arXiv subjects

Yiming Zhang

Publications and source records attributed to Yiming Zhang.

216 records · Page 12Linked to original sources

arXiv2020

MLCVNet: Multi-Level Context VoteNet for 3D Object Detection

In this paper, we address the 3D object detection task by capturing multi-level contextual information with the self-attention mechanism and multi-scale feature fusion. Most existing 3D object detection methods recognize objects individually, without giving any consideration on contextual information between these objects. Comparatively, we propose Multi-Level Context VoteNet (MLCVNet) to recognize 3D objects correlatively, building on the state-of-the-art VoteNet. We introduce three context modules into the voting and classifying stages of VoteNet to encode contextual information at different levels. Specifically, a Patch-to-Patch Context (PPC) module is employed to capture contextual information between the point patches, before voting for their corresponding object centroid points. Subsequently, an Object-to-Object Context (OOC) module is incorporated before the proposal and classification stage, to capture the contextual information between object candidates. Finally, a Global Scene Context (GSC) module is designed to learn the global scene context. We demonstrate these by capturing contextual information at patch, object and scene levels. Our method is an effective way to promote detection accuracy, achieving new state-of-the-art detection performance on challenging 3D object detection datasets, i.e., SUN RGBD and ScanNet. We also release our code at https://github.com/NUAAXQ/MLCVNet.

cs.CV↗

arXiv2020

$α$-Satellite: An AI-driven System and Benchmark Datasets for Hierarchical Community-level Risk Assessment to Help Combat COVID-19

The novel coronavirus and its deadly outbreak have posed grand challenges to human society: as of March 26, 2020, there have been 85,377 confirmed cases and 1,293 reported deaths in the United States; and the World Health Organization (WHO) characterized coronavirus disease (COVID-19) - which has infected more than 531,000 people with more than 24,000 deaths in at least 171 countries - a global pandemic. A growing number of areas reporting local sub-national community transmission would represent a significant turn for the worse in the battle against the novel coronavirus, which points to an urgent need for expanded surveillance so we can better understand the spread of COVID-19 and thus better respond with actionable strategies for community mitigation. By advancing capabilities of artificial intelligence (AI) and leveraging the large-scale and real-time data generated from heterogeneous sources (e.g., disease related data from official public health organizations, demographic data, mobility data, and user geneated data from social media), in this work, we propose and develop an AI-driven system (named $α$-Satellite}, as an initial offering, to provide hierarchical community-level risk assessment to assist with the development of strategies for combating the fast evolving COVID-19 pandemic. More specifically, given a specific location (either user input or automatic positioning), the developed system will automatically provide risk indexes associated with it in a hierarchical manner (e.g., state, county, city, specific location) to enable individuals to select appropriate actions for protection while minimizing disruptions to daily life to the extent possible. The developed system and the generated benchmark datasets have been made publicly accessible through our website. The system description and disclaimer are also available in our website.

cs.SI↗

arXiv2020

Advances in Bayesian Probabilistic Modeling for Industrial Applications

Industrial applications frequently pose a notorious challenge for state-of-the-art methods in the contexts of optimization, designing experiments and modeling unknown physical response. This problem is aggravated by limited availability of clean data, uncertainty in available physics-based models and additional logistic and computational expense associated with experiments. In such a scenario, Bayesian methods have played an impactful role in alleviating the aforementioned obstacles by quantifying uncertainty of different types under limited resources. These methods, usually deployed as a framework, allows decision makers to make informed choices under uncertainty while being able to incorporate information on the the fly, usually in the form of data, from multiple sources while being consistent with the physical intuition about the problem. This is a major advantage that Bayesian methods bring to fruition especially in the industrial context. This paper is a compendium of the Bayesian modeling methodology that is being consistently developed at GE Research. The methodology, called GE's Bayesian Hybrid Modeling (GEBHM), is a probabilistic modeling method, based on the Kennedy and O'Hagan framework, that has been continuously scaled-up and industrialized over several years. In this work, we explain the various advancements in GEBHM's methods and demonstrate their impact on several challenging industrial problems.

stat.ML↗

arXiv2019

Global cracking elements: a novel tool for Galerkin-based approaches simulating quasi-brittle fracture

Following the so-called Cracking Elements Method (CEM), recently presented in \cite{Yiming:14,Yiming:16}, we propose a novel Galerkin-based numerical approach for simulating quasi-brittle fracture, named Global Cracking Elements Method (GCEM). For this purpose the formulation of the original CEM is reorganized. The new approach is embedded in the standard framework of the Galerkin-based Finite Element Method (FEM), which uses disconnected element-wise crack openings for capturing crack initiation and propagation. The similarity between the proposed Global Cracking Elements (GCE) and the standard 9-node quadrilateral element (Q9) suggests a special procedure: the degrees of freedom of the center node of the Q9, originally defining the displacements, are "borrowed" to describe the crack openings of the GCE. The proposed approach does not need remeshing, enrichment, or a crack-tracking strategy, and it avoids a precise description of the crack tip. Several benchmark tests provide evidence that the new approach inherits from the CEM most of the advantages. The numerical stability and robustness of the GCEM are better than the ones of the CEM. However, presently only quadrilateral elements with nonlinear interpolations of the displacement field can be used.

cs.CE↗

arXiv2019

Multielemental single-atom-thick A layers in nanolaminated V2(Sn, A)C (A=Fe, Co, Ni, Mn) for tailoring magnetic properties

Tailoring of individual single-atom-thick layers in nanolaminated materials offers atomic-level control over material properties. Nonetheless, multielement alloying in individual atomic layers in nanolaminates is largely unexplored. Here, we report a series of inherently nanolaminated V2(A'xSn1-x)C (A'=Fe, Co, Ni and Mn, and combinations thereof, with x=1/3) synthesized by an alloy-guided reaction. The simultaneous occupancy of the four magnetic elements and Sn, the individual single-atom-thick A layers in the compound constitute high-entropy-alloy analogues, two-dimensional in the sense that the alloying exclusively occurs in the A layers. V2(A'xSn1-x)C exhibit distinct ferromagnetic behavior that can be compositionally tailored from the multielement A-layer alloying. This two-dimensional alloying provides a structural-design route with expanded chemical space for discovering materials and exploit properties.

cond-mat.mtrl-sci↗

arXiv2019

A Strategy for Adaptive Sampling of Multi-fidelity Gaussian Process to Reduce Predictive Uncertainty

Multi-fidelity Gaussian process is a common approach to address the extensive computationally demanding algorithms such as optimization, calibration and uncertainty quantification. Adaptive sampling for multi-fidelity Gaussian process is a changing task due to the fact that not only we seek to estimate the next sampling location of the design variable, but also the level of the simulator fidelity. This issue is often addressed by including the cost of the simulator as an another factor in the searching criterion in conjunction with the uncertainty reduction metric. In this work, we extent the traditional design of experiment framework for the multi-fidelity Gaussian process by partitioning the prediction uncertainty based on the fidelity level and the associated cost of execution. In addition, we utilize the concept of Believer which quantifies the effect of adding an exploratory design point on the Gaussian process uncertainty prediction. We demonstrated our framework using academic examples as well as a industrial application of steady-state thermodynamic operation point of a fluidized bed process

stat.ML↗

arXiv2019

Locality-Sensitive Sketching for Resilient Network Flow Monitoring

Network monitoring is vital in modern clouds and data center networks for traffic engineering, network diagnosis, network intrusion detection, which need diverse traffic statistics ranging from flow size distributions to heavy hitters. To cope with increasing network rates and massive traffic volumes, sketch based approximate measurement has been extensively studied to trade the accuracy for memory and computation cost, which unfortunately, is sensitive to hash collisions. In addition, deploying the sketch involves fine-grained performance control and instrumentation. This paper presents a locality-sensitive sketch (LSS) to be resilient to hash collisions. LSS proactively minimizes the estimation error due to hash collisions with an autoencoder based optimization model, and reduces the estimation variance by keeping similar network flows to the same bucket array. To illustrate the feasibility of the sketch, we develop a disaggregated monitoring application that supports non-intrusive sketching deployment and native network-wide analysis. Testbed shows that the framework adapts to line rates and provides accurate query results. Real-world trace-driven simulations show that LSS remains stable performance under wide ranges of parameters and dramatically outperforms state-of-the-art sketching structures, with over $10^3$ to $10^5$ times reduction in relative errors for per-flow queries as the ratio of the number of buckets to the number of network flows reduces from 10\% to 0.1\%.

cs.NI↗

arXiv2018

Supervised Policy Update for Deep Reinforcement Learning

We propose a new sample-efficient methodology, called Supervised Policy Update (SPU), for deep reinforcement learning. Starting with data generated by the current policy, SPU formulates and solves a constrained optimization problem in the non-parameterized proximal policy space. Using supervised regression, it then converts the optimal non-parameterized policy to a parameterized policy, from which it draws new samples. The methodology is general in that it applies to both discrete and continuous action spaces, and can handle a wide variety of proximity constraints for the non-parameterized optimization problem. We show how the Natural Policy Gradient and Trust Region Policy Optimization (NPG/TRPO) problems, and the Proximal Policy Optimization (PPO) problem can be addressed by this methodology. The SPU implementation is much simpler than TRPO. In terms of sample efficiency, our extensive experiments show SPU outperforms TRPO in Mujoco simulated robotic tasks and outperforms PPO in Atari video game tasks.

cs.LG↗

arXiv2018

Efficient Entropy for Policy Gradient with Multidimensional Action Space

In recent years, deep reinforcement learning has been shown to be adept at solving sequential decision processes with high-dimensional state spaces such as in the Atari games. Many reinforcement learning problems, however, involve high-dimensional discrete action spaces as well as high-dimensional state spaces. This paper considers entropy bonus, which is used to encourage exploration in policy gradient. In the case of high-dimensional action spaces, calculating the entropy and its gradient requires enumerating all the actions in the action space and running forward and backpropagation for each action, which may be computationally infeasible. We develop several novel unbiased estimators for the entropy bonus and its gradient. We apply these estimators to several models for the parameterized policies, including Independent Sampling, CommNet, Autoregressive with Modified MDP, and Autoregressive with LSTM. Finally, we test our algorithms on two environments: a multi-hunter multi-rabbit grid game and a multi-agent multi-arm bandit problem. The results show that our entropy estimators substantially improve performance with marginal additional computational cost.

cs.LG↗

arXiv2018

Adaptive Sampling for Rapidly Matching Histograms

In exploratory data analysis, analysts often have a need to identify histograms that possess a specific distribution, among a large class of candidate histograms, e.g., find countries whose income distribution is most similar to that of Greece. This distribution could be a new one that the user is curious about, or a known distribution from an existing histogram visualization. At present, this process of identification is brute-force, requiring the manual generation and evaluation of a large number of histograms. We present FastMatch: an end-to-end approach for interactively retrieving the histogram visualizations most similar to a user-specified target, from a large collection of histograms. The primary technical contribution underlying FastMatch is a probabilistic algorithm, HistSim, a theoretically sound sampling-based approach to identify the top-$k$ closest histograms under $\ell_1$ distance. While HistSim can be used independently, within FastMatch we couple HistSim with a novel system architecture that is aware of practical considerations, employing asynchronous block-based sampling policies, building on lightweight sampling engines developed in recent work. FastMatch obtains near-perfect accuracy with up to $35\times$ speedup over approaches that do not use sampling on several real-world datasets.

cs.DB↗

arXiv2018

Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions

Depthwise convolutions provide significant performance benefits owing to the reduction in both parameters and mult-adds. However, training depthwise convolution layers with GPUs is slow in current deep learning frameworks because their implementations cannot fully utilize the GPU capacity. To address this problem, in this paper we present an efficient method (called diagonalwise refactorization) for accelerating the training of depthwise convolution layers. Our key idea is to rearrange the weight vectors of a depthwise convolution into a large diagonal weight matrix so as to convert the depthwise convolution into one single standard convolution, which is well supported by the cuDNN library that is highly-optimized for GPU computations. We have implemented our training method in five popular deep learning frameworks. Evaluation results show that our proposed method gains $15.4\times$ training speedup on Darknet, $8.4\times$ on Caffe, $5.4\times$ on PyTorch, $3.5\times$ on MXNet, and $1.4\times$ on TensorFlow, compared to their original implementations of depthwise convolutions.

cs.CV↗

arXiv2017

Which is better? A Modularized Evaluation for Topic Popularity Prediction

Topic popularity prediction in social networks has drawn much attention recently. Various elegant models have been proposed for this issue. However, different datasets and evaluation metrics they use lead to low comparability. So far there is no unified scheme to evaluate them, making it difficult to select and compare models. We conduct a comprehensible survey, propose an evaluation scheme and apply it to existing methods. Our scheme consists of four modules: classification; qualitative evaluation on several metrics; quantitative experiment on real world data; final ranking with risk matrix and $\textit{MinDis}$ to reflect performances under different scenarios. Furthermore, we analyze the efficiency and contribution of features used in feature oriented methods. The results show that feature oriented methods are more suitable for scenarios requiring high accuracy, while relation based methods have better consistency. Our work helps researchers compare and choose methods appropriately, and provides insights for further improvements.

cs.IR↗

arXiv2017

A softening-healing law for self-healing quasi-brittle materials: analyzing with Strong Discontinuity embedded Approach

Quasi-brittle materials such as concrete suffer from cracks during their life cycle, requiring great cost for conventional maintenance or replacement. In the last decades, self-healing materials are developed which are capable of filling and healing the cracks and regaining part of the stiffness and strength automatically after getting damaged, bringing the possibility of maintenance-free materials and structures. In this paper, a time dependent softening-healing law for self-healing quasi-brittle materials is presented by introducing limited material parameters with clear physical background. Strong Discontinuity embedded Approach (SDA) is adopted for evaluating the reliability of the model. In the numerical studies, values of healing parameters are firstly obtained by back analysis of experimental results of self-healing beams. Then numerical models regarding concrete members and structures built with self-healing and non-healing materials are simulated and compared for showing the capability of the self-healing material.

cs.CE↗

arXiv2017

Multi-Fidelity Surrogate Based on Single Linear Regression

Various frameworks have been proposed to predict mechanical system responses by combining data from different fidelities for design optimization and uncertainty quantification as reviewed by Fernández-Godino et al. and Peherstorfer et al.. Among all frameworks, the Bayesian framework based on Gaussian processes has the potential of highest accuracy. However, the Bayesian framework requires optimization for estimating hyper-parameters, and there is a risk of estimating inappropriate hyper-parameters as Kriging surrogate often does, especially in the presence of noisy data. We propose an easy and yet powerful framework for practical design and applications. In this technical note, we revised a heuristic framework which minimizes the prediction errors at high-fidelity samples using optimization. The system behavior (high-fidelity behavior) is approximated by a linear combination of the low-fidelity predictions and a polynomial-based discrepancy function. The key idea is to consider the low-fidelity model as a basis function in the multi-fidelity model with the scale factor as a regression coefficient. The design matrix for least-square estimation consists of both the low-fidelity model and discrepancy function. Then the scale factor and coefficients of the basis functions are obtained simultaneously using linear regression, which guarantees the uniqueness of fitting process. Besides enabling efficient estimation of the parameters, the proposed least-squares multi-fidelity surrogate (LS-MFS) can be applicable to other regression models by simply replacing the design matrix. Therefore, the LS-MFS is expected to be easily applied to various applications such as prediction variance, D-optimal designs, uncertainty propagation and design optimization.

physics.data-an↗

arXiv2009

Edge-State Velocity and Coherence in a Quantum Hall Fabry-Perot Interferometer

We investigate nonlinear transport in electronic Fabry-Perot interferometers in the integer quantum Hall regime. For interferometers sufficiently large that Coulomb blockade effects are absent, a checkerboard-like pattern of conductance oscillations as a function of dc bias and perpendicular magnetic field is observed. Edge-state velocities extracted from the checkerboard data are compared to model calculations and found to be consistent with a crossover from skipping orbits at low fields to E x B drift at high fields. Suppression of visibility as a function of bias and magnetic field is accounted for by including energy- and field-dependent dephasing of edge electrons.

cond-mat.mes-hall↗

arXiv2008

Distinct Signatures For Coulomb Blockade and Aharonov-Bohm Interference in Electronic Fabry-Perot Interferometers

Two distinct types of magnetoresistance oscillations are observed in two electronic Fabry-Perot interferometers of different sizes in the integer quantum Hall regime. Measuring these oscillations as a function of magnetic field and gate voltages, we observe three signatures that distinguish the two types. The oscillations observed in a 2.0 square micron device are understood to arise from the Coulomb blockade mechanism, and those observed in an 18 square micron device from the Aharonov-Bohm mechanism. This work clarifies, provides ways to distinguish, and demonstrates control over, these distinct physical origins of resistance oscillations seen in electronic Fabry-Perot interferometers.

cond-mat.mes-hall↗

arXiv2008

Shot Noise in Graphene

We report measurements of current noise in single- and multi-layer graphene devices. In four single-layer devices, including a p-n junction, the Fano factor remains constant to within +/-10% upon varying carrier type and density, and averages between 0.35 and 0.38. The Fano factor in a multi-layer device is found to decrease from a maximal value of 0.33 at the charge-neutrality point to 0.25 at high carrier density. These results are compared to theoretical predictions for shot noise in ballistic and disordered graphene.

cond-mat.mes-hall↗

arXiv2007

Current Noise in Quantum Point Contacts

We present measurements of current noise in quantum point contacts as a function of source-drain bias, gate voltage, and in-plane magnetic field. At zero bias, Johnson noise provides a measure of the electron temperature. At finite bias, shot noise at zero field exhibits an asymmetry related to the 0.7 structure in conductance. The asymmetry in noise evolves smoothly into the symmetric signature of spin-resolved electron transmission at high field. Comparison to a phenomenological model with density-dependent level splitting yields quantitative agreement. Additionally, a device-specific contribution to the finite-bias noise, particularly visible on conductance plateaus (where shot noise vanishes), agrees quantitatively with a model of bias-dependent electron heating.

cond-mat.mes-hall↗