arXiv subjects

Zhe Zhang

Publications and source records attributed to Zhe Zhang.

At least 199 records · Page 11Linked to original sources

arXiv2022

Smoothing Advantage Learning

Advantage learning (AL) aims to improve the robustness of value-based reinforcement learning against estimation errors with action-gap-based regularization. Unfortunately, the method tends to be unstable in the case of function approximation. In this paper, we propose a simple variant of AL, named smoothing advantage learning (SAL), to alleviate this problem. The key to our method is to replace the original Bellman Optimal operator in AL with a smooth one so as to obtain more reliable estimation of the temporal difference target. We give a detailed account of the resulting action gap and the performance bound for approximate SAL. Further theoretical analysis reveals that the proposed value smoothing technique not only helps to stabilize the training procedure of AL by controlling the trade-off between convergence rate and the upper bound of the approximation errors, but is beneficial to increase the action gap between the optimal and sub-optimal action value as well.

cs.LG↗

arXiv2022

Robust Action Gap Increasing with Clipped Advantage Learning

Advantage Learning (AL) seeks to increase the action gap between the optimal action and its competitors, so as to improve the robustness to estimation errors. However, the method becomes problematic when the optimal action induced by the approximated value function does not agree with the true optimal action. In this paper, we present a novel method, named clipped Advantage Learning (clipped AL), to address this issue. The method is inspired by our observation that increasing the action gap blindly for all given samples while not taking their necessities into account could accumulate more errors in the performance loss bound, leading to a slow value convergence, and to avoid that, we should adjust the advantage value adaptively. We show that our simple clipped AL operator not only enjoys fast convergence guarantee but also retains proper action gaps, hence achieving a good balance between the large action gap and the fast convergence. The feasibility and effectiveness of the proposed method are verified empirically on several RL benchmarks with promising performance.

cs.LG↗

arXiv2022

MD modeling of cracks in clay at the nanoscale

Cracks in clay are significant in geotechnical and geoenvironmental engineering (e.g., embankment erosion and stability of landfill cover systems). This article studies the mechanism of nucleation and growth of cracks in clay at the nanoscale through full-scale molecular dynamics simulations. The clay adopted is pyrophyllite, and the force field is CLAYFF. The crack formation in a pyrophyllite clay layer is evaluated under uniaxial tension and simple shear. The numerical results show that cracks in the nanoscale pyrophyllite clay layer are brittle and strain-rate dependent. Small strain rate results in low ultimate tensile/shear strength. As strain rate increases, clay crack shifts from a single-crack pattern to a multiple-crack one. The cracking mechanism is investigated from bond breakage analysis at the atomic scale. It is found that the first bond breakage occurs in the silicon-surface oxygen bond. As a crack propagates, the relative percentage of broken silicon-surface oxygen bonds is the smallest compared to other types of metal-oxygen interactions, demonstrating that the atomic interaction between silicon and surface oxygen atoms is the strongest. To understand the propagation of cracks, we also study the stress intensity factor and energy release rate of pyrophyllite and their size dependence at the atomic scale.

cond-mat.mtrl-sci↗

arXiv2022

Robust Semi-supervised Federated Learning for Images Automatic Recognition in Internet of Drones

Air access networks have been recognized as a significant driver of various Internet of Things (IoT) services and applications. In particular, the aerial computing network infrastructure centered on the Internet of Drones has set off a new revolution in automatic image recognition. This emerging technology relies on sharing ground truth labeled data between Unmanned Aerial Vehicle (UAV) swarms to train a high-quality automatic image recognition model. However, such an approach will bring data privacy and data availability challenges. To address these issues, we first present a Semi-supervised Federated Learning (SSFL) framework for privacy-preserving UAV image recognition. Specifically, we propose model parameters mixing strategy to improve the naive combination of FL and semi-supervised learning methods under two realistic scenarios (labels-at-client and labels-at-server), which is referred to as Federated Mixing (FedMix). Furthermore, there are significant differences in the number, features, and distribution of local data collected by UAVs using different camera modules in different environments, i.e., statistical heterogeneity. To alleviate the statistical heterogeneity problem, we propose an aggregation rule based on the frequency of the client's participation in training, namely the FedFreq aggregation rule, which can adjust the weight of the corresponding local model according to its frequency. Numerical results demonstrate that the performance of our proposed method is significantly better than those of the current baseline and is robust to different non-IID levels of client data.

cs.LG↗

arXiv2021

NEMD modeling of nanoscale hydrodynamics of clay-water system at elevated temperature

The engineering problems involving clay under non-isothermal conditions (e.g., geothermal energy harvest, landfill cover system, and nuclear waste disposal) are multiscale and multiphysics by nature. The nanoscale hydrodynamics of clay at elevated temperature is essential in developing a physics-based multiscale model for clay under non-isothermal conditions. The nonequilibrium molecular dynamics (NEMD) is a useful tool to study the nanoscale hydrodyndamics of clay. This article presents an NEMD modeling of hydrodynamics of clay nanopores at elevated temperatures. Water flow confined in pyrophyllite and montmorillonite clay nanopores is investigated. The nonequilibrium state is maintained by uniformly exerting an external force on each water molecule. The NEMD simulations have provided a molecular-scale perspective of temperature effect on clay-water density, water flow velocity, shear viscosity, clay-water slip length, hydraulic conductivity, and clay-water friction coefficient. The numerical results have shown a strong temperature dependence of fluid flow velocity, shear viscosity, clay-water slip length, and hydraulic conductivity at the nanoscale. We have validated the applicability of cubic law in determining hydraulic conductivity at the nanopore scale under at elevated temperature. It is found from our numerical results that slip clay-water boundary condition is an essential factor in properly determining nanoscale fluid flow velocity. By numerical examples, we also study the impact of nanopore size and clay layer thickness on the hydrodynamics of the clay-water system.

physics.flu-dyn↗

arXiv2021

Multi-View Stereo with Transformer

This paper proposes a network, referred to as MVSTR, for Multi-View Stereo (MVS). It is built upon Transformer and is capable of extracting dense features with global context and 3D consistency, which are crucial to achieving reliable matching for MVS. Specifically, to tackle the problem of the limited receptive field of existing CNN-based MVS methods, a global-context Transformer module is first proposed to explore intra-view global context. In addition, to further enable dense features to be 3D-consistent, a 3D-geometry Transformer module is built with a well-designed cross-view attention mechanism to facilitate inter-view information interaction. Experimental results show that the proposed MVSTR achieves the best overall performance on the DTU dataset and strong generalization on the Tanks & Temples benchmark dataset.

cs.CV↗

arXiv2021

Van der Waals Heterostructure Polaritons with moiré-Induced Nonlinearity

Controlling matter-light interactions with cavities is of fundamental importance in modern science and technology. It is exemplified in the strong-coupling regime, where matter-light hybrid modes form, with properties controllable via the photon component on the optical-wavelength scale. In contrast, matter excitations on the nanometer scale are harder to access. In two-dimensional van der Waals heterostructures, a tunable moiré lattice potential for electronic excitations may form, enabling correlated electron gases in lattice potentials. Excitons confined in moiré lattices have also been reported, but cooperative effects have been elusive and interactions with light have remained perturbative. Here, integrating MoSe$_{2}$-WS$_{2}$ heterobilayers in a microcavity, we establish cooperative coupling between moiré-lattice excitons and microcavity photons up to liquid-nitrogen temperature, thereby integrating into one platform versatile control over both matter and light. The density dependence of the moiré polaritons reveals strong nonlinearity due to exciton blockade, suppressed exciton energy shift, and suppressed excitation-induced dephasing, all of which are consistent with the quantum-confined nature of the moiré excitons. Such a moiré polariton system combines strong nonlinearity and microscopic-scale tuning of matter excitations with the power of cavity engineering and long range coherence of light, providing a new platform for collective phenomena from tunable arrays of quantum emitters.

cond-mat.mes-hall↗

arXiv2021

Semi-Supervised Federated Learning with non-IID Data: Algorithm and System Design

Federated Learning (FL) allows edge devices (or clients) to keep data locally while simultaneously training a shared high-quality global model. However, current research is generally based on an assumption that the training data of local clients have ground-truth. Furthermore, FL faces the challenge of statistical heterogeneity, i.e., the distribution of the client's local training data is non-independent identically distributed (non-IID). In this paper, we present a robust semi-supervised FL system design, where the system aims to solve the problem of data availability and non-IID in FL. In particular, this paper focuses on studying the labels-at-server scenario where there is only a limited amount of labeled data on the server and only unlabeled data on the clients. In our system design, we propose a novel method to tackle the problems, which we refer to as Federated Mixing (FedMix). FedMix improves the naive combination of FL and semi-supervised learning methods and designs parameter decomposition strategies for disjointed learning of labeled, unlabeled data, and global models. To alleviate the non-IID problem, we propose a novel aggregation rule based on the frequency of the client's participation in training, namely the FedFreq aggregation algorithm, which can adjust the weight of the corresponding local model according to this frequency. Extensive evaluations conducted on CIFAR-10 dataset show that the performance of our proposed method is significantly better than those of the current baseline. It is worth noting that our system is robust to different non-IID levels of client data.

cs.LG↗

arXiv2021

The First Airborne Experiment of Sparse Microwave Imaging: Prototype System Design and Result Analysis

In this paper we report the first airborne experiments of sparse microwave imaging, conducted in September 2013 and May 2014, using our prototype sparse microwave imaging radar system. This is the first reported imaging radar system and airborne experiment that specially designed for sparse microwave imaging. Sparse microwave imaging is a novel concept of radar imaging, it is mainly the combination of traditional radar imaging technology and newly developed sparse signal processing theory, achieving benefits in both improving the imaging quality of current microwave imaging systems and designing optimized sparse microwave imaging radar system to reduce system sampling rate towards the sparse target scenes. During recent years, many researchers focus on related topics of sparse microwave imaging, but rarely few paid attention to prototype system design and experiment. We introduce our prototype sparse microwave imaging radar system, including its system design, hardware considerations and signal processing methods. Several design principles should be considered during the system designing, including the sampling scheme, antenna, SNR, waveform, resolution, etc. We select jittered sampling in azimuth and uniform sampling in range to balance the system complexity and performance. The imaging algorithm is accelerated $\ell_q$ regularization algorithm. To test the prototype radar system and verify the effectiveness of sparse microwave imaging framework, airborne experiments are carried out using our prototype system and we achieve the first sparse microwave image successfully. We analyze the imaging performance of prototype sparse microwave radar system with different sparsities, sampling rates, SNRs and sampling schemes, using three-dimensional phase transit diagram as the evaluation tool.

eess.SP↗

arXiv2021

Feasibility study of urban flood mapping using traffic signs for route optimization

Water events are the most frequent and costliest climate disasters around the world. In the U.S., an estimated 127 million people who live in coastal areas are at risk of substantial home damage from hurricanes or flooding. In flood emergency management, timely and effective spatial decision-making and intelligent routing depend on flood depth information at a fine spatiotemporal scale. In this paper, crowdsourcing is utilized to collect photos of submerged stop signs, and pair each photo with a pre-flood photo taken at the same location. Each photo pair is then analyzed using deep neural network and image processing to estimate the depth of floodwater in the location of the photo. Generated point-by-point depth data is converted to a flood inundation map and used by an A* search algorithm to determine an optimal flood-free path connecting points of interest. Results provide crucial information to rescue teams and evacuees by enabling effective wayfinding during flooding events.

cs.CV↗

arXiv2021

High-Dimensional Differentially-Private EM Algorithm: Methods and Near-Optimal Statistical Guarantees

In this paper, we develop a general framework to design differentially private expectation-maximization (EM) algorithms in high-dimensional latent variable models, based on the noisy iterative hard-thresholding. We derive the statistical guarantees of the proposed framework and apply it to three specific models: Gaussian mixture, mixture of regression, and regression with missing covariates. In each model, we establish the near-optimal rate of convergence with differential privacy constraints, and show the proposed algorithm is minimax rate optimal up to logarithm factors. The technical tools developed for the high-dimensional setting are then extended to the classic low-dimensional latent variable models, and we propose a near rate-optimal EM algorithm with differential privacy guarantees in this setting. Simulation studies and real data analysis are conducted to support our results.

stat.ML↗

arXiv2021

The solution space structure of planted constraint satisfaction problems with growing domains

Planting a solution into the random RB model, which is a prototype of random constraint satisfaction problem (CSP) with growing domains, can generate very hard satisfiable CSP benchmarks. We study the solution space structure of the planted RB model. With constraint density growing, we find that this model goes through four phase transitions. In the replica symmetric phase, what we call the independent phase transition occurs, after which the planted cluster (cluster containing the planted solution) is separated from the giant cluster. Then the solutions except that in the planted cluster go through the same clustering phase transition and the same satisfiability phase transition as the random RB model. The planted cluster goes through the isolated phase transition, after which the planted cluster contains only one solution. This phase diagram provides strong evidence that this model can generate very hard satisfiable CSP benchmarks. For over constraint instances (where the constraint density is very large), we find that the configuration space has only a single energy valley, which makes the instances tractable. Experiments using Belief Propagation confirm the locations of the clustering, satisfiability (by configurations outside the planted cluster), and isolated phase transition points.

cond-mat.dis-nn↗

arXiv2021

BlockGNN: Towards Efficient GNN Acceleration Using Block-Circulant Weight Matrices

In recent years, Graph Neural Networks (GNNs) appear to be state-of-the-art algorithms for analyzing non-euclidean graph data. By applying deep-learning to extract high-level representations from graph structures, GNNs achieve extraordinary accuracy and great generalization ability in various tasks. However, with the ever-increasing graph sizes, more and more complicated GNN layers, and higher feature dimensions, the computational complexity of GNNs grows exponentially. How to inference GNNs in real time has become a challenging problem, especially for some resource-limited edge-computing platforms. To tackle this challenge, we propose BlockGNN, a software-hardware co-design approach to realize efficient GNN acceleration. At the algorithm level, we propose to leverage block-circulant weight matrices to greatly reduce the complexity of various GNN models. At the hardware design level, we propose a pipelined CirCore architecture, which supports efficient block-circulant matrices computation. Basing on CirCore, we present a novel BlockGNN accelerator to compute various GNNs with low latency. Moreover, to determine the optimal configurations for diverse deployed tasks, we also introduce a performance and resource model that helps choose the optimal hardware parameters automatically. Comprehensive experiments on the ZC706 FPGA platform demonstrate that on various GNN tasks, BlockGNN achieves up to $8.3\times$ speedup compared to the baseline HyGCN architecture and $111.9\times$ energy reduction compared to the Intel Xeon CPU platform.

cs.AI↗

arXiv2021

Barocaloric thermal batteries

Nowadays the world is facing a prominent paradox regarding thermal energy. The production of heat accounts for more than 50% of global final energy consumption while the waste heat potential analysis reveals that 72% of the global primary energy consumption is lost after conversion mainly in the form of heat. Towards global decarbonization, it is of vital importance to establish a solution to thermal energy utilization under full control. Here, we propose and realize an unprecedented concept -- barocaloric thermal batteries based on the inverse colossal barocaloric effect of NH4SCN. Thermal charging is initialized upon pressurization through an order-to-disorder phase transition below 364 K and in turn the discharging of 43 J g-1, which are eleven times more than the input mechanical energy, occurs on demand at depressurization at lower temperatures. The discharging is also manifested as a directly measured temperature rise of 12 K. The thermodynamic equilibrium nature of the pressure-restrained heat-carrying phase guarantees stable storage and/or transport over a variety of temporal and/or spatial scales. The barocaloric thermal batteries reinforced by their solid microscopic mechanism are expected to significantly advance the ability to take advantage of waste heat.

cond-mat.mtrl-sci↗

arXiv2021

Dual-Modality Vehicle Anomaly Detection via Bilateral Trajectory Tracing

Traffic anomaly detection has played a crucial role in Intelligent Transportation System (ITS). The main challenges of this task lie in the highly diversified anomaly scenes and variational lighting conditions. Although much work has managed to identify the anomaly in homogenous weather and scene, few resolved to cope with complex ones. In this paper, we proposed a dual-modality modularized methodology for the robust detection of abnormal vehicles. We introduced an integrated anomaly detection framework comprising the following modules: background modeling, vehicle tracking with detection, mask construction, Region of Interest (ROI) backtracking, and dual-modality tracing. Concretely, we employed background modeling to filter the motion information and left the static information for later vehicle detection. For the vehicle detection and tracking module, we adopted YOLOv5 and multi-scale tracking to localize the anomalies. Besides, we utilized the frame difference and tracking results to identify the road and obtain the mask. In addition, we introduced multiple similarity estimation metrics to refine the anomaly period via backtracking. Finally, we proposed a dual-modality bilateral tracing module to refine the time further. The experiments conducted on the Track 4 testset of the NVIDIA 2021 AI City Challenge yielded a result of 0.9302 F1-Score and 3.4039 root mean square error (RMSE), indicating the effectiveness of our framework.

cs.CV↗

arXiv2021

Femtosecond dynamics of a polariton bosonic cascade at room temperature

Whispering gallery modes in a microwire are characterized by a nearly equidistant energy spectrum. In the strong exciton-photon coupling regime, this system represents a bosonic cascade: a ladder of discrete energy levels that sustains stimulated transitions between neighboring steps. In this work, by using femtosecond angle-resolved spectroscopic imaging technique, the ultrafast dynamics of polaritons in a bosonic cascade based on a one-dimensional ZnO whispering gallery microcavity is explicitly visualized. Clear ladder-form build-up process from higher to lower energy branches of the polariton condensates are observed, which are well reproduced by modeling using rate equations. Moreover, the polariton parametric scattering dynamics are distinguished on a timescale of hundreds of femtoseconds. Our understanding of the femtosecond condensation and scattering dynamics paves the way towards ultrafast coherent control of polaritons at room temperature, which will make it promising for high-speed all-optical integrated applications.

physics.optics↗

arXiv2021

Subspace-based compressive sensing algorithm for raypath separation in a shallow-water waveguide

Compressive sensing (CS) has been applied to estimate the direction of arrival (DOA) in underwater acoustics. However, the key problem needed to be resolved in a {multipath} propagation environment is to suppress the interferences between the raypaths. Thus, in this paper, {a subspace-based compressive sensing algorithm that formulates the statistic information of the signal subspace in a CS framework is proposed.} The experiment results show that (1) the proposed algorithm enables the separation of raypaths that arrive closely at the {receiver} array and (2) the existing algorithms fail, especially in a low signal-to-noise ratio (SNR) environment.

cs.SD↗

arXiv2021

Anomalous nonreciprocal topological networks: stronger than Chern insulators

Robustness against disorder and defects is a pivotal advantage of topological systems, manifested by absence of electronic backscattering in the quantum Hall and spin-Hall effects, and unidirectional waveguiding in their classical analogs. Two-dimensional (2D) topological insulators, in particular, provide unprecedented opportunities in a variety of fields due to their compact planar geometries compatible with the fabrication technologies used in modern electronics and photonics. Among all 2D topological phases, Chern insulators are to date the most reliable designs due to the genuine backscattering immunity of their non-reciprocal edge modes, brought via time-reversal symmetry breaking. Yet, such resistance to fabrication tolerances is limited to fluctuations of the same order of magnitude as their band gap, limiting their resilience to small perturbations only. Here, we tackle this vexing problem by introducing the concept of anomalous non-reciprocal topological networks, that survive disorder levels with strengths arbitrarily larger than their bandgap. We explore the general conditions to obtain such unusual effect in systems made of unitary three-port scattering matrices connected by phase links, and establish the superior robustness of the anomalous edge modes over the Chern ones to phase link disorder of arbitrarily large values. We confirm experimentally the exceptional resilience of the anomalous phase, and demonstrate its operation by building an ideal anomalous topological circulator despite its arbitrary shape and large number of ports. Our results pave the way to efficient, arbitrary planar energy transport on 2D substrates for wave devices with full protection against large fabrication flaws or imperfections.

cond-mat.mes-hall↗