain of relationships. We extend existing works to consider a generalized form of multi-hop rules, where each rule is a set of relation chains. To learn such generalized rules efficiently, we propose a two-step approach that first selects a small set of relation chains as a rule and then evaluates the confidence of the target relationship by jointly scoring the selected chains. A game-theoretical framework is proposed to this end to simultaneously optimize the rule selection and prediction steps. Empirical results show that our multi-chain multi-hop (MCMH) rules result in superior results compared to the standard single-chain approaches, justifying both our formulation of generalized rules and the effectiveness of the proposed learning framework.

cs.CL↗

arXiv2020

Service Ecosystem: A Lens of Smart Society

Intelligence services are playing an increasingly important role in the operation of our society. Exploring the evolution mechanism, boundaries and challenges of service ecosystem is essential to our ability to realize smart society, reap its benefits and prevent potential risks. We argue that this necessitates a broad scientific research agenda to study service ecosystem that incorporates and expands upon the disciplines of computer science and includes insights from across the sciences. We firstly outline a set of research issues that are fundamental to this emerging field, and then explores the technical, social, legal and institutional challenges on the study of service ecosystem.

cs.CY↗

arXiv2020

OCoR: An Overlapping-Aware Code Retriever

Code retrieval helps developers reuse the code snippet in the open-source projects. Given a natural language description, code retrieval aims to search for the most relevant code among a set of code. Existing state-of-the-art approaches apply neural networks to code retrieval. However, these approaches still fail to capture an important feature: overlaps. The overlaps between different names used by different people indicate that two different names may be potentially related (e.g., "message" and "msg"), and the overlaps between identifiers in code and words in natural language descriptions indicate that the code snippet and the description may potentially be related. To address these problems, we propose a novel neural architecture named OCoR, where we introduce two specifically-designed components to capture overlaps: the first embeds identifiers by character to capture the overlaps between identifiers, and the second introduces a novel overlap matrix to represent the degrees of overlaps between each natural language word and each identifier. The evaluation was conducted on two established datasets. The experimental results show that OCoR significantly outperforms the existing state-of-the-art approaches and achieves 13.1% to 22.3% improvements. Moreover, we also conducted several in-depth experiments to help understand the performance of different components in OCoR.

cs.CL↗

arXiv2020

An accurate hyper-singular boundary integral equation method for dynamic poroelasticity in two dimensions

This paper is concerned with the boundary integral equation method for solving the exterior Neumann boundary value problem of dynamic poroelasticity in two dimensions. The main contribution of this work consists of two aspescts: the proposal of a novel regularized boundary integral equation, and the presentation of new regularized formulations of the strongly-singular and hyper-singular boundary integral operators. Firstly, turning to the spectral properties of the double-layer operator and the corresponding Calderón relation of the poroelasticity, we propose the novel low-GMRES-iteration integral equation whose eigenvalues are bounded away from zero and infinity. Secondly, with the help of the Günter derivatives, we reformulate the strongly-singular and hyper-singular integral operators into combinations of the weakly-singular operators and the tangential derivatives. The accuracy and efficiency of the proposed methodology are demonstrated through several numerical examples.

physics.comp-ph↗

arXiv2020

Optical Flow and Mode Selection for Learning-based Video Coding

This paper introduces a new method for inter-frame coding based on two complementary autoencoders: MOFNet and CodecNet. MOFNet aims at computing and conveying the Optical Flow and a pixel-wise coding Mode selection. The optical flow is used to perform a prediction of the frame to code. The coding mode selection enables competition between direct copy of the prediction or transmission through CodecNet. The proposed coding scheme is assessed under the Challenge on Learned Image Compression 2020 (CLIC20) P-frame coding conditions, where it is shown to perform on par with the state-of-the-art video codec ITU/MPEG HEVC. Moreover, the possibility of copying the prediction enables to learn the optical flow in an end-to-end fashion i.e. without relying on pre-training and/or a dedicated loss term.

eess.IV↗

arXiv2020

ModeNet: Mode Selection Network For Learned Video Coding

In this paper, a mode selection network (ModeNet) is proposed to enhance deep learning-based video compression. Inspired by traditional video coding, ModeNet purpose is to enable competition among several coding modes. The proposed ModeNet learns and conveys a pixel-wise partitioning of the frame, used to assign each pixel to the most suited coding mode. ModeNet is trained alongside the different coding modes to minimize a rate-distortion cost. It is a flexible component which can be generalized to other systems to allow competition between different coding tools. Mod-eNet interest is studied on a P-frame coding task, where it is used to design a method for coding a frame given its prediction. ModeNet-based systems achieve compelling performance when evaluated under the Challenge on Learned Image Compression 2020 (CLIC20) P-frame coding track conditions.

cs.NE↗

arXiv2020

A Fixation-based 360° Benchmark Dataset for Salient Object Detection

Fixation prediction (FP) in panoramic contents has been widely investigated along with the booming trend of virtual reality (VR) applications. However, another issue within the field of visual saliency, salient object detection (SOD), has been seldom explored in 360° (or omnidirectional) images due to the lack of datasets representative of real scenes with pixel-level annotations. Toward this end, we collect 107 equirectangular panoramas with challenging scenes and multiple object classes. Based on the consistency between FP and explicit saliency judgements, we further manually annotate 1,165 salient objects over the collected images with precise masks under the guidance of real human eye fixation maps. Six state-of-the-art SOD models are then benchmarked on the proposed fixation-based 360° image dataset (F-360iSOD), by applying a multiple cubic projection-based fine-tuning method. Experimental results show a limitation of the current methods when used for SOD in panoramic images, which indicates the proposed dataset is challenging. Key issues for 360° SOD is also discussed. The proposed dataset is available at https://github.com/PanoAsh/F-360iSOD.

cs.CV↗

arXiv2020

Efficient Uncertainty-aware Decision-making for Automated Driving Using Guided Branching

Decision-making in dense traffic scenarios is challenging for automated vehicles (AVs) due to potentially stochastic behaviors of other traffic participants and perception uncertainties (e.g., tracking noise and prediction errors, etc.). Although the partially observable Markov decision process (POMDP) provides a systematic way to incorporate these uncertainties, it quickly becomes computationally intractable when scaled to the real-world large-size problem. In this paper, we present an efficient uncertainty-aware decision-making (EUDM) framework, which generates long-term lateral and longitudinal behaviors in complex driving environments in real-time. The computation complexity is controlled to an appropriate level by two novel techniques, namely, the domain-specific closed-loop policy tree (DCP-Tree) structure and conditional focused branching (CFB) mechanism. The key idea is utilizing domain-specific expert knowledge to guide the branching in both action and intention space. The proposed framework is validated using both onboard sensing data captured by a real vehicle and an interactive multi-agent simulation platform. We also release the code of our framework to accommodate benchmarking.

cs.RO↗

arXiv2020

Binary Probability Model for Learning Based Image Compression

In this paper, we propose to enhance learned image compression systems with a richer probability model for the latent variables. Previous works model the latents with a Gaussian or a Laplace distribution. Inspired by binary arithmetic coding , we propose to signal the latents with three binary values and one integer, with different probability models. A relaxation method is designed to perform gradient-based training. The richer probability model results in a better entropy coding leading to lower rate. Experiments under the Challenge on Learned Image Compression (CLIC) test conditions demonstrate that this method achieves 18% rate saving compared to Gaussian or Laplace models.

eess.IV↗

arXiv2020

Bi-parameter trilinear Fourier multipliers and pseudo-differential operators with flag symbols

The main purpose of this paper is to study $L^r$ Hölder type estimates for a bi-parameter trilinear Fourier multiplier with flag singularity, and the analogous pseudo-differential operator, when the symbols are in a certain product form. More precisely, for $f,g,h\in \mathcal{S}(\mathbb{R}^{2})$, the bi-parameter trilinear flag Fourier multiplier operators we consider are defined by $$ T_{m_1,m_2}(f,g,h)(x):=\int_{\mathbb{R}^{6}}m_1(ξ,η,ζ)m_2(η,ζ)\hat f(ξ) \hat g(η)\hat h(ζ)e^{2πi(ξ+η+ζ)\cdot x}dξdηdζ, $$ when $m_1,m_2$ are two bi-parameter symbols. We will show that our problem can be reduced to establish the $L^r$ estimate for the special multiplier $m_1(ξ_1, η_1, ζ_1) m_2(η_2, ζ_2)$ (see Theorem 1.7). We also study these $L^r$ estimates for the corresponding bi-parameter trilinear pseudo-differential operators defined by $$ T_{ab}(f,g,h)(x):=\int_{\mathbb{R}^6}a(x,ξ,η,ζ)b(x,η,ζ)\hat f(ξ)\hat g(η)\hat h(ζ)e^{2πi x(ξ+η+ζ)}dξdηdζ, $$ where the smooth symbols $a,b$ satisfy certain bi-parameter Hörmander conditions. We will also show that the $L^r$ estimate holds for $T_{ab}$ as long as the $L^r$ estimate for the flag multiplier operator holds when the multiplier has the special form $m_1(ξ_1, η_1, ζ_1) m_2(η_2, ζ_2)$ (see Theorem 1.10). The bi-parameter and trilinear flag Fourier multipliers considered in this paper do not satisfy the conditions of the classical bi-parameter trilinear Fourier multipliers considered by Muscalu, Tao, Thiele and the second author [21, 22]. They may also be viewed as the bi-parameter trilinear variants of estimates obtained for the one-parameter flag paraproducts by Muscalu [18].

math.CA↗

arXiv2020

Modeling Programs Hierarchically with Stack-Augmented LSTM

Programming language modeling has attracted extensive attention in recent years, and it plays an essential role in program processing fields. Statistical language models, which are initially designed for natural languages, have been generally used for modeling programming languages. However, different from natural languages, programming languages contain explicit and hierarchical structure that is hard to learn by traditional statistical language models. To address this challenge, we propose a novel Stack-Augmented LSTM neural network for programming language modeling. Adding a stack memory component into the LSTM network enables our model to capture the hierarchical information of programs through the PUSH and POP operations, which further allows our model capturing the long-term dependency in the programs. We evaluate the proposed model on three program analysis tasks, i.e., code completion, program classification, and code summarization. Evaluation results show that our proposed model outperforms baseline models in all the three tasks, indicating that by capturing the structural information of programs with a stack, our proposed model can represent programs more precisely.

cs.SE↗

arXiv2020

Medusa: Blockchain Powered Log Storage System

Blockchain is one of the most heavily invested technologies in recent years. Due to its tamper-proof and decentralization properties, blockchain has become an ideal utility for data storage that is applicable in many real world industrial scenarios. One important scenario is web log, which is treated as sources of technical significance and commercial revenues in major internet companies. In this paper, we illustrate our design of a web log storage system based on HyperLedger. HyperLedger yields higher throughput and lower latency compared with other blockchain systems. Alongside its efficiency advantages, HyperLeger is a permissioned blockchain, which is an ideal fit for enterprise software design scenario.

cs.CR↗

arXiv2020

An energy-based discontinuous Galerkin method for semilinear wave equations

We generalize the energy-based discontinuous Galerkin method proposed in [SIAM J. Num. Anal., 53(6):2705-2726, 2015.] to second-order semilinear wave equations. A stability and convergence analysis is presented along with numerical experiments demonstrating optimal convergence for certain choices of the interelement fluxes. Applications to the sine-Gordon equation include simulations of breathers, kink, and anti-kink solitons.

math.NA↗

arXiv2020

A Study of Bug Resolution Characteristics in Popular Programming Languages

This paper presents a large-scale study that investigates the bug resolution characteristics among popular Github projects written in different programming languages. We explore correlations but, of course, we cannot infer causation. Specifically, we analyse bug resolution data from approximately 70 million Source Line of Code, drawn from 3 million commits to 600 GitHub projects, primarily written in 10 programming languages. We find notable variations in apparent bug resolution time and patch (fix) size. While interpretation of results from such large-scale empirical studies is inherently difficult, we believe that the differences in medians are sufficiently large to warrant further investigation, replication, re-analysis and follow up research. For example, in our corpus, the median apparent bug resolution time (elapsed time from raise to resolve) for Ruby was 4X that for Go and 2.5X for Java. We also found that patches tend to touch more files for the corpus of strongly typed and for statically typed programs. However, we also found evidence for a lower elapsed resolution time for bug resolution committed to projects constructed from statically typed languages. These findings, if replicated in subsequent follow on studies, may shed further empirical light on the debate about the importance of static typing.

cs.SE↗

arXiv2019

Automatic Testing and Improvement of Machine Translation

This paper presents TransRepair, a fully automatic approach for testing and repairing the consistency of machine translation systems. TransRepair combines mutation with metamorphic testing to detect inconsistency bugs (without access to human oracles). It then adopts probability-reference or cross-reference to post-process the translations, in a grey-box or black-box manner, to repair the inconsistencies. Our evaluation on two state-of-the-art translators, Google Translate and Transformer, indicates that TransRepair has a high precision (99%) on generating input pairs with consistent translations. With these tests, using automatic consistency metrics and manual assessment, we find that Google Translate and Transformer have approximately 36% and 40% inconsistency bugs. Black-box repair fixes 28% and 19% bugs on average for Google Translate and Transformer. Grey-box repair fixes 30% bugs on average for Transformer. Manual inspection indicates that the translations repaired by our approach improve consistency in 87% of cases (degrading it in 2%), and that our repairs have better translation acceptability in 27% of the cases (worse in 8%).

cs.SE↗