arXiv subjects
Publications and source records attributed to Xin Liu.
In this paper, we prove that the global version of the $Ł$ojasiewicz gradient inequality holds for quadratic sphere constrained optimization problem with exponent $θ=\frac{3}{4}$. An example from Ting Kei Pong shows that $θ=\frac{3}{4}$ is tight. This is the first $Ł$ojasiewicz gradient inequality established for the sphere constrained optimization problem with a linear term.
This paper presents an academia-industry joint case study, which was conducted to quantify and compare multi-year changes in power production performance of multiple turbines scattered over a mid-size wind farm. This analysis is referred to as a space-time performance comparison. One key aspect in power performance analysis is to have the wind and environmental inputs controlled for. This research employs, in a sequential fashion, two principal modeling components to exercise tight control of multiple input conditions -- a covariate matching method, followed by a Gaussian process model-based functional comparison. The analysis method is applied to a wind farm that houses 66 turbines on a moderately complex terrain. The power production and environmental data span nearly four years, during which period the turbines have gone through multiple technical upgrades. The space-time analysis presents a quantitative and global picture showing how turbines differ relative to each other as well as how each of them changes over time.
This paper studies load balancing for many-server ($N$ servers) systems. Each server has a buffer of size $b-1,$ and can have at most one job in service and $b-1$ jobs in the buffer. The service time of a job follows the Coxian-2 distribution. We focus on steady-state performance of load balancing policies in the heavy traffic regime such that the normalized load of system is $λ= 1 - N^{-α}$ for $0<α<0.5.$ We identify a set of policies that achieve asymptotic zero waiting. The set of policies include several classical policies such as join-the-shortest-queue (JSQ), join-the-idle-queue (JIQ), idle-one-first (I1F) and power-of-$d$-choices (Po$d$) with $d=O(N^α\log N)$. The proof of the main result is based on Stein's method and state space collapse. A key technical contribution of this paper is the iterative state space collapse approach that leads to a simple generator approximation when applying Stein's method.
The COVID-19 pandemic has spread globally for several months. Because its transmissibility and high pathogenicity seriously threaten people's lives, it is crucial to accurately and quickly detect COVID-19 infection. Many recent studies have shown that deep learning (DL) based solutions can help detect COVID-19 based on chest CT scans. However, most existing work focuses on 2D datasets, which may result in low quality models as the real CT scans are 3D images. Besides, the reported results span a broad spectrum on different datasets with a relatively unfair comparison. In this paper, we first use three state-of-the-art 3D models (ResNet3D101, DenseNet3D121, and MC3\_18) to establish the baseline performance on the three publicly available chest CT scan datasets. Then we propose a differentiable neural architecture search (DNAS) framework to automatically search for the 3D DL models for 3D chest CT scans classification with the Gumbel Softmax technique to improve the searching efficiency. We further exploit the Class Activation Mapping (CAM) technique on our models to provide the interpretability of the results. The experimental results show that our automatically searched models (CovidNet3D) outperform the baseline human-designed models on the three datasets with tens of times smaller model size and higher accuracy. Furthermore, the results also verify that CAM can be well applied in CovidNet3D for COVID-19 datasets to provide interpretability for medical diagnosis.
Differential evolution is one of the most prestigious population-based stochastic optimization algorithm for black-box problems. The performance of a differential evolution algorithm depends highly on its mutation and crossover strategy and associated control parameters. However, the determination process for the most suitable parameter setting is troublesome and time-consuming. Adaptive control parameter methods that can adapt to problem landscape and optimization environment are more preferable than fixed parameter settings. This paper proposes a novel adaptive parameter control approach based on learning from the optimization experiences over a set of problems. In the approach, the parameter control is modeled as a finite-horizon Markov decision process. A reinforcement learning algorithm, named policy gradient, is applied to learn an agent (i.e. parameter controller) that can provide the control parameters of a proposed differential evolution adaptively during the search procedure. The differential evolution algorithm based on the learned agent is compared against nine well-known evolutionary algorithms on the CEC'13 and CEC'17 test suites. Experimental results show that the proposed algorithm performs competitively against these compared algorithms on the test suites.
The explosive growth of bandwidth hungry Internet applications has led to the rapid development of new generation mobile network technologies that are expected to provide broadband access to the Internet in a pervasive manner. For example, 6G networks are capable of providing high-speed network access by exploiting higher frequency spectrum; high-throughout satellite communication services are also adopted to achieve pervasive coverage in remote and isolated areas. In order to enable seamless access, Integrated Satellite-Terrestrial Communication Networks (ISTCN) has emerged as an important research area. ISTCN aims to provide high speed and pervasive network services by integrating broadband terrestrial mobile networks with satellite communication networks. As terrestrial mobile networks began to use higher frequency spectrum (between 3GHz to 40GHz) which overlaps with that of satellite communication (4GHz to 8GHz for C band and 26GHz to 40GHz for Ka band), there are opportunities and challenges. On one hand, satellite terminals can potentially access terrestrial networks in an integrated manner; on the other hand, there will be more congestion and interference in this spectrum, hence more efficient spectrum management techniques are required. In this paper, we propose a new technique to improve spectrum sharing performance by introducing Non-orthogonal Frequency Division Multiplexing (NOMA) and Cognitive Radio (CR) in the spectrum sharing of ISTCN. In essence, NOMA technology improves spectrum efficiency by allowing different users to transmit on the same carrier and distinguishing users by user power levels while CR technology improves spectrum efficiency through dynamic spectrum sharing. Furthermore, some open researches and challenges in ISTCN will be discussed.
Super-resolution (SR) is a coveted image processing technique for mobile apps ranging from the basic camera apps to mobile health. Existing SR algorithms rely on deep learning models with significant memory requirements, so they have yet to be deployed on mobile devices and instead operate in the cloud to achieve feasible inference time. This shortcoming prevents existing SR methods from being used in applications that require near real-time latency. In this work, we demonstrate state-of-the-art latency and accuracy for on-device super-resolution using a novel hybrid architecture called SplitSR and a novel lightweight residual block called SplitSRBlock. The SplitSRBlock supports channel-splitting, allowing the residual blocks to retain spatial information while reducing the computation in the channel dimension. SplitSR has a hybrid design consisting of standard convolutional blocks and lightweight residual blocks, allowing people to tune SplitSR for their computational budget. We evaluate our system on a low-end ARM CPU, demonstrating both higher accuracy and up to 5 times faster inference than previous approaches. We then deploy our model onto a smartphone in an app called ZoomSR to demonstrate the first-ever instance of on-device, deep learning-based SR. We conducted a user study with 15 participants to have them assess the perceived quality of images that were post-processed by SplitSR. Relative to bilinear interpolation -- the existing standard for on-device SR -- participants showed a statistically significant preference when looking at both images (Z=-9.270, p<0.01) and text (Z=-6.486, p<0.01).
To achieve reliable mining results for massive vessel trajectories, one of the most important challenges is how to efficiently compute the similarities between different vessel trajectories. The computation of vessel trajectory similarity has recently attracted increasing attention in the maritime data mining research community. However, traditional shape- and warping-based methods often suffer from several drawbacks such as high computational cost and sensitivity to unwanted artifacts and non-uniform sampling rates, etc. To eliminate these drawbacks, we propose an unsupervised learning method which automatically extracts low-dimensional features through a convolutional auto-encoder (CAE). In particular, we first generate the informative trajectory images by remapping the raw vessel trajectories into two-dimensional matrices while maintaining the spatio-temporal properties. Based on the massive vessel trajectories collected, the CAE can learn the low-dimensional representations of informative trajectory images in an unsupervised manner. The trajectory similarity is finally equivalent to efficiently computing the similarities between the learned low-dimensional features, which strongly correlate with the raw vessel trajectories. Comprehensive experiments on realistic data sets have demonstrated that the proposed method largely outperforms traditional trajectory similarity computation methods in terms of efficiency and effectiveness. The high-quality trajectory clustering performance could also be guaranteed according to the CAE-based trajectory similarity computation results.
Novelty detection using deep generative models such as autoencoder, generative adversarial networks mostly takes image reconstruction error as novelty score function. However, image data, high dimensional as it is, contains a lot of different features other than class information which makes models hard to detect novelty data. The problem gets harder in multi-modal normality case. To address this challenge, we propose a new way of measuring novelty score in multi-modal normality cases using orthogonalized latent space. Specifically, we employ orthogonal low-rank embedding in the latent space to disentangle the features in the latent space using mutual class information. With the orthogonalized latent space, novelty score is defined by the change of each latent vector. Proposed algorithm was compared to state-of-the-art novelty detection algorithms using GAN such as RaPP and OCGAN, and experimental results show that ours outperforms those algorithms.
Most of the current anti-jamming algorithms for wireless communications only consider how to avoid jamming attacks, but ignore that the communication waveform or frequency action may be obtained by the jammers. Although existing anti-jamming methods can guarantee temporary communication effects, the long-term performance of these anti-jamming methods may be depressed when intelligent jammers are capable of learning from historical communication activities. Aiming at this issue, a hidden anti-jamming method based on the idea of reducing the jammer's sense probability is proposed. Firstly, the sensing probability of the jammer is obtained by calculating the correlation between the actions of the jammer and the user. Later, a deep reinforcement learning framework is designed, which aims at not only maximizing the communication throughput but also minimizing the action's correlation between the jammer and the user. Finally, a hidden anti-jamming algorithm is proposed, which links the instantaneous return with the communication quality of users and the correlation between users and jammer. The simulation result shows that the proposed algorithm not only avoids being sensed by the jammer but also improves its anti-jamming performance compared to the current algorithm that only considers jamming avoidance.
We perform a systematic search for high-redshift ($z >$ 1.5) extreme variability quasars (EVQs) using repeat spectra from the Sixteenth Data Release of Sloan Digital Sky Survey, which provides a baseline spanning up to $\sim$18 yrs in the observed frame. We compile a sample of 348 EVQs with a maximum continuum variability at rest frame 1450 Angstrom of more than 100% (i.e., $δ$V $\equiv$ (Max$-$Min)/Mean $>$1). The EVQs show a range of emission line variability, including 23 where at least one line in our redshift range disappears below detectability, which can then be seen as analogous to low-redshift changing-look quasars (CLQs)". Importantly, spurious CLQs caused by SDSS problematic spectral flux calibration, e.g., fiber drop issue, have been rejected. The similar properties (e.g., continuum/line, difference-composite spectra and Eddington ratio) of normal EVQs and CLQs, implies that they are basically the same physical population with analogous intrinsic variability mechanisms, as a tail of a continuous distribution of normal quasar properties. In addition, we find no reliable evidence ($\lesssim$ 1$σ$) to support that the CLQs are a subset of EVQs with less efficient accretion. Finally, we also confirm the anti-breathing of C IV (i.e., line width increases as luminosity increases) in EVQs, and find that in addition to $\sim$ 0.4 dex systematic uncertainty in single-epoch C IV virial black hole mass estimates, an extra scatter of $\sim$ 0.3 dex will be introduced by extreme variability.
Graph Convolutional Network (GCN) has experienced great success in graph analysis tasks. It works by smoothing the node features across the graph. The current GCN models overwhelmingly assume that the node feature information is complete. However, real-world graph data are often incomplete and containing missing features. Traditionally, people have to estimate and fill in the unknown features based on imputation techniques and then apply GCN. However, the process of feature filling and graph learning are separated, resulting in degraded and unstable performance. This problem becomes more serious when a large number of features are missing. We propose an approach that adapts GCN to graphs containing missing features. In contrast to traditional strategy, our approach integrates the processing of missing features and graph learning within the same neural network architecture. Our idea is to represent the missing data by Gaussian Mixture Model (GMM) and calculate the expected activation of neurons in the first hidden layer of GCN, while keeping the other layers of the network unchanged. This enables us to learn the GMM parameters and network weight parameters in an end-to-end manner. Notably, our approach does not increase the computational complexity of GCN and it is consistent with GCN when the features are complete. We demonstrate through extensive experiments that our approach significantly outperforms the imputation-based methods in node classification and link prediction tasks. We show that the performance of our approach for the case with a low level of missing features is even superior to GCN for the case with complete features.
The NASA LISA Study Team was tasked to study how NASA might support US scientists to participate and maximize the science return from the Laser Interferometer Space Antenna (LISA) mission. LISA is gravitational wave observatory led by ESA with NASA as a junior partner, and is scheduled to launch in 2034. Among our findings: LISA science productivity is greatly enhanced by a full-featured US science center and an open access data model. As other major missions have demonstrated, a science center acts as both a locus and an amplifier of research innovation, data analysis, user support, user training and user interaction. In its most basic function, a US Science Center could facilitate entry into LISA science by hosting a Data Processing Center and a portal for the US community to access LISA data products. However, an enhanced LISA Science Center could: support one of the parallel independent processing pipelines required for data product validation; stimulate the high level of research on data analysis that LISA demands; support users unfamiliar with a novel observatory; facilitate astrophysics and fundamental research; provide an interface into the subtleties of the instrument to validate extraordinary discoveries; train new users; and expand the research community through guest investigator, postdoc and student programs. Establishing a US LISA Science Center well before launch can have a beneficial impact on the participation of the broader astronomical community by providing training, hosting topical workshops, disseminating mock catalogs, software pipelines, and documentation. Past experience indicates that successful science centers are established several years before launch; this early adoption model may be especially relevant for a pioneering mission like LISA.
Supermassive black holes (SMBHs) are ubiquitously found at the centers of most galaxies. Measuring SMBH mass is important for understanding the origin and evolution of SMBHs. However, traditional methods require spectral data which is expensive to gather. To solve this problem, we present an algorithm that weighs SMBHs using quasar light time series, circumventing the need for expensive spectra. We train, validate, and test neural networks that directly learn from the Sloan Digital Sky Survey (SDSS) Stripe 82 data for a sample of $9,038$ spectroscopically confirmed quasars to map out the nonlinear encoding between black hole mass and multi-color optical light curves. We find a 1$σ$ scatter of 0.35 dex between the predicted mass and the fiducial virial mass based on SDSS single-epoch spectra. Our results have direct implications for efficient applications with future observations from the Vera Rubin Observatory.
We propose a class of multipliers correction methods to minimize a differentiable function over the Stiefel manifold. The proposed methods combine a function value reduction step with a proximal correction step. The former one searches along an arbitrary descent direction in the Euclidean space instead of a vector in the tangent space of the Stiefel manifold. Meanwhile, the latter one minimizes a first-order proximal approximation of the objective function in the range space of the current iterate to make Lagrangian multipliers associated with orthogonality constraints symmetric at any accumulation point. The global convergence has been established for the proposed methods. Preliminary numerical experiments demonstrate that the new methods significantly outperform other state-of-the-art first-order approaches in solving various kinds of testing problems.
Noises, artifacts, and loss of information caused by the magnetic resonance (MR) reconstruction may compromise the final performance of the downstream applications. In this paper, we develop a re-weighted multi-task deep learning method to learn prior knowledge from the existing big dataset and then utilize them to assist simultaneous MR reconstruction and segmentation from the under-sampled k-space data. The multi-task deep learning framework is equipped with two network sub-modules, which are integrated and trained by our designed iterative teacher forcing scheme (ITFS) under the dynamic re-weighted loss constraint (DRLC). The ITFS is designed to avoid error accumulation by injecting the fully-sampled data into the training process. The DRLC is proposed to dynamically balance the contributions from the reconstruction and segmentation sub-modules so as to co-prompt the multi-task accuracy. The proposed method has been evaluated on two open datasets and one in vivo in-house dataset and compared to six state-of-the-art methods. Results show that the proposed method possesses encouraging capabilities for simultaneous and accurate MR reconstruction and segmentation.
In 2017, LHCb collaboration reported their first observation of the rare decays $B_s \to ϕ(f_0(980)$ $/f_2(1270) \to ) π^+π^-$ and the evidence of $B^0 \to ϕ(f_0(980)/f_2(1270)\to)π^+π^-$. Motivated by this, we study these quasi-two-body decays in the perturbative QCD approach. The branching fractions, $CP$ asymmetries and the polarization fractions are calculated. We find that within the appropriate two-meson wave functions, the calculated branching fractions are in agreement with the measurements of LHCb. Based on the narrow-width approximation, We also calculate the branching fractions of the quasi-two-body $B_{d,s}\to ϕ(f_0(980)/f_2(1270)\to) π^0π^0$ and $B_{d,s}\to ϕ(f_2(1270)\to) K^+K^-$, and hope the predictions to be tested in the ongoing LHCb and Belle II experiments. Moreover, the processes $B_{d,s}\to ϕf_2(1270)$ are also analyzed under this approximation. We note that the $CP$ asymmetries of these decays are very small, because these decays are either penguin dominant or pure penguin processes.
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world RAW-to-RGB mapping problem, where to goal was to map the original low-quality RAW images captured by the Huawei P20 device to the same photos obtained with the Canon 5D DSLR camera. The considered task embraced a number of complex computer vision subtasks, such as image demosaicing, denoising, white balancing, color and contrast correction, demoireing, etc. The target metric used in this challenge combined fidelity scores (PSNR and SSIM) with solutions' perceptual results measured in a user study. The proposed solutions significantly improved the baseline results, defining the state-of-the-art for practical image signal processing pipeline modeling.