arXiv subjects

Bo Zhang

Publications and source records attributed to Bo Zhang.

At least 631 records · Page 35Linked to original sources

arXiv2021

Bridging preference-based instrumental variable studies and cluster-randomized encouragement experiments: study design, noncompliance, and average cluster effect ratio

Instrumental variable methods are widely used in medical and social science research to draw causal conclusions when the treatment and outcome are confounded by unmeasured confounding variables. One important feature of such studies is that the instrumental variable is often applied at the cluster level, e.g., hospitals' or physicians' preference for a certain treatment where each hospital or physician naturally defines a cluster. This paper proposes to embed such observational instrumental variable data into a cluster-randomized encouragement experiment using statistical matching. Potential outcomes and causal assumptions underpinning the design are formalized and examined. Testing procedures for two commonly-used estimands, Fisher's sharp null hypothesis and the pooled effect ratio, are extended to the current setting. We then introduce a novel cluster-heterogeneous proportional treatment effect model and the relevant estimand: the average cluster effect ratio. This new estimand is advantageous over the structural parameter in a constant proportional treatment effect model in that it allows treatment heterogeneity, and is advantageous over the pooled effect ratio estimand in that it is immune to Simpson's paradox. We develop an asymptotically valid randomization-based testing procedure for this new estimand based on solving a mixed integer quadratically-constrained optimization problem. The proposed design and inferential methods are applied to a study of the effect of using transesophageal echocardiography during CABG surgery on patients' 30-day mortality rate.

stat.ME↗

arXiv2021

All-fiber photonic lantern multimode optical receiver with coherent adaptive optics beam combining

A multimode optical receiver for free space optical communications (FSOC) based on a photonic lantern and adaptive optics coherent beam combining (CBC) of the lantern's single-mode outputs is proposed and demonstrated for the first time. The use of optical coherent combining in fiber serves to increase the signal to noise ratio compared to similar receivers based on electrically combined signals, and represents an all-fiber approach to low-order adaptive optics. This optical receiver is demonstrated using a photonic lantern with three outputs, fibre couplers and active phase locking, and further investigated under atmospheric conditions with and without turbulence.

physics.optics↗

arXiv2021

Style-based Point Generator with Adversarial Rendering for Point Cloud Completion

In this paper, we proposed a novel Style-based Point Generator with Adversarial Rendering (SpareNet) for point cloud completion. Firstly, we present the channel-attentive EdgeConv to fully exploit the local structures as well as the global shape in point features. Secondly, we observe that the concatenation manner used by vanilla foldings limits its potential of generating a complex and faithful shape. Enlightened by the success of StyleGAN, we regard the shape feature as style code that modulates the normalization layers during the folding, which considerably enhances its capability. Thirdly, we realize that existing point supervisions, e.g., Chamfer Distance or Earth Mover's Distance, cannot faithfully reflect the perceptual quality of the reconstructed points. To address this, we propose to project the completed points to depth maps with a differentiable renderer and apply adversarial training to advocate the perceptual realism under different viewpoints. Comprehensive experiments on ShapeNet and KITTI prove the effectiveness of our method, which achieves state-of-the-art quantitative performance while offering superior visual quality.

cs.CV↗

arXiv2021

Microshift: An Efficient Image Compression Algorithm for Hardware

In this paper, we propose an image compression algorithm called Microshift. We employ an algorithm hardware co-design methodology, yielding a hardware-friendly compression approach with low power consumption. In our method, the image is first micro-shifted, then the sub-quantized values are further compressed. Two methods, the FAST and MRF model, are proposed to recover the bit-depth by exploiting the spatial correlation of natural images. Both methods can decompress images progressively. Our compression algorithm compresses images to 1.25 bits per pixel on average with PSNR of 33.16 dB, outperforming other on-chip compression algorithms. Then, we propose a hardware architecture and implement the algorithm on an FPGA and ASIC. The results on the VLSI design further validate the low hardware complexity and high power efficiency, showing our method is promising, particularly for low-power wireless vision sensor networks.

eess.IV↗

arXiv2021

Let's See Clearly: Contaminant Artifact Removal for Moving Cameras

Contaminants such as dust, dirt and moisture adhering to the camera lens can greatly affect the quality and clarity of the resulting image or video. In this paper, we propose a video restoration method to automatically remove these contaminants and produce a clean video. Our approach first seeks to detect attention maps that indicate the regions that need to be restored. In order to leverage the corresponding clean pixels from adjacent frames, we propose a flow completion module to hallucinate the flow of the background scene to the attention regions degraded by the contaminants. Guided by the attention maps and completed flows, we propose a recurrent technique to restore the input frame by fetching clean pixels from adjacent frames. Finally, a multi-frame processing stage is used to further process the entire video sequence in order to enforce temporal consistency. The entire network is trained on a synthetic dataset that approximates the physical lighting properties of contaminant artifacts. This new dataset and our novel framework lead to our method that is able to address different contaminants and outperforms competitive restoration approaches both qualitatively and quantitatively.

cs.CV↗

arXiv2021

An Empirical Bayesian Approach to Limb-darkening in Modeling WASP-121b Transit Light Curves

We present a novel, iterative method using an empirical Bayesian approach for modeling the limb darkened WASP-121b transit from the TESS light curve. Our method is motivated by the need to improve $R_{p}/R_{\ast}$ estimates for exoplanet atmosphere modeling, and is particularly effective with the limb darkening (LD) quadratic law requiring no prior central value from stellar atmospheric models. With the non-linear LD law, the method has all the advantages of not needing atmospheric models but does not converge. The iterative method gives a different $R_{p}/R_{\ast}$ for WASP-121b at a significance level of 1$σ$ when compared with existing non-iterative methods. To assess the origins and implications of this difference, we generate and analyze light curves with known values of the limb darkening coefficients (LDCs). We find that non-iterative modeling with LDC priors from stellar atmospheric models results in an inconsistent $R_{p}/R_{\ast}$ at 1.5$σ$ level when the known LDC values are as those previously found when modeling real data by the iterative method. In contrast, the LDC values from the iterative modeling yields the correct value of $R_{p}/R_{\ast}$ to within 0.25$σ$. For more general cases with different known inputs, Monte Carlo simulations show that the iterative method obtains unbiased LDCs and correct $R_{p}/R_{\ast}$ to within a significance level of 0.3$σ$. Biased LDC priors can cause biased LDC posteriors and lead to bias in the $R_{p}/R_{\ast}$ of up to 0.82$\%$, 2.5$σ$ for the quadratic law and 0.32$\%$, 1.0$σ$ for the non-linear law. Our improvement in $R_{p}/R_{\ast}$ estimation is important when analyzing exoplanet atmospheres.

astro-ph.EP↗

arXiv2021

Estimating and Improving Dynamic Treatment Regimes With a Time-Varying Instrumental Variable

Estimating dynamic treatment regimes (DTRs) from retrospective observational data is challenging as some degree of unmeasured confounding is often expected. In this work, we develop a framework of estimating properly defined "optimal" DTRs with a time-varying instrumental variable (IV) when unmeasured covariates confound the treatment and outcome, rendering the potential outcome distributions only partially identified. We derive a novel Bellman equation under partial identification, use it to define a generic class of estimands (termed IV-optimal DTRs), and study the associated estimation problem. We then extend the IV-optimality framework to tackle the policy improvement problem, delivering IV-improved DTRs that are guaranteed to perform no worse and potentially better than a pre-specified baseline DTR. Importantly, our IV-improvement framework opens up the possibility of strictly improving upon DTRs that are optimal under the no unmeasured confounding assumption (NUCA). We demonstrate via extensive simulations the superior performance of IV-optimal and IV-improved DTRs over the DTRs that are optimal only under the NUCA. In a real data example, we embed retrospective observational registry data into a natural, two-stage experiment with noncompliance using a time-varying IV and estimate useful IV-optimal DTRs that assign mothers to high-level or low-level neonatal intensive care units based on their prognostic variables.

stat.ME↗

arXiv2021

East Asian VLBI Network Observations of Active Galactic Nuclei Jets: Imaging with KaVA+Tianma+Nanshan

The East Asian very-long-baseline interferometry (VLBI) Network (EAVN) is a rapidly evolving international VLBI array that is currently promoted under joint efforts among China, Japan, and Korea. EAVN aims at forming a joint VLBI Network by combining a large number of radio telescopes distributed over East Asian regions. After the combination of the Korean VLBI Network (KVN) and the VLBI Exploration of Radio Astrometry (VERA) into KaVA, further expansion with the joint array in East Asia is actively promoted. Here we report the first imaging results (at 22 and 43 GHz) of bright radio sources obtained with KaVA connected to Tianma 65-m and Nanshan 26-m Radio Telescopes in China. To test the EAVN imaging performance for different sources, we observed four active galactic nuclei (AGN) having different brightness and morphology. As a result, we confirmed that Tianma 65-m Radio Telescope (TMRT) significantly enhances the overall array sensitivity, a factor of 4 improvement in baseline sensitivity and 2 in image dynamic range compared to the case of KaVA only. The addition of Nanshan 26-m Radio Telescope (NSRT) further doubled the east-west angular resolution. With the resulting high-dynamic-range, high-resolution images with EAVN (KaVA+TMRT+NSRT), various fine-scale structures in our targets, such as the counter-jet in M87, a kink-like morphology of the 3C273 jet and the weak emission in other sources, are successfully detected. This demonstrates the powerful capability of EAVN to study AGN jets and to achieve other science goals in general. Ongoing expansion of EAVN will further enhance the angular resolution, detection sensitivity and frequency coverage of the network.

astro-ph.GA↗

arXiv2021

Beyond Clicks: Modeling Multi-Relational Item Graph for Session-Based Target Behavior Prediction

Session-based target behavior prediction aims to predict the next item to be interacted with specific behavior types (e.g., clicking). Although existing methods for session-based behavior prediction leverage powerful representation learning approaches to encode items' sequential relevance in a low-dimensional space, they suffer from several limitations. Firstly, they focus on only utilizing the same type of user behavior for prediction, but ignore the potential of taking other behavior data as auxiliary information. This is particularly crucial when the target behavior is sparse but important (e.g., buying or sharing an item). Secondly, item-to-item relations are modeled separately and locally in one behavior sequence, and they lack a principled way to globally encode these relations more effectively. To overcome these limitations, we propose a novel Multi-relational Graph Neural Network model for Session-based target behavior Prediction, namely MGNN-SPred for short. Specifically, we build a Multi-Relational Item Graph (MRIG) based on all behavior sequences from all sessions, involving target and auxiliary behavior types. Based on MRIG, MGNN-SPred learns global item-to-item relations and further obtains user preferences w.r.t. current target and auxiliary behavior sequences, respectively. In the end, MGNN-SPred leverages a gating mechanism to adaptively fuse user representations for predicting next item interacted with target behavior. The extensive experiments on two real-world datasets demonstrate the superiority of MGNN-SPred by comparing with state-of-the-art session-based prediction methods, validating the benefits of leveraging auxiliary behavior and learning item-to-item relations over MRIG.

cs.IR↗

arXiv2021

CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation

We present the full-resolution correspondence learning for cross-domain images, which aids image translation. We adopt a hierarchical strategy that uses the correspondence from coarse level to guide the fine levels. At each hierarchy, the correspondence can be efficiently computed via PatchMatch that iteratively leverages the matchings from the neighborhood. Within each PatchMatch iteration, the ConvGRU module is employed to refine the current correspondence considering not only the matchings of larger context but also the historic estimates. The proposed CoCosNet v2, a GRU-assisted PatchMatch approach, is fully differentiable and highly efficient. When jointly trained with image translation, full-resolution semantic correspondence can be established in an unsupervised manner, which in turn facilitates the exemplar-based image translation. Experiments on diverse translation tasks show that CoCosNet v2 performs considerably better than state-of-the-art literature on producing high-resolution images.

cs.CV↗

arXiv2021

Measuring Uncertainty through Bayesian Learning of Deep Neural Network Structure

Bayesian neural networks (BNNs) augment deep networks with uncertainty quantification by Bayesian treatment of the network weights. However, such models face the challenge of Bayesian inference in a high-dimensional and usually over-parameterized space. This paper investigates a new line of Bayesian deep learning by performing Bayesian inference on network structure. Instead of building structure from scratch inefficiently, we draw inspirations from neural architecture search to represent the network structure. We then develop an efficient stochastic variational inference approach which unifies the learning of both network structure and weights. Empirically, our method exhibits competitive predictive performance while preserving the benefits of Bayesian principles across challenging scenarios. We also provide convincing experimental justification for our modeling choice.

cs.LG↗

arXiv2021

MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes

Deepfakes raised serious concerns on the authenticity of visual contents. Prior works revealed the possibility to disrupt deepfakes by adding adversarial perturbations to the source data, but we argue that the threat has not been eliminated yet. This paper presents MagDR, a mask-guided detection and reconstruction pipeline for defending deepfakes from adversarial attacks. MagDR starts with a detection module that defines a few criteria to judge the abnormality of the output of deepfakes, and then uses it to guide a learnable reconstruction procedure. Adaptive masks are extracted to capture the change in local facial regions. In experiments, MagDR defends three main tasks of deepfakes, and the learned reconstruction pipeline transfers across input data, showing promising performance in defending both black-box and white-box attacks.

cs.CV↗

arXiv2021

Learning with Smooth Hinge Losses

Due to the non-smoothness of the Hinge loss in SVM, it is difficult to obtain a faster convergence rate with modern optimization algorithms. In this paper, we introduce two smooth Hinge losses $ψ_G(α;σ)$ and $ψ_M(α;σ)$ which are infinitely differentiable and converge to the Hinge loss uniformly in $α$ as $σ$ tends to $0$. By replacing the Hinge loss with these two smooth Hinge losses, we obtain two smooth support vector machines(SSVMs), respectively. Solving the SSVMs with the Trust Region Newton method (TRON) leads to two quadratically convergent algorithms. Experiments in text classification tasks show that the proposed SSVMs are effective in real-world applications. We also introduce a general smooth convex loss function to unify several commonly-used convex loss functions in machine learning. The general framework provides smooth approximation functions to non-smooth convex loss functions, which can be used to obtain smooth models that can be solved with faster convergent optimization algorithms.

cs.LG↗

arXiv2021

A Minimax Probability Machine for Non-Decomposable Performance Measures

Imbalanced classification tasks are widespread in many real-world applications. For such classification tasks, in comparison with the accuracy rate, it is usually much more appropriate to use non-decomposable performance measures such as the Area Under the receiver operating characteristic Curve (AUC) and the $F_β$ measure as the classification criterion since the label class is imbalanced. On the other hand, the minimax probability machine is a popular method for binary classification problems and aims at learning a linear classifier by maximizing the accuracy rate, which makes it unsuitable to deal with imbalanced classification tasks. The purpose of this paper is to develop a new minimax probability machine for the $F_β$ measure, called MPMF, which can be used to deal with imbalanced classification tasks. A brief discussion is also given on how to extend the MPMF model for several other non-decomposable performance measures listed in the paper. To solve the MPMF model effectively, we derive its equivalent form which can then be solved by an alternating descent method to learn a linear classifier. Further, the kernel trick is employed to derive a nonlinear MPMF model to learn a nonlinear classifier. Several experiments on real-world benchmark datasets demonstrate the effectiveness of our new model.

cs.LG↗

arXiv2021

Extragalactic HI 21-cm absorption line observations with the Five-hundred-meter Aperture Spherical radio Telescope

We present a pilot study of extragalactic HI 21-cm absorption lines using the Five-hundred-meter Aperture Spherical radio Telescope (FAST). We observed 5 continuum sources with HI absorption features firstly identified in the 40% data release of the Arecibo Legacy Fast Arecibo L-Band Feed Array (ALFA) Survey (ALFALFA), including two systems later detected by the Westerbork Synthesis Radio Telescope (WSRT). Most of our observations were carried out during the FAST commissioning phase, and we have tested different observing modes, as well as data reduction methods, to produce the best spectra. Our observations successfully confirmed the existence of HI absorption lines in all these systems, including two sources that were marginally detected by ALFALFA. We fitted the HI profiles with single or double of Gaussian functions, and calculated the HI column densities of each source. The HI absorption profiles obtained by FAST show much higher spectral resolution and higher S/N ratio than the existing data in the literature, thus demonstrating the power of FAST in revealing detailed structures of HI absorption lines. Our pilot observations and tests have enabled us to develop a strategy to search for HI absorption sources using the data from the FAST extragalactic HI survey, which is one of the key projects undertaken at FAST. We expect that over 1,500 extragalactic HI absorbing systems could be detected with survey data, based on sensitivity level we achieved in pilot observations.

astro-ph.GA↗

arXiv2021

AutoKWS: Keyword Spotting with Differentiable Architecture Search

Smart audio devices are gated by an always-on lightweight keyword spotting program to reduce power consumption. It is however challenging to design models that have both high accuracy and low latency for accurate and fast responsiveness. Many efforts have been made to develop end-to-end neural networks, in which depthwise separable convolutions, temporal convolutions, and LSTMs are adopted as building units. Nonetheless, these networks designed with human expertise may not achieve an optimal trade-off in an expansive search space. In this paper, we propose to leverage recent advances in differentiable neural architecture search to discover more efficient networks. Our searched model attains 97.2% top-1 accuracy on Google Speech Command Dataset v1 with only nearly 100K parameters.

eess.AS↗

arXiv2021

Improving Accuracy and Diversity in Matching of Recommendation with Diversified Preference Network

Recently, real-world recommendation systems need to deal with millions of candidates. It is extremely challenging to conduct sophisticated end-to-end algorithms on the entire corpus due to the tremendous computation costs. Therefore, conventional recommendation systems usually contain two modules. The matching module focuses on the coverage, which aims to efficiently retrieve hundreds of items from large corpora, while the ranking module generates specific ranks for these items. Recommendation diversity is an essential factor that impacts user experience. Most efforts have explored recommendation diversity in ranking, while the matching module should take more responsibility for diversity. In this paper, we propose a novel Heterogeneous graph neural network framework for diversified recommendation (GraphDR) in matching to improve both recommendation accuracy and diversity. Specifically, GraphDR builds a huge heterogeneous preference network to record different types of user preferences, and conduct a field-level heterogeneous graph attention network for node aggregation. We also innovatively conduct a neighbor-similarity based loss to balance both recommendation accuracy and diversity for the diversified matching task. In experiments, we conduct extensive online and offline evaluations on a real-world recommendation system with various accuracy and diversity metrics and achieve significant improvements. We also conduct model analyses and case study for a better understanding of our model. Moreover, GraphDR has been deployed on a well-known recommendation system, which affects millions of users. The source code will be released.

cs.IR↗

arXiv2021

Time domain analysis for electromagnetic scattering by an elastic obstacle in a two-layered medium

In this paper, we consider the scattering of a time-dependent electromagnetic wave by an elastic body immersed in the lower half-space of a two-layered background medium which is separated by an unbounded rough surface. By proposing two exact transparent boundary conditions (TBCs) on the artificial planes, we reformulate the unbounded scattering problem into an equivalent initial-boundary value problem in a strip domain with the well-posedness and stability proved using the Laplace transform, variational method and energy method. A perfectly matched layer (PML) is then introduced to truncate the interaction problem with two finite layers containing the elastic body, leading to a PML problem in a finite strip domain. We further verify the existence, uniqueness and stability estimate of solution for the PML problem. Finally, we establish the exponential convergence in terms of the thickness and parameters of the PML layers via an error estimate on the electric-to-magnetic (EtM) capacity operators between the original problem and the PML problem.

math.AP↗