arXiv subjects

Ye Li

Publications and source records attributed to Ye Li.

At least 145 records · Page 8Linked to original sources

arXiv2023

Efficient Discrete Physics-informed Neural Networks for Addressing Evolutionary Partial Differential Equations

Physics-informed neural networks (PINNs) have shown promising potential for solving partial differential equations (PDEs) using deep learning. However, PINNs face training difficulties for evolutionary PDEs, particularly for dynamical systems whose solutions exhibit multi-scale or turbulent behavior over time. The reason is that PINNs may violate the temporal causality property since all the temporal features in the PINNs loss are trained simultaneously. This paper proposes to use implicit time differencing schemes to enforce temporal causality, and use transfer learning to sequentially update the PINNs in space as surrogates for PDE solutions in different time frames. The evolving PINNs are better able to capture the varying complexities of the evolutionary equations, while only requiring minor updates between adjacent time frames. Our method is theoretically proven to be convergent if the time step is small and each PINN in different time frames is well-trained. In addition, we provide state-of-the-art (SOTA) numerical results for a variety of benchmarks for which existing PINNs formulations may fail or be inefficient. We demonstrate that the proposed method improves the accuracy of PINNs approximation for evolutionary PDEs and improves efficiency by a factor of 4-40x.

cs.NE↗

arXiv2023

Spach Transformer: Spatial and Channel-wise Transformer Based on Local and Global Self-attentions for PET Image Denoising

Position emission tomography (PET) is widely used in clinics and research due to its quantitative merits and high sensitivity, but suffers from low signal-to-noise ratio (SNR). Recently convolutional neural networks (CNNs) have been widely used to improve PET image quality. Though successful and efficient in local feature extraction, CNN cannot capture long-range dependencies well due to its limited receptive field. Global multi-head self-attention (MSA) is a popular approach to capture long-range information. However, the calculation of global MSA for 3D images has high computational costs. In this work, we proposed an efficient spatial and channel-wise encoder-decoder transformer, Spach Transformer, that can leverage spatial and channel information based on local and global MSAs. Experiments based on datasets of different PET tracers, i.e., $^{18}$F-FDG, $^{18}$F-ACBC, $^{18}$F-DCFPyL, and $^{68}$Ga-DOTATATE, were conducted to evaluate the proposed framework. Quantitative results show that the proposed Spach Transformer framework outperforms state-of-the-art deep learning architectures. Our codes are available at https://github.com/sijang/SpachTransformer

eess.IV↗

arXiv2023

TTMFN: Two-stream Transformer-based Multimodal Fusion Network for Survival Prediction

Survival prediction plays a crucial role in assisting clinicians with the development of cancer treatment protocols. Recent evidence shows that multimodal data can help in the diagnosis of cancer disease and improve survival prediction. Currently, deep learning-based approaches have experienced increasing success in survival prediction by integrating pathological images and gene expression data. However, most existing approaches overlook the intra-modality latent information and the complex inter-modality correlations. Furthermore, existing modalities do not fully exploit the immense representational capabilities of neural networks for feature aggregation and disregard the importance of relationships between features. Therefore, it is highly recommended to address these issues in order to enhance the prediction performance by proposing a novel deep learning-based method. We propose a novel framework named Two-stream Transformer-based Multimodal Fusion Network for survival prediction (TTMFN), which integrates pathological images and gene expression data. In TTMFN, we present a two-stream multimodal co-attention transformer module to take full advantage of the complex relationships between different modalities and the potential connections within the modalities. Additionally, we develop a multi-head attention pooling approach to effectively aggregate the feature representations of the two modalities. The experiment results on four datasets from The Cancer Genome Atlas demonstrate that TTMFN can achieve the best performance or competitive results compared to the state-of-the-art methods in predicting the overall survival of patients.

eess.IV↗

arXiv2023

A global test of jet structure and delay time distribution of short-duration gamma-ray bursts

The multi-messenger joint observations of GW170817 and GRB170817A shed new light on the study of short-duration gamma-ray bursts (SGRBs). Not only did it substantiate the assumption that SGRBs originate from binary neutron star (BNS) mergers, but it also confirms that the jet generated by this type of merger must be structured, hence the observed energy of an SGRB depends on the viewing angle from the observer. However, the precise structure of the jet is still subject to debate. Moreover, whether a single unified jet model can be applied to all SGRBs is not known. Another uncertainty is the delay timescale of BNS mergers with respect to star formation history of the Universe. In this paper, we conduct a global test of both delay and jet models of BNS mergers across a wide parameter space with simulated SGRBs. We compare the simulated peak flux, redshift and luminosity distributions with the observed ones and test the goodness-of-fit for a set of models and parameter combinations. Our simulations suggest that GW170817/GRB 170817A and all SGRBs can be understood within the framework of a universal structured jet viewed at different viewing angles. Furthermore, models invoking a jet plus cocoon structure with a lognormal delay timescale is most favored. Some other combinations (e.g. a Gaussian delay with a power-law jet model) are also acceptable. However, the Gaussian delay with Gaussian jet model and the entire set of power-law delay models are disfavored.

astro-ph.HE↗

arXiv2023

Identifying the physical origin of gamma-ray bursts with supervised machine learning

The empirical classification of gamma-ray bursts (GRBs) into long and short GRBs based on their durations is already firmly established. This empirical classification is generally linked to the physical classification of GRBs originating from compact binary mergers and GRBs originating from massive star collapses, or Type I and II GRBs, with the majority of short GRBs belonging to Type I and the majority of long GRBs belonging to Type II. However, there is a significant overlap in the duration distributions of long and short GRBs. Furthermore, some intermingled GRBs, i.e., short-duration Type II and long-duration Type I GRBs, have been reported. A multi-parameter classification scheme of GRBs is evidently needed. In this paper, we seek to build such a classification scheme with supervised machine learning methods, chiefly XGBoost. We utilize the GRB Big Table and Greiner's GRB catalog and divide the input features into three subgroups: prompt emission, afterglow, and host galaxy. We find that the prompt emission subgroup performs the best in distinguishing between Type I and II GRBs. We also find the most important distinguishing feature in prompt emission to be T_{90}, hardness ratio, and fluence. After building the machine learning model, we apply it to the currently unclassified GRBs to predict their probabilities of being either GRB class, and we assign the most probable class of each GRB to be its possible physical class.

astro-ph.HE↗

arXiv2023

Valuation Duration of the Stock Market

At the peak of the tech bubble, only 0.57% of market valuation comes from dividends in the next year. Taking the ratio of total market value to the value of one-year dividends, we obtain a valuation-based duration of 175 years. In contrast, at the height of the global financial crisis, more than 2.2% of market value is from dividends in the next year, implying a duration of 46 years. What drives valuation duration? We find that market participants have limited information about cash flow beyond one year. Therefore, an increase in valuation duration is due to a decrease in the discount rate rather than good news about long-term growth. Accordingly, valuation duration negatively predicts annual market return with an out-of-sample R2 of 15%, robustly outperforming other predictors in the literature. While the price-dividend ratio reflects the overall valuation level, our valuation-based measure of duration captures the slope of the valuation term structure. We show that valuation duration, as a discount rate proxy, is a critical state variable that augments the price-dividend ratio in spanning the (latent) state space for stock-market dynamics.

q-fin.PR↗

arXiv2023

Sciences with the 2.5-meter Wide Field Survey Telescope (WFST)

The Wide Field Survey Telescope (WFST) is a dedicated photometric surveying facility being built jointly by the University of Science and Technology of China and the Purple Mountain Observatory. It is equipped with a 2.5-meter diameter primary mirror, an active optics system, and a mosaic CCD camera with 0.73 gigapixels on the primary focal plane for high-quality image capture over an FOV of 6.5-square-degree. It is anticipated that WFST will be set up at the Lenghu site in the summer of 2023 and begin to observe the northern sky in four optical bands (u, g, r, and i) with a range of cadences, from hourly/daily in the Deep High-Cadence Survey (DHS) program to semiweekly in the Wide-Field Survey (WFS) program, three months later. During a photometric night, a nominal 30 s exposure in the WFS program will reach a depth of 22.27, 23.32, 22.84, and 22.31 (AB magnitudes) in these four bands, respectively, allowing for the detection of a tremendous amount of transients in the low-z universe and a systematic investigation of the variability of Galactic and extragalactic objects. In the DHS program, intranight 90 s exposures as deep as 23 (u) and 24 mag (g), in combination with target of opportunity follow-ups, will provide a unique opportunity to explore energetic transients in demand for high sensitivities, including the electromagnetic counterparts of gravitational wave events, supernovae within a few hours of their explosions, tidal disruption events and fast, luminous optical transients even beyond a redshift of unity. In addition, the final 6-year co-added images, anticipated to reach g=25.8 mag in WFS or 1.5 mags deeper in DHS, will be of fundamental importance to general Galactic and extragalactic science. The highly uniform legacy surveys of WFST will serve as an indispensable complement to those of LSST that monitor the southern sky.

astro-ph.IM↗

arXiv2023

Underwater Object Tracker: UOSTrack for Marine Organism Grasping of Underwater Vehicles

A visual single-object tracker is an indispensable component of underwater vehicles (UVs) in marine organism grasping tasks. Its accuracy and stability are imperative to guide the UVs to perform grasping behavior. Although single-object trackers show competitive performance in the challenge of underwater image degradation, there are still issues with sample imbalance and exclusion of similar objects that need to be addressed for application in marine organism grasping. This paper proposes Underwater OSTrack (UOSTrack), which consists of underwater image and open-air sequence hybrid training (UOHT), and motion-based post-processing (MBPP). The UOHT training paradigm is designed to train the sample-imbalanced underwater tracker so that the tracker is exposed to a great number of underwater domain training samples and learns the feature expressions. The MBPP paradigm is proposed to exclude similar objects. It uses the estimation box predicted with a Kalman filter and the candidate boxes in the response map to relocate the lost tracked object in the candidate area. UOSTrack achieves an average performance improvement of 4.41% and 7.98% maximum compared to state-of-the-art methods on various benchmarks, respectively. Field experiments have verified the accuracy and stability of our proposed UOSTrack for UVs in marine organism grasping tasks. More details can be found at https://github.com/LiYunfengLYF/UOSTrack.

cs.CV↗

arXiv2023

Approximation and Generalization of DeepONets for Learning Operators Arising from a Class of Singularly Perturbed Problems

Singularly perturbed problems present inherent difficulty due to the presence of a thin boundary layer in its solution. To overcome this difficulty, we propose using deep operator networks (DeepONets), a method previously shown to be effective in approximating nonlinear operators between infinite-dimensional Banach spaces. In this paper, we demonstrate for the first time the application of DeepONets to one-dimensional singularly perturbed problems, achieving promising results that suggest their potential as a robust tool for solving this class of problems. We consider the convergence rate of the approximation error incurred by the operator networks in approximating the solution operator, and examine the generalization gap and empirical risk, all of which are shown to converge uniformly with respect to the perturbation parameter. By utilizing Shishkin mesh points as locations of the loss function, we conduct several numerical experiments that provide further support for the effectiveness of operator networks in capturing the singular boundary layer behavior.

math.NA↗

arXiv2023

Bi-LSTM Price Prediction based on Attention Mechanism

With the increasing enrichment and development of the financial derivatives market, the frequency of transactions is also faster and faster. Due to human limitations, algorithms and automatic trading have recently become the focus of discussion. In this paper, we propose a bidirectional LSTM neural network based on an attention mechanism, which is based on two popular assets, gold and bitcoin. In terms of Feature Engineering, on the one hand, we add traditional technical factors, and at the same time, we combine time series models to develop factors. In the selection of model parameters, we finally chose a two-layer deep learning network. According to AUC measurement, the accuracy of bitcoin and gold is 71.94% and 73.03% respectively. Using the forecast results, we achieved a return of 1089.34% in two years. At the same time, we also compare the attention Bi-LSTM model proposed in this paper with the traditional model, and the results show that our model has the best performance in this data set. Finally, we discuss the significance of the model and the experimental results, as well as the possible improvement direction in the future.

q-fin.CP↗

arXiv2023

Predicting RNA Secondary Structure on Universal Quantum Computer

It is the first step for understanding how RNA structure folds from base sequences that to know how its secondary structure is formed. Traditional energy-based algorithms are short of precision, particularly for non-nested sequences, while learning-based algorithms face challenges in obtaining high-quality training data. Recently, quantum annealer has rapidly predicted the folding of the secondary structure, highlighting that quantum computing is a promising solution to this problem. However, gate model algorithms for universal quantum computing are not available. In this paper, gate-based quantum algorithms will be presented, which are highly flexible and can be applied to various physical devices. Mapped all possible secondary structure to the state of a quadratic Hamiltonian, the whole folding process is described as a quadratic unconstrained binary optimization model. Then the model can be solved through quantum approximation optimization algorithm. We demonstrate the performance with both numerical simulation and experimental realization. Throughout our benchmark dataset, simulation results suggest that our quantum approach is comparable in accuracy to classical methods. For non-nested sequences, our quantum approach outperforms classical energy-based methods. Experimental results also indicate our method is robust in current noisy devices. It is the first instance of universal quantum algorithms being employed to tackle RNA folding problems, and our work provides a valuable model for utilizing universal quantum computers in solving RNA folding problems.

quant-ph↗

arXiv2023

Brain PET Synthesis from MRI Using Joint Probability Distribution of Diffusion Model at Ultrahigh Fields

MRI and PET are important modalities and can provide complementary information for the diagnosis of brain diseases because MRI can provide structural information of brain and PET can obtain functional information of brain. However, PET is usually missing. Especially, simultaneous PET and MRI imaging at ultrahigh field is not achievable in the current. Thus, synthetic PET using MRI at ultrahigh field is essential. In this paper, we synthetic PET using MRI as a guide by joint probability distribution of diffusion model (JPDDM). Meanwhile, We utilized our model in Ultrahigh Fields.

cs.MM↗

arXiv2023

OneShotSTL: One-Shot Seasonal-Trend Decomposition For Online Time Series Anomaly Detection And Forecasting

Seasonal-trend decomposition is one of the most fundamental concepts in time series analysis that supports various downstream tasks, including time series anomaly detection and forecasting. However, existing decomposition methods rely on batch processing with a time complexity of O(W), where W is the number of data points within a time window. Therefore, they cannot always efficiently support real-time analysis that demands low processing delay. To address this challenge, we propose OneShotSTL, an efficient and accurate algorithm that can decompose time series online with an update time complexity of O(1). OneShotSTL is more than $1,000$ times faster than the batch methods, with accuracy comparable to the best counterparts. Extensive experiments on real-world benchmark datasets for downstream time series anomaly detection and forecasting tasks demonstrate that OneShotSTL is from 10 to over 1,000 times faster than the state-of-the-art methods, while still providing comparable or even better accuracy.

cs.LG↗

arXiv2023

Simulation of chemical reaction dynamics based on quantum computing

The molecular energies of chemical systems have been successfully calculated on quantum computers, however, more attention has been paid to the dynamic process of chemical reactions in practical application, especially in catalyst design, material synthesis. Due to the limited the capabilities of the noisy intermediate scale quantum (NISQ) devices, directly simulating the reaction dynamics and determining reaction pathway still remain a challenge. Here we develop the ab initio molecular dynamics based on quantum computing to simulate reaction dynamics by extending correlated sampling approach. And, we use this approach to calculate Hessian matrix and evaluate computation resources. We test the performance of our approach by simulating hydrogen exchange reaction and bimolecular nucleophilic substitution SN2 reaction. Our results suggest that it is reliable to characterize the molecular structure, property, and reactivity, which is another important expansion of the application of quantum computing

quant-ph↗

arXiv2023

DAA: A Delta Age AdaIN operation for age estimation via binary code transformer

Naked eye recognition of age is usually based on comparison with the age of others. However, this idea is ignored by computer tasks because it is difficult to obtain representative contrast images of each age. Inspired by the transfer learning, we designed the Delta Age AdaIN (DAA) operation to obtain the feature difference with each age, which obtains the style map of each age through the learned values representing the mean and standard deviation. We let the input of transfer learning as the binary code of age natural number to obtain continuous age feature information. The learned two groups of values in Binary code mapping are corresponding to the mean and standard deviation of the comparison ages. In summary, our method consists of four parts: FaceEncoder, DAA operation, Binary code mapping, and AgeDecoder modules. After getting the delta age via AgeDecoder, we take the average value of all comparison ages and delta ages as the predicted age. Compared with state-of-the-art methods, our method achieves better performance with fewer parameters on multiple facial age datasets.

cs.CV↗

arXiv2023

Scalable Program Implementation and Simulation of the Large-Scale Quantum Algorithm: $1024\times 1024$ Quantum Linear Solver and Beyond

Program implementation and simulation are essential for research in the field of quantum algorithms. However, complex and large-scale quantum algorithms can pose challenges for existing quantum programming languages and simulators. Here, we present a scalable program implementation of the quantum walk on a sparse matrix and the quantum linear solver based on the quantum walk. Our implementation is based on a practical scenario in which the sparse matrix is stored in the compressed-sparse-column format in quantum random access memory. All necessary modules are implemented unitarily and are ensured to be decomposed at the quantum gate level, including implementing a quantum binary search and a modification of the original algorithm. The program is validated using a highly efficient quantum circuit simulator which is based on the register level and sparse state representation. With only a single core, we simulate the quantum walk on a 16384-dimensional matrix with 582 qubits in 1.1 minutes per step, as well as a quantum linear solver up to 1024 dimensions and 212245 steps in 70 hours. Our work narrows the gap between the simulation of a quantum algorithm and its classical counterparts, where the asymptotic complexity of our quantum linear solver simulation approximates a classical linear solver. These program implementation and simulation techniques have the potential to expand the boundary of numerical research for large-scale quantum algorithms, with implications for the development of error-correction-era quantum computing solutions.

quant-ph↗

arXiv2023

Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks

Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems, but they are still trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit stochastic gradient descent (ISGD) method to train PINNs for improving the stability of training process. We heuristically analyze how ISGD overcome stiffness in the gradient flow dynamics of PINNs, especially for problems with multi-scale solutions. We theoretically prove that for two-layer fully connected neural networks with large hidden nodes, randomly initialized ISGD converges to a globally optimal solution for the quadratic loss function. Empirical results demonstrate that ISGD works well in practice and compares favorably to other gradient-based optimization methods such as SGD and Adam, while can also effectively address the numerical stiffness in training dynamics via gradient descent.

cs.LG↗

arXiv2023

Interactive Log Parsing via Light-weight User Feedback

Template mining is one of the foundational tasks to support log analysis, which supports the diagnosis and troubleshooting of large scale Web applications. This paper develops a human-in-the-loop template mining framework to support interactive log analysis, which is highly desirable in real-world diagnosis or troubleshooting of Web applications but yet previous template mining algorithms fails to support it. We formulate three types of light-weight user feedbacks and based on them we design three atomic human-in-the-loop template mining algorithms. We derive mild conditions under which the outputs of our proposed algorithms are provably correct. We also derive upper bounds on the computational complexity and query complexity of each algorithm. We demonstrate the versatility of our proposed algorithms by combining them to improve the template mining accuracy of five representative algorithms over sixteen widely used benchmark datasets.

cs.AI↗