arXiv subjects

Fang Liu

Publications and source records attributed to Fang Liu.

At least 253 records · Page 14Linked to original sources

arXiv2022

Photon orbits and phase transition for Non-Linear charged Anti-de Sitter black holes

In this work, we investigate the relationship between the photon sphere radius and the first-order phase transition for the charged EPYM AdS black hole. Through the analysis, we find with a certain condition there exist the non-monotonic behaviors between the photon sphere radius, the impact parameter, the non-linear YM charge parameter, temperature, and pressure. And both the changes of photon sphere radius and impact parameter before and after phase transition can be regarded as the order parameter, their critical exponents near the critical point are equal to the same value $1/2$, just like the ordinary thermal systems. These indicate that there maybe exists a universal relationship of gravity nearby the critical point for a black hole thermodynamical system. Furthermore, the effect of impact parameter on the deflect angle is also investigated.

hep-th↗

arXiv2022

A Dual-fusion Semantic Segmentation Framework With GAN For SAR Images

Deep learning based semantic segmentation is one of the popular methods in remote sensing image segmentation. In this paper, a network based on the widely used encoderdecoder architecture is proposed to accomplish the synthetic aperture radar (SAR) images segmentation. With the better representation capability of optical images, we propose to enrich SAR images with generated optical images via the generative adversative network (GAN) trained by numerous SAR and optical images. These optical images can be used as expansions of original SAR images, thus ensuring robust result of segmentation. Then the optical images generated by the GAN are stitched together with the corresponding real images. An attention module following the stitched data is used to strengthen the representation of the objects. Experiments indicate that our method is efficient compared to other commonly used methods

eess.IV↗

arXiv2022

Symmetrized two-scale finite element discretizations for partial differential equations with symmetric solutions

In this paper, a symmetrized two-scale finite element method is proposed for a class of partial differential equations with symmetric solutions. With this method, the finite element approximation on a fine tensor product grid is reduced to the finite element approximations on a much coarse grid and a univariant fine grid. It is shown by both theory and numerics including electronic structure calculations that the resulting approximation still maintains an asymptotically optimal accuracy. Consequently the symmetrized two-scale finite element method reduces computational cost significantly.

math.NA↗

arXiv2022

Efficient Reinforcement Learning from Demonstration Using Local Ensemble and Reparameterization with Split and Merge of Expert Policies

The current work on reinforcement learning (RL) from demonstrations often assumes the demonstrations are samples from an optimal policy, an unrealistic assumption in practice. When demonstrations are generated by sub-optimal policies or have sparse state-action pairs, policy learned from sub-optimal demonstrations may mislead an agent with incorrect or non-local action decisions. We propose a new method called Local Ensemble and Reparameterization with Split and Merge of expert policies (LEARN-SAM) to improve efficiency and make better use of the sub-optimal demonstrations. First, LEARN-SAM employs a new concept, the lambda-function, based on a discrepancy measure between the current state to demonstrated states to "localize" the weights of the expert policies during learning. Second, LEARN-SAM employs a split-and-merge (SAM) mechanism by separating the helpful parts in each expert demonstration and regrouping them into new expert policies to use the demonstrations selectively. Both the lambda-function and SAM mechanism help boost the learning speed. Theoretically, we prove the invariant property of reparameterized policy before and after the SAM mechanism, providing theoretical guarantees for the convergence of the employed policy gradient method. We demonstrate the superiority of the LEARN-SAM method and its robustness with varying demonstration quality and sparsity in six experiments on complex continuous control problems of low to high dimensions, compared to existing methods on RL from demonstration.

cs.LG↗

arXiv2022

Putting Density Functional Theory to the Test in Machine-Learning-Accelerated Materials Discovery

Accelerated discovery with machine learning (ML) has begun to provide the advances in efficiency needed to overcome the combinatorial challenge of computational materials design. Nevertheless, ML-accelerated discovery both inherits the biases of training data derived from density functional theory (DFT) and leads to many attempted calculations that are doomed to fail. Many compelling functional materials and catalytic processes involve strained chemical bonds, open-shell radicals and diradicals, or metal-organic bonds to open-shell transition-metal centers. Although promising targets, these materials present unique challenges for electronic structure methods and combinatorial challenges for their discovery. In this Perspective, we describe the advances needed in accuracy, efficiency, and approach beyond what is typical in conventional DFT-based ML workflows. These challenges have begun to be addressed through ML models trained to predict the results of multiple methods or the differences between them, enabling quantitative sensitivity analysis. For DFT to be trusted for a given data point in a high-throughput screen, it must pass a series of tests. ML models that predict the likelihood of calculation success and detect the presence of strong correlation will enable rapid diagnoses and adaptation strategies. These "decision engines" represent the first steps toward autonomous workflows that avoid the need for expert determination of the robustness of DFT-based materials discoveries.

cond-mat.mtrl-sci↗

arXiv2022

Polyhalogenated Molecules in the Polarizable Ellipsoidal Force Field Model

Polyhalogenated compounds are common in industrial, agricultural, and environmental applications. These compounds contain more halogen bonds than monohalogenated compounds. The presence of coupled σ-holes in the covalent halogen atoms, which demonstrates strong interplay in halogen bonds, should be carefully evaluated in force field optimization. In this study, a polarizable ellipsoidal force field model was successfully applied to many possible halogenated benzenes. The symmetry of the fitted parameters was reproduced without any additional restrictions. The optimized parameters for the anisotropic electrostatic potential showed good accuracy, stability, and transferability with reasonable physical meanings. The parameter fitting protocol was efficiently performed on a laptop, showing the potential of being completely parallelized for thousands of halogenated homologues.

physics.chem-ph↗

arXiv2022

Variational Inference with NoFAS: Normalizing Flow with Adaptive Surrogate for Computationally Expensive Models

Fast inference of numerical model parameters from data is an important prerequisite to generate predictive models for a wide range of applications. Use of sampling-based approaches such as Markov chain Monte Carlo may become intractable when each likelihood evaluation is computationally expensive. New approaches combining variational inference with normalizing flow are characterized by a computational cost that grows only linearly with the dimensionality of the latent variable space, and rely on gradient-based optimization instead of sampling, providing a more efficient approach for Bayesian inference about the model parameters. Moreover, the cost of frequently evaluating an expensive likelihood can be mitigated by replacing the true model with an offline trained surrogate model, such as neural networks. However, this approach might generate significant bias when the surrogate is insufficiently accurate around the posterior modes. To reduce the computational cost without sacrificing inferential accuracy, we propose Normalizing Flow with Adaptive Surrogate (NoFAS), an optimization strategy that alternatively updates the normalizing flow parameters and surrogate model parameters. We also propose an efficient sample weighting scheme for surrogate model training that preserves global accuracy while effectively capturing high posterior density regions. We demonstrate the inferential and computational superiority of NoFAS against various benchmarks, including cases where the underlying model lacks identifiability. The source code and numerical experiments used for this study are available at https://github.com/cedricwangyu/NoFAS.

cs.LG↗

arXiv2022

Non-autoregressive Model for Full-line Code Completion

Code completion tools are frequently used by software developers to accelerate software development by suggesting the following code elements. Completing a sequence of code tokens (e.g., a full line of code) has been proved more efficient than predicting a single token at a time. To complete the code sequence, researchers are employing AutoRegressive (AR) decoders to generate tokens in a left-to-right, token-by-token fashion. Consequently, the prediction of the next token depends on all previously generated tokens, which leads to high latency in inference. To improve the efficiency and accuracy of full-line code completion, in this paper, we propose a Non-AutoRegressive (NAR) model for code completion boosted by a syntax-aware sampling strategy. Our experimental results on two widely used datasets suggest that our model outperforms both AR and NAR baselines on full-line code completion, and it is faster than the AR model with up to 9 times speed-up.

cs.SE↗

arXiv2022

Adaptive Noisy Data Augmentation for Regularized Estimation and Inference in Generalized Linear Models

We propose the AdaPtive Noise Augmentation (PANDA) procedure to regularize the estimation and inference of generalized linear models (GLMs). PANDA iteratively optimizes the objective function given noise augmented data until convergence to obtain the regularized model estimates. The augmented noises are designed to achieve various regularization effects, including $l_0$, bridge (lasso and ridge included), elastic net, adaptive lasso, and SCAD, as well as group lasso and fused ridge. We examine the tail bound of the noise-augmented loss function and establish the almost sure convergence of the noise-augmented loss function and its minimizer to the expected penalized loss function and its minimizer, respectively. We derive the asymptotic distributions for the regularized parameters, based on which, inferences can be obtained simultaneously with variable selection. PANDA exhibits ensemble learning behaviors that help further decrease the generalization error. Computationally, PANDA is easy to code, leveraging existing software for implementing GLMs, without resorting to complicated optimization techniques. We demonstrate the superior or similar performance of PANDA against the existing approaches of the same type of regularizers in simulated and real-life data. We show that the inferences through PANDA achieve nominal or near-nominal coverage and are far more efficient compared to a popular existing post-selection procedure.

stat.ML↗

arXiv2022

Learning Optimal K-space Acquisition and Reconstruction using Physics-Informed Neural Networks

The inherent slow imaging speed of Magnetic Resonance Image (MRI) has spurred the development of various acceleration methods, typically through heuristically undersampling the MRI measurement domain known as k-space. Recently, deep neural networks have been applied to reconstruct undersampled k-space data and have shown improved reconstruction performance. While most of these methods focus on designing novel reconstruction networks or new training strategies for a given undersampling pattern, e.g., Cartesian undersampling or Non-Cartesian sampling, to date, there is limited research aiming to learn and optimize k-space sampling strategies using deep neural networks. This work proposes a novel optimization framework to learn k-space sampling trajectories by considering it as an Ordinary Differential Equation (ODE) problem that can be solved using neural ODE. In particular, the sampling of k-space data is framed as a dynamic system, in which neural ODE is formulated to approximate the system with additional constraints on MRI physics. In addition, we have also demonstrated that trajectory optimization and image reconstruction can be learned collaboratively for improved imaging efficiency and reconstruction performance. Experiments were conducted on different in-vivo datasets (e.g., brain and knee images) acquired with different sequences. Initial results have shown that our proposed method can generate better image quality in accelerated MRI than conventional undersampling schemes in Cartesian and Non-Cartesian acquisitions.

eess.IV↗

arXiv2022

Transformers Meet Visual Learning Understanding: A Comprehensive Review

Dynamic attention mechanism and global modeling ability make Transformer show strong feature learning ability. In recent years, Transformer has become comparable to CNNs methods in computer vision. This review mainly investigates the current research progress of Transformer in image and video applications, which makes a comprehensive overview of Transformer in visual learning understanding. First, the attention mechanism is reviewed, which plays an essential part in Transformer. And then, the visual Transformer model and the principle of each module are introduced. Thirdly, the existing Transformer-based models are investigated, and their performance is compared in visual learning understanding applications. Three image tasks and two video tasks of computer vision are investigated. The former mainly includes image classification, object detection, and image segmentation. The latter contains object tracking and video classification. It is significant for comparing different models' performance in various tasks on several public benchmark data sets. Finally, ten general problems are summarized, and the developing prospects of the visual Transformer are given in this review.

cs.CV↗

arXiv2022

Learning to Recommend Method Names with Global Context

In programming, the names for the program entities, especially for the methods, are the intuitive characteristic for understanding the functionality of the code. To ensure the readability and maintainability of the programs, method names should be named properly. Specifically, the names should be meaningful and consistent with other names used in related contexts in their codebase. In recent years, many automated approaches are proposed to suggest consistent names for methods, among which neural machine translation (NMT) based models are widely used and have achieved state-of-the-art results. However, these NMT-based models mainly focus on extracting the code-specific features from the method body or the surrounding methods, the project-specific context and documentation of the target method are ignored. We conduct a statistical analysis to explore the relationship between the method names and their contexts. Based on the statistical results, we propose GTNM, a Global Transformer-based Neural Model for method name suggestion, which considers the local context, the project-specific context, and the documentation of the method simultaneously. Experimental results on java methods show that our model can outperform the state-of-the-art results by a large margin on method name suggestion, demonstrating the effectiveness of our proposed model.

cs.SE↗

arXiv2022

On-chip mechanical exceptional points based on an optomechanical zipper cavity

Exceptional points (EPs) represent a distinct type of spectral singularity in non-Hermitian systems, and intriguing physics concepts have been studied with optical EPs recently. As a system beyond photonics, the mechanical oscillators coupling with many physical systems are expected to be further exploited EPs for mechanical sensing, topology energy transfer, nonreciprocal dynamics etc. In this study, we demonstrated on-chip mechanical EPs with a silicon optomechanical zipper cavity, wherein two near-degenerate mechanical breathing modes are coupled via a single co-localized optical mode. By tailoring the dissipative and coherent couplings between two mechanical oscillators, the spectral splitting with 1/2 order response, a distinctive feature of EP, was observed successfully. Our work provides an integrated platform for investigating the physics related to mechanical EPs on silicon chips and suggests their possible applications for ultrasensitive measurements.

physics.optics↗

arXiv2022

Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularization

Training speaker-discriminative and robust speaker verification systems without speaker labels is still challenging and worthwhile to explore. In this study, we propose an effective self-supervised learning framework and a novel regularization strategy to facilitate self-supervised speaker representation learning. Different from contrastive learning-based self-supervised learning methods, the proposed self-supervised regularization (SSReg) focuses exclusively on the similarity between the latent representations of positive data pairs. We also explore the effectiveness of alternative online data augmentation strategies on both the time domain and frequency domain. With our strong online data augmentation strategy, the proposed SSReg shows the potential of self-supervised learning without using negative pairs and it can significantly improve the performance of self-supervised speaker representation learning with a simple Siamese network architecture. Comprehensive experiments on the VoxCeleb datasets demonstrate that our proposed self-supervised approach obtains a 23.4% relative improvement by adding the effective self-supervised regularization and outperforms other previous works.

eess.AS↗

arXiv2022

AdaAnn: Adaptive Annealing Scheduler for Probability Density Approximation

Approximating probability distributions can be a challenging task, particularly when they are supported over regions of high geometrical complexity or exhibit multiple modes. Annealing can be used to facilitate this task which is often combined with constant a priori selected increments in inverse temperature. However, using constant increments limit the computational efficiency due to the inability to adapt to situations where smooth changes in the annealed density could be handled equally well with larger increments. We introduce AdaAnn, an adaptive annealing scheduler that automatically adjusts the temperature increments based on the expected change in the Kullback-Leibler divergence between two distributions with a sufficiently close annealing temperature. AdaAnn is easy to implement and can be integrated into existing sampling approaches such as normalizing flows for variational inference and Markov chain Monte Carlo. We demonstrate the computational efficiency of the AdaAnn scheduler for variational inference with normalizing flows on a number of examples, including density approximation and parameter estimation for dynamical systems.

stat.CO↗

arXiv2021

Room-temperature on-chip generation of heralded single photons with switchable orbital angular momentum

In quantum optics, orbital angular momentum (OAM) is very promising to achieve high-dimensional quantum states due to the nature of infinite and discrete eigenvalue, which is quantized by the topological charge of l. Here, a heralded single-photon source with switchable OAM modes is proposed and demonstrated on silicon chip. At room-temperature, the heralded single photons with 11 OAM modes (l=2~6, -6~-1) have been successfully generated and switched through thermo-optical effect. We believe that such an integrated quantum source with multiple OAM modes and operating at room-temperature would provide a practical platform for high-dimensional quantum information processing. Moreover, our proposed architecture can also be extended to other material systems to further improve the performance of OAM quantum source.

quant-ph↗

arXiv2021

Phase transition of non-linear charged Anti-de Sitter black holes

Understanding the thermodynamic phase transition of black holes can provide a deep insight into the fundamental properties of black hole gravity to establish the theory of quantum gravity. We investigate the condition and latent heat of phase transition for non-linear charged AdS black holes using the Maxwell's equal-area law, and analysis the boundary and curve of the two-phase coexistence area in the expanded phase space. We suggest that the phase transition of the non-linear charged AdS black hole with the fixed temperature ($T<T_c$) is related to the electric potential at the horizon, not only to the location of horizon. Recently, the molecular number density was introduced to study the phase transition and microstructure of black holes. On this basis, we discuss the continuous phase transition of a non-linear charged AdS black hole to reveal the potential microstructure of a black hole by introducing the order parameter and using the scalar curvature.

hep-th↗

arXiv2021

Vis-TOP: Visual Transformer Overlay Processor

In recent years, Transformer has achieved good results in Natural Language Processing (NLP) and has also started to expand into Computer Vision (CV). Excellent models such as the Vision Transformer and Swin Transformer have emerged. At the same time, the platform for Transformer models was extended to embedded devices to meet some resource-sensitive application scenarios. However, due to the large number of parameters, the complex computational flow and the many different structural variants of Transformer models, there are a number of issues that need to be addressed in its hardware design. This is both an opportunity and a challenge. We propose Vis-TOP (Visual Transformer Overlay Processor), an overlay processor for various visual Transformer models. It differs from coarse-grained overlay processors such as CPU, GPU, NPE, and from fine-grained customized designs for a specific model. Vis-TOP summarizes the characteristics of all visual Transformer models and implements a three-layer and two-level transformation structure that allows the model to be switched or changed freely without changing the hardware architecture. At the same time, the corresponding instruction bundle and hardware architecture are designed in three-layer and two-level transformation structure. After quantization of Swin Transformer tiny model using 8-bit fixed points (fix_8), we implemented an overlay processor on the ZCU102. Compared to GPU, the TOP throughput is 1.5x higher. Compared to the existing Transformer accelerators, our throughput per DSP is between 2.2x and 11.7x higher than others. In a word, the approach in this paper meets the requirements of real-time AI in terms of both resource consumption and inference speed. Vis-TOP provides a cost-effective and power-effective solution based on reconfigurable devices for computer vision at the edge.

cs.CV↗