arXiv subjects

Yu Wang

Publications and source records attributed to Yu Wang.

At least 1,189 records · Page 66Linked to original sources

arXiv2020

Curating a COVID-19 data repository and forecasting county-level death counts in the United States

As the COVID-19 outbreak evolves, accurate forecasting continues to play an extremely important role in informing policy decisions. In this paper, we present our continuous curation of a large data repository containing COVID-19 information from a range of sources. We use this data to develop predictions and corresponding prediction intervals for the short-term trajectory of COVID-19 cumulative death counts at the county-level in the United States up to two weeks ahead. Using data from January 22 to June 20, 2020, we develop and combine multiple forecasts using ensembling techniques, resulting in an ensemble we refer to as Combined Linear and Exponential Predictors (CLEP). Our individual predictors include county-specific exponential and linear predictors, a shared exponential predictor that pools data together across counties, an expanded shared exponential predictor that uses data from neighboring counties, and a demographics-based shared exponential predictor. We use prediction errors from the past five days to assess the uncertainty of our death predictions, resulting in generally-applicable prediction intervals, Maximum (absolute) Error Prediction Intervals (MEPI). MEPI achieves a coverage rate of more than 94% when averaged across counties for predicting cumulative recorded death counts two weeks in the future. Our forecasts are currently being used by the non-profit organization, Response4Life, to determine the medical supply need for individual hospitals and have directly contributed to the distribution of medical supplies across the country. We hope that our forecasts and data repository at https://covidseverity.com can help guide necessary county-specific decision-making and help counties prepare for their continued fight against COVID-19.

stat.AP↗

arXiv2020

Physical Adversarial Attack on Vehicle Detector in the Carla Simulator

In this paper, we tackle the issue of physical adversarial examples for object detectors in the wild. Specifically, we proposed to generate adversarial patterns to be applied on vehicle surface so that it's not recognizable by detectors in the photo-realistic Carla simulator. Our approach contains two main techniques, an Enlarge-and-Repeat process and a Discrete Searching method, to craft mosaic-like adversarial vehicle textures without access to neither the model weight of the detector nor a differential rendering procedure. The experimental results demonstrate the effectiveness of our approach in the simulator.

cs.CV↗

arXiv2020

Few-Shot Drum Transcription in Polyphonic Music

Data-driven approaches to automatic drum transcription (ADT) are often limited to a predefined, small vocabulary of percussion instrument classes. Such models cannot recognize out-of-vocabulary classes nor are they able to adapt to finer-grained vocabularies. In this work, we address open vocabulary ADT by introducing few-shot learning to the task. We train a Prototypical Network on a synthetic dataset and evaluate the model on multiple real-world ADT datasets with polyphonic accompaniment. We show that, given just a handful of selected examples at inference time, we can match and in some cases outperform a state-of-the-art supervised ADT approach under a fixed vocabulary setting. At the same time, we show that our model can successfully generalize to finer-grained or extended vocabularies unseen during training, a scenario where supervised approaches cannot operate at all. We provide a detailed analysis of our experimental results, including a breakdown of performance by sound class and by polyphony.

cs.SD↗

arXiv2020

Statistical Model Checking for Hyperproperties

Hyperproperties have shown to be a powerful tool for expressing and reasoning about information-flow security policies. In this paper, we investigate the problem of statistical model checking (SMC) for hyperproperties. Unlike exhaustive model checking, SMC works based on drawing samples from the system at hand and evaluate the specification with statistical confidence. The main benefit of applying SMC over exhaustive techniques is its efficiency and scalability. To reason about probabilistic hyperproperties, we first propose the temporal logic HyperPCLT* that extends PCTL* and HyperPCTL. We show that HyperPCLT* can express important probabilistic information-flow security policies that cannot be expressed with HyperPCTL. Then, we introduce SMC algorithms for verifying HyperPCLT* formulas on discrete-time Markov chains, based on sequential probability ratio tests (SPRT) with a new notion of multi-dimensional indifference region. Our SMC algorithms can handle both non-nested and nested probability operators for any desired significance level. To show the effectiveness of our technique, we evaluate our SMC algorithms on four case studies focused on information security: timing side-channel vulnerability in encryption, probabilistic anonymity in dining cryptographers, probabilistic noninterference of parallel programs, and the performance of a randomized cache replacement policy that acts as a countermeasure against cache flush attacks.

cs.LO↗

arXiv2020

DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation

Budgeted pruning is the problem of pruning under resource constraints. In budgeted pruning, how to distribute the resources across layers (i.e., sparsity allocation) is the key problem. Traditional methods solve it by discretely searching for the layer-wise pruning ratios, which lacks efficiency. In this paper, we propose Differentiable Sparsity Allocation (DSA), an efficient end-to-end budgeted pruning flow. Utilizing a novel differentiable pruning process, DSA finds the layer-wise pruning ratios with gradient-based optimization. It allocates sparsity in continuous space, which is more efficient than methods based on discrete evaluation and search. Furthermore, DSA could work in a pruning-from-scratch manner, whereas traditional budgeted pruning methods are applied to pre-trained models. Experimental results on CIFAR-10 and ImageNet show that DSA could achieve superior performance than current iterative budgeted pruning methods, and shorten the time cost of the overall pruning process by at least 1.5x in the meantime.

cs.CV↗

arXiv2020

Antiferromagnetism of Double Molybdate LiFe(MoO$_4$)$_2$

The magnetic properties of the spin-5/2 double molybdate LiFe(MoO$_4$)$_2$ have been characterized by heat capacity, magnetic susceptibility, and neutron powder diffraction techniques. Unlike the multiferroic system LiFe(MoO$_4$)$_2$ which exhibits two successive magnetic transitions, LiFe(MoO$_4$)$_2$ undergoes only one antiferromagnetic transition at $T_N$ ~ 23.8 K. Its antiferromagnetic magnetic structure with the commensurate propagation vector k = (0, 0.5, 0) has been determined. Density functional theory calculations confirm the antiferromagnetic ground state and provide a numerical estimate of the relevant exchange coupling constants.

cond-mat.mtrl-sci↗

arXiv2020

Novel hydrogen clathrate hydrate

We report a new hydrogen clathrate hydrate synthesized at 1.2 GPa and 298 K documented by single-crystal X-ray diffraction, Raman spectroscopy, and first-principles calculations. The oxygen sublattice of the new clathrate hydrate matches that of ice II, while hydrogen molecules are in the ring cavities, which results in the trigonal R3c or R-3c space group (proton ordered or disordered, respectively) and the composition of (H2O)6H2. Raman spectroscopy and theoretical calculations reveal a hydrogen disordered nature of the new phase C1', distinct from the well-known ordered C1 clathrate, to which this new structure transforms upon compression and/or cooling. This new clathrate phase can be viewed as a realization of a disordered ice II, unobserved before, in contrast to all other ordered ice structures.

cond-mat.mtrl-sci↗

arXiv2020

Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification

Deep neural networks are highly effective when a large number of labeled samples are available but fail with few-shot classification tasks. Recently, meta-learning methods have received much attention, which train a meta-learner on massive additional tasks to gain the knowledge to instruct the few-shot classification. Usually, the training tasks are randomly sampled and performed indiscriminately, often making the meta-learner stuck into a bad local optimum. Some works in the optimization of deep neural networks have shown that a better arrangement of training data can make the classifier converge faster and perform better. Inspired by this idea, we propose an easy-to-hard expert meta-training strategy to arrange the training tasks properly, where easy tasks are preferred in the first phase, then, hard tasks are emphasized in the second phase. A task hardness aware module is designed and integrated into the training procedure to estimate the hardness of a task based on the distinguishability of its categories. In addition, we explore multiple hardness measurements including the semantic relation, the pairwise Euclidean distance, the Hausdorff distance, and the Hilbert-Schmidt independence criterion. Experimental results on the miniImageNet and tieredImageNetSketch datasets show that the meta-learners can obtain better results with our expert training strategy.

cs.CV↗

arXiv2020

Context-Aware Temporal Logic for Probabilistic Systems

In this paper, we introduce the context-aware probabilistic temporal logic (CAPTL) that provides an intuitive way to formalize system requirements by a set of PCTL objectives with a context-based priority structure. We formally present the syntax and semantics of CAPTL and propose a synthesis algorithm for CAPTL requirements. We also implement the algorithm based on the PRISM-games model checker. Finally, we demonstrate the usage of CAPTL on two case studies: a robotic task planning problem, and synthesizing error-resilient scheduler for micro-electrode-dot-array digital microfluidic biochips.

cs.LO↗

arXiv2020

ATOMS: ALMA Three-millimeter Observations of Massive Star-forming regions -- II. Compact objects in ACA observations and star formation scaling relations

We report studies of the relationships between the total bolometric luminosity ($L_{\rm bol}$ or $L_{\rm TIR}$) and the molecular line luminosities of $J=1-0$ transitions of H$^{13}$CN, H$^{13}$CO$^+$, HCN, and HCO$^+$ with data obtained from ACA observations in the "ATOMS" survey of 146 active Galactic star forming regions. The correlations between $L_{\rm bol}$ and molecular line luminosities $L'_{\rm mol}$ of the four transitions all appear to be approximately linear. Line emission of isotopologues shows as large scatters in $L_{\rm bol}$-$L'_{\rm mol}$ relations as their main line emission. The log($L_{\rm bol}$/$L'_{\rm mol}$) for different molecular line tracers have similar distributions. The $L_{\rm bol}$-to-$L'_{\rm mol}$ ratios do not change with galactocentric distances ($R_{\rm GC}$) and clump masses ($M_{\rm clump}$). The molecular line luminosity ratios (HCN-to-HCO$^+$, H$^{13}$CN-to-H$^{13}$CO$^+$, HCN-to-H$^{13}$CN and HCO$^+$-to-H$^{13}$CO$^+$) all appear constant against $L_{\rm bol}$, dust temperature ($T_{\rm d}$), $M_{\rm clump}$ and $R_{\rm GC}$. Our studies suggest that both the main lines and isotopologue lines are good tracers of the total masses of dense gas in Galactic molecular clumps. The large optical depths of main lines do not affect the interpretation of the slopes in star formation relations. We find that the mean star formation efficiency (SFE) of massive Galactic clumps in the "ATOMS" survey is reasonably consistent with other measures of the SFE for dense gas, even those using very different tracers or examining very different spatial scales.

astro-ph.GA↗

arXiv2020

ATOMS: ALMA Three-millimeter Observations of Massive Star-forming regions -- I. Survey description and a first look at G9.62+0.19

The "ATOMS," standing for {\it ALMA Three-millimeter Observations of Massive Star-forming regions}, survey has observed 146 active star forming regions with ALMA Band 3, aiming to systematically investigate the spatial distribution of various dense gas tracers in a large sample of Galactic massive clumps, to study the roles of stellar feedback in star formation, and to characterize filamentary structures inside massive clumps. In this work, the observations, data analysis, and example science of the "ATOMS" survey are presented, using a case study for the G9.62+0.19 complex. Toward this source, some transitions, commonly assumed to trace dense gas, including CS $J = 2-1$, HCO$^+$ $J = 1-0$ and HCN $J = 1-0$, are found to show extended gas emission in low density regions within the clump; less than 25\% of their emission is from dense cores. SO, CH$_3$OH, H$^{13}$CN and HC$_3$N show similar morphologies in their spatial distributions and reveal well the dense cores. Widespread narrow SiO emission is present (over $\sim$1 pc), which may be caused by slow shocks from large--scale colliding flows or H{\sc ii} regions. Stellar feedback from an expanding H{\sc ii} region has greatly reshaped the natal clump, significantly changed the spatial distribution of gas, and may also account for the sequential high-mass star formation in the G9.62+0.19 complex. The ATOMS survey data can be jointly analyzed with other survey data, e.g., "MALT90", "Orion B", "EMPIRE", "ALMA\_IMF", and "ALMAGAL", to deepen our understandings of "dense gas" star formation scaling relations and massive proto-cluster formation.

astro-ph.GA↗

arXiv2020

GE-SpMM: General-purpose Sparse Matrix-Matrix Multiplication on GPUs for Graph Neural Networks

Graph Neural Networks (GNNs) have achieved significant improvements in various domains. Sparse Matrix-Matrix multiplication (SpMM) is a fundamental operator in GNNs, which performs a multiplication between a sparse matrix and a dense matrix. Accelerating SpMM on parallel hardware like GPUs can face the following challenges: From the GNN application perspective, the compatibility needs to be considered. General GNN algorithms require SpMM-like operations (e.g., pooling) between matrices, which are not supported in current high-performance GPU libraries (e.g., Nvidia cuSPARSE). Moreover, the sophisticated preprocessing in previous implementations will lead to heavy data format conversion overheads in GNN frameworks. From the GPU hardware perspective, optimizations in SpMV (Sparse Matrix-Vector) designs on GPUs do not apply well to SpMM. SpMM exposes the column-wise parallelism in the dense output matrix, but straightforward generalization from SpMV leads to inefficient, uncoalesced access to sparse matrix in global memory. The sparse row data can be reused among GPU threads, which is neither possible in SpMM designs inherited from SpMV. To tackle these challenges, we propose GE-SpMM. GE-SpMM performs SpMM-like operation on sparse matrices represented in the most common Compressed Sparse Row (CSR) format, so it can be embedded in GNN frameworks with no preprocessing overheads and support general GNN algorithms. We introduce the Coalesced Row Caching method to process columns in parallel and ensure coalesced access to sparse matrix data. We also present the Coarse-grained Warp Merging to reduce redundant data loading among GPU warps. Experiments on a real-world graph dataset show that GE-SpMM achieves up to 1.41X speedup over Nvidia cuSPARSE and up to 1.81X over GraphBLAST. We also embed GE-SpMM in GNN frameworks and get up to 3.67X speedup over popular GNN models like GCN and GraphSAGE.

cs.DC↗

arXiv2020

Monitoring Depression Trend on Twitter during the COVID-19 Pandemic

The COVID-19 pandemic has severely affected people's daily lives and caused tremendous economic loss worldwide. However, its influence on people's mental health conditions has not received as much attention. To study this subject, we choose social media as our main data resource and create by far the largest English Twitter depression dataset containing 2,575 distinct identified depression users with their past tweets. To examine the effect of depression on people's Twitter language, we train three transformer-based depression classification models on the dataset, evaluate their performance with progressively increased training sizes, and compare the model's "tweet chunk"-level and user-level performances. Furthermore, inspired by psychological studies, we create a fusion classifier that combines deep learning model scores with psychological text features and users' demographic information and investigate these features' relations to depression signals. Finally, we demonstrate our model's capability of monitoring both group-level and population-level depression trends by presenting two of its applications during the COVID-19 pandemic. We hope this study can raise awareness among researchers and the general public of COVID-19's impact on people's mental health.

cs.SI↗

arXiv2020

AFDet: Anchor Free One Stage 3D Object Detection

High-efficiency point cloud 3D object detection operated on embedded systems is important for many robotics applications including autonomous driving. Most previous works try to solve it using anchor-based detection methods which come with two drawbacks: post-processing is relatively complex and computationally expensive; tuning anchor parameters is tricky. We are the first to address these drawbacks with an anchor free and Non-Maximum Suppression free one stage detector called AFDet. The entire AFDet can be processed efficiently on a CNN accelerator or a GPU with the simplified post-processing. Without bells and whistles, our proposed AFDet performs competitively with other one stage anchor-based methods on KITTI validation set and Waymo Open Dataset validation set.

cs.CV↗

arXiv2020

1st Place Solution for Waymo Open Dataset Challenge -- 3D Detection and Domain Adaptation

In this technical report, we introduce our winning solution "HorizonLiDAR3D" for the 3D detection track and the domain adaptation track in Waymo Open Dataset Challenge at CVPR 2020. Many existing 3D object detectors include prior-based anchor box design to account for different scales and aspect ratios and classes of objects, which limits its capability of generalization to a different dataset or domain and requires post-processing (e.g. Non-Maximum Suppression (NMS)). We proposed a one-stage, anchor-free and NMS-free 3D point cloud object detector AFDet, using object key-points to encode the 3D attributes, and to learn an end-to-end point cloud object detection without the need of hand-engineering or learning the anchors. AFDet serves as a strong baseline in our winning solution and significant improvements are made over this baseline during the challenges. Specifically, we design stronger networks and enhance the point cloud data using densification and point painting. To leverage camera information, we append/paint additional attributes to each point by projecting them to camera space and gathering image-based perception information. The final detection performance also benefits from model ensemble and Test-Time Augmentation (TTA) in both the 3D detection track and the domain adaptation track. Our solution achieves the 1st place with 77.11% mAPH/L2 and 69.49% mAPH/L2 respectively on the 3D detection track and the domain adaptation track.

cs.CV↗

arXiv2020

1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking

This technical report presents the online and real-time 2D and 3D multi-object tracking (MOT) algorithms that reached the 1st places on both Waymo Open Dataset 2D tracking and 3D tracking challenges. An efficient and pragmatic online tracking-by-detection framework named HorizonMOT is proposed for camera-based 2D tracking in the image space and LiDAR-based 3D tracking in the 3D world space. Within the tracking-by-detection paradigm, our trackers leverage our high-performing detectors used in the 2D/3D detection challenges and achieved 45.13% 2D MOTA/L2 and 63.45% 3D MOTA/L2 in the 2D/3D tracking challenges.

cs.CV↗

arXiv2020

2nd Place Solution for Waymo Open Dataset Challenge -- 2D Object Detection

A practical autonomous driving system urges the need to reliably and accurately detect vehicles and persons. In this report, we introduce a state-of-the-art 2D object detection system for autonomous driving scenarios. Specifically, we integrate both popular two-stage detector and one-stage detector with anchor free fashion to yield a robust detection. Furthermore, we train multiple expert models and design a greedy version of the auto ensemble scheme that automatically merges detections from different models. Notably, our overall detection system achieves 70.28 L2 mAP on the Waymo Open Dataset v1.2, ranking the 2nd place in the 2D detection track of the Waymo Open Dataset Challenges.

cs.CV↗

arXiv2020

Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training

Large-scale distributed training requires significant communication bandwidth for gradient exchange that limits the scalability of multi-node training, and requires expensive high-bandwidth network infrastructure. The situation gets even worse with distributed training on mobile devices (federated learning), which suffers from higher latency, lower throughput, and intermittent poor connections. In this paper, we find 99.9% of the gradient exchange in distributed SGD is redundant, and propose Deep Gradient Compression (DGC) to greatly reduce the communication bandwidth. To preserve accuracy during compression, DGC employs four methods: momentum correction, local gradient clipping, momentum factor masking, and warm-up training. We have applied Deep Gradient Compression to image classification, speech recognition, and language modeling with multiple datasets including Cifar10, ImageNet, Penn Treebank, and Librispeech Corpus. On these scenarios, Deep Gradient Compression achieves a gradient compression ratio from 270x to 600x without losing accuracy, cutting the gradient size of ResNet-50 from 97MB to 0.35MB, and for DeepSpeech from 488MB to 0.74MB. Deep gradient compression enables large-scale distributed training on inexpensive commodity 1Gbps Ethernet and facilitates distributed training on mobile. Code is available at: https://github.com/synxlin/deep-gradient-compression.

cs.CV↗