arXiv subjects

Yuanyuan Liu

Publications and source records attributed to Yuanyuan Liu.

At least 73 records · Page 4Linked to original sources

arXiv2022

Construction of Lyapunov Functions Using Vector Field Decomposition

In the present paper, a novel vector field decomposition based approach for constructing Lyapunov functions is proposed. For a given dynamical system, if the defining vector field admits a decomposition into two mutually orthogonal vector fields, one of which is curl-free and the other is divergence-free, then the potential function of the former can serve as a Lyapunov function candidate, since its positive definiteness will reflect the stability of the system. Moreover, under some additional conditions, its sublevel sets will give the exact attraction domain of the system. A sufficient condition for the existence of the proposed vector field decomposition is first obtained for $2$-dimensional systems by solving a partial differential equation and then generalized to $n$-dimensional systems. Furthermore, the proposed vector field decomposition always exists for linear systems and can be obtained by solving a specific algebraic Riccati equation.

eess.SY↗

arXiv2022

Matrix-analytic methods for solving Poisson's equation with applications to Markov chains of GI/G/1-type

In this paper, we are devoted to developing matrix-analytic methods for solving Poisson's equation for irreducible and positive recurrent discrete-time Markov chains (DTMCs). Two special solutions, including the deviation matrix D and the expected additive-type functional matrix K, will be considered. The results are applied to Markov chains of GI/G/1-type and MAP/G/1 queues with negative customers. Further extensions to continuous-time Markov chains (CTMCs) are also investigated.

math.PR↗

arXiv2022

On Convergence of General Truncation-Augmentation Schemes for Approximating Stationary Distributions of Markov Chains

In the analysis of Markov chains and processes, it is sometimes convenient to replace an unbounded state space with a "truncated" bounded state space. When such a replacement is made, one often wants to know whether the equilibrium behavior of the truncated chain or process is close to that of the untruncated system. For example, such questions arise naturally when considering numerical methods for computing stationary distributions on unbounded state space. In this paper, we study general truncation-augmentation schemes, in which the substochastic truncated "northwest corner" of the transition matrix or kernel is stochasticized (or augmented) arbitrarily. In the presence of a Lyapunov condition involving a coercive function, we show that such schemes are generally convergent in countable state space, provided that the truncation is chosen as a sublevel set of the Lyapunov function. For stochastically monotone Markov chains on $\mathbb Z_+$, we prove that we can always choose the truncation sets to be of the form $\{0,1,...,n\}$. We then provide sufficient conditions for weakly continuous Markov chains under which general truncation-augmentation schemes converge weakly in continuous state space. Finally, we briefly discuss the extension of the theory to continuous time Markov jump processes.

math.PR↗

arXiv2022

Video Super Resolution Based on Deep Learning: A Comprehensive Survey

In recent years, deep learning has made great progress in many fields such as image recognition, natural language processing, speech recognition and video super-resolution. In this survey, we comprehensively investigate 33 state-of-the-art video super-resolution (VSR) methods based on deep learning. It is well known that the leverage of information within video frames is important for video super-resolution. Thus we propose a taxonomy and classify the methods into six sub-categories according to the ways of utilizing inter-frame information. Moreover, the architectures and implementation details of all the methods are depicted in detail. Finally, we summarize and compare the performance of the representative VSR method on some benchmark datasets. We also discuss some challenges, which need to be further addressed by researchers in the community of VSR. To the best of our knowledge, this work is the first systematic review on VSR tasks, and it is expected to make a contribution to the development of recent studies in this area and potentially deepen our understanding to the VSR techniques based on deep learning.

cs.CV↗

arXiv2022

Dual Perceptual Loss for Single Image Super-Resolution Using ESRGAN

The proposal of perceptual loss solves the problem that per-pixel difference loss function causes the reconstructed image to be overly-smooth, which acquires a significant progress in the field of single image super-resolution reconstruction. Furthermore, the generative adversarial networks (GAN) is applied to the super-resolution field, which effectively improves the visual quality of the reconstructed image. However, under the condtion of high upscaling factors, the excessive abnormal reasoning of the network produces some distorted structures, so that there is a certain deviation between the reconstructed image and the ground-truth image. In order to fundamentally improve the quality of reconstructed images, this paper proposes a effective method called Dual Perceptual Loss (DP Loss), which is used to replace the original perceptual loss to solve the problem of single image super-resolution reconstruction. Due to the complementary property between the VGG features and the ResNet features, the proposed DP Loss considers the advantages of learning two features simultaneously, which significantly improves the reconstruction effect of images. The qualitative and quantitative analysis on benchmark datasets demonstrates the superiority of our proposed method over state-of-the-art super-resolution methods.

eess.IV↗

arXiv2021

Equilibrated Zeroth-Order Unrolled Deep Networks for Accelerated MRI

Recently, model-driven deep learning unrolls a certain iterative algorithm of a regularization model into a cascade network by replacing the first-order information (i.e., (sub)gradient or proximal operator) of the regularizer with a network module, which appears more explainable and predictable compared to common data-driven networks. Conversely, in theory, there is not necessarily such a functional regularizer whose first-order information matches the replaced network module, which means the network output may not be covered by the original regularization model. Moreover, up to now, there is also no theory to guarantee the global convergence and robustness (regularity) of unrolled networks under realistic assumptions. To bridge this gap, this paper propose to present a safeguarded methodology on network unrolling. Specifically, focusing on accelerated MRI, we unroll a zeroth-order algorithm, of which the network module represents the regularizer itself, so that the network output can be still covered by the regularization model. Furthermore, inspired by the ideal of deep equilibrium models, before backpropagating, we carry out the unrolled iterative network to converge to a fixed point to ensure the convergence. In case the measurement data contains noise, we prove that the proposed network is robust against noisy interference. Finally, numerical experiments show that the proposed network consistently outperforms the state-of-the-art MRI reconstruction methods including traditional regularization methods and other deep learning methods.

cs.LG↗

arXiv2021

Highly accelerated MR parametric mapping by undersampling the k-space and reducing the contrast number simultaneously with deep learning

Purpose: To propose a novel deep learning-based method called RG-Net (reconstruction and generation network) for highly accelerated MR parametric mapping by undersampling k-space and reducing the acquired contrast number simultaneously. Methods: The proposed framework consists of a reconstruction module and a generative module. The reconstruction module reconstructs MR images from the acquired few undersampled k-space data with the help of a data prior. The generative module then synthesizes the remaining multi-contrast images from the reconstructed images, where the exponential model is implicitly incorporated into the image generation through the supervision of fully sampled labels. The RG-Net was evaluated on the T1\r{ho} mapping data of knee and brain at different acceleration rates. Regional T1\r{ho} analysis for cartilage and the brain was performed to access the performance of RG-Net. Results: RG-Net yields a high-quality T1\r{ho} map at a high acceleration rate of 17. Compared with the competing methods that only undersample k-space, our framework achieves better performance in T1\r{ho} value analysis. Our method also improves quality of T1\r{ho} maps on patient with glioma. Conclusion: The proposed RG-Net that adopted a new strategy by undersampling k-space and reducing the contrast number simultaneously for fast MR parametric mapping, can achieve a high acceleration rate while maintaining good reconstruction quality. The generative module of our framework can also be used as an insert module in other fast MR parametric mapping methods. Keywords: Deep learning, convolutional neural network, fast MR parametric mapping

eess.IV↗

arXiv2021

Global Controllability for General Nonlinear Systems

This note studies the global controllability of a general nonlinear system by extending it to affine one. The state space of the obtained affine system admits a nature foliation, each leaf of which is diffeomorphic to the state space of the original system. Through this foliation, the global controllability of these two kinds of systems are closely related and we prove that they are indeed equivalent. The result is then extended to the case with bounded inputs to make it practically more useful. To demonstrate the power of our approach, several examples are presented.

math.OC↗

arXiv2021

Expression Snippet Transformer for Robust Video-based Facial Expression Recognition

The recent success of Transformer has provided a new direction to various visual understanding tasks, including video-based facial expression recognition (FER). By modeling visual relations effectively, Transformer has shown its power for describing complicated patterns. However, Transformer still performs unsatisfactorily to notice subtle facial expression movements, because the expression movements of many videos can be too small to extract meaningful spatial-temporal relations and achieve robust performance. To this end, we propose to decompose each video into a series of expression snippets, each of which contains a small number of facial movements, and attempt to augment the Transformer's ability for modeling intra-snippet and inter-snippet visual relations, respectively, obtaining the Expression snippet Transformer (EST). In particular, for intra-snippet modeling, we devise an attention-augmented snippet feature extractor (AA-SFE) to enhance the encoding of subtle facial movements of each snippet by gradually attending to more salient information. In addition, for inter-snippet modeling, we introduce a shuffled snippet order prediction (SSOP) head and a corresponding loss to improve the modeling of subtle motion changes across subsequent snippets by training the Transformer to identify shuffled snippet orders. Extensive experiments on four challenging datasets (i.e., BU-3DFE, MMI, AFEW, and DFEW) demonstrate that our EST is superior to other CNN-based methods, obtaining state-of-the-art performance.

cs.CV↗

arXiv2021

Language-Independent Approach for Automatic Computation of Vowel Articulation Features in Dysarthric Speech Assessment

Imprecise vowel articulation can be observed in people with Parkinson's disease (PD). Acoustic features measuring vowel articulation have been demonstrated to be effective indicators of PD in its assessment. Standard clinical vowel articulation features of vowel working space area (VSA), vowel articulation index (VAI) and formants centralization ratio (FCR), are derived the first two formants of the three corner vowels /a/, /i/ and /u/. Conventionally, manual annotation of the corner vowels from speech data is required before measuring vowel articulation. This process is time-consuming. The present work aims to reduce human effort in clinical analysis of PD speech by proposing an automatic pipeline for vowel articulation assessment. The method is based on automatic corner vowel detection using a language universal phoneme recognizer, followed by statistical analysis of the formant data. The approach removes the restrictions of prior knowledge of speaking content and the language in question. Experimental results on a Finnish PD speech corpus demonstrate the efficacy and reliability of the proposed automatic method in deriving VAI, VSA, FCR and F2i/F2u (the second formant ratio for vowels /i/ and /u/). The automatically computed parameters are shown to be highly correlated with features computed with manual annotations of corner vowels. In addition, automatically and manually computed vowel articulation features have comparable correlations with experts' ratings on speech intelligibility, voice impairment and overall severity of communication disorder. Language-independence of the proposed approach is further validated on a Spanish PD database, PC-GITA, as well as on TORGO corpus of English dysarthric speech.

eess.AS↗

arXiv2021

Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learning

Federated Learning (FL) has become an active and promising distributed machine learning paradigm. As a result of statistical heterogeneity, recent studies clearly show that the performance of popular FL methods (e.g., FedAvg) deteriorates dramatically due to the client drift caused by local updates. This paper proposes a novel Federated Learning algorithm (called IGFL), which leverages both Individual and Group behaviors to mimic distribution, thereby improving the ability to deal with heterogeneity. Unlike existing FL methods, our IGFL can be applied to both client and server optimization. As a by-product, we propose a new attention-based federated learning in the server optimization of IGFL. To the best of our knowledge, this is the first time to incorporate attention mechanisms into federated optimization. We conduct extensive experiments and show that IGFL can significantly improve the performance of existing federated learning methods. Especially when the distributions of data among individuals are diverse, IGFL can improve the classification accuracy by about 13% compared with prior baselines.

cs.LG↗

arXiv2021

Learned Interpretable Residual Extragradient ISTA for Sparse Coding

Recently, the study on learned iterative shrinkage thresholding algorithm (LISTA) has attracted increasing attentions. A large number of experiments as well as some theories have proved the high efficiency of LISTA for solving sparse coding problems. However, existing LISTA methods are all serial connection. To address this issue, we propose a novel extragradient based LISTA (ELISTA), which has a residual structure and theoretical guarantees. In particular, our algorithm can also provide the interpretability for Res-Net to a certain extent. From a theoretical perspective, we prove that our method attains linear convergence. In practice, extensive empirical results verify the advantages of our method.

cs.LG↗

arXiv2021

Quadrature Photonic Spatial Ising Machine

The mining in physics and biology for accelerating the hardcore algorithm to solve non-deterministic polynomial (NP) hard problems has inspired a great amount of special-purpose ma-chine models. Ising machine has become an efficient solver for various combinatorial optimizationproblems. As a computing accelerator, large-scale photonic spatial Ising machine have great advan-tages and potentials due to excellent scalability and compact system. However, current fundamentallimitation of photonic spatial Ising machine is the configuration flexibility of problem implementationin the accelerator model. Arbitrary spin interactions is highly desired for solving various NP hardproblems. Moreover, the absence of external magnetic field in the proposed photonic Ising machinewill further narrow the freedom to map the optimization applications. In this paper, we propose anovel quadrature photonic spatial Ising machine to break through the limitation of photonic Isingaccelerator by synchronous phase manipulation in two and three sections. Max-cut problem solutionwith graph order of 100 and density from 0.5 to 1 is experimentally demonstrated after almost 100iterations. We derive and verify using simulation the solution for Max-cut problem with more than1600 nodes and the system tolerance for light misalignment. Moreover, vertex cover problem, modeled as an Ising model with external magnetic field, has been successfully implemented to achievethe optimal solution. Our work suggests flexible problem solution by large-scale photonic spatialIsing machine.

cs.ET↗

arXiv2021

Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling

Video super-resolution (VSR) aims at restoring a video in low-resolution (LR) and improving it to higher-resolution (HR). Due to the characteristics of video tasks, it is very important that motion information among frames should be well concerned, summarized and utilized for guidance in a VSR algorithm. Especially, when a video contains large motion, conventional methods easily bring incoherent results or artifacts. In this paper, we propose a novel deep neural network with Dual Subnet and Multi-stage Communicated Upsampling (DSMC) for super-resolution of videos with large motion. We design a new module named U-shaped residual dense network with 3D convolution (U3D-RDN) for fine implicit motion estimation and motion compensation (MEMC) as well as coarse spatial feature extraction. And we present a new Multi-Stage Communicated Upsampling (MSCU) module to make full use of the intermediate results of upsampling for guiding the VSR. Moreover, a novel dual subnet is devised to aid the training of our DSMC, whose dual loss helps to reduce the solution space as well as enhance the generalization ability. Our experimental results confirm that our method achieves superior performance on videos with large motion compared to state-of-the-art methods.

cs.CV↗

arXiv2021

Augmented truncation approximations to the solution of Poisson's equation for Markov chains

Poisson's equation has a lot of applications in various areas. Usually it is hard to derive the explicit expression of the solution of Poisson's equation for a Markov chain on an infinitely many state space. We will present a computational framework for the solution for both discrete-time Markov chains (DTMCs) and continuous-time Markov chains (CTMCs), by developing the technique of augmented truncation approximations. The convergence to the solution is investigated in terms of the assumption about the monotonicity of the first return times, and is further established for two types of truncation approximation schemes: the censored chain and the linear augmented truncation. Moreover, truncation approximations to the variance constant in central limit theorems (CLTs) are also considered. The results obtained are applied to discrete-time single-birth processes and continuous-time single-death processes.

math.PR↗

arXiv2020

Outlier-robust Kalman Filter in the Presence of Correlated Measurements

We consider the robust filtering problem for a state-space model with outliers in correlated measurements. We propose a new robust filtering framework to further improve the robustness of conventional robust filters. Specifically, the measurement fitting error is processed separately during the reweighting procedure, which differs from existing solutions where a jointly processed scheme is involved. Simulation results reveal that, under the same setup, the proposed method outperforms the existing robust filter when the outlier-contaminated measurements are correlated, while it has the same performance as the existing one in the presence of uncorrelated measurements since these two types of robust filters are equivalent under such a circumstance.

stat.AP↗

arXiv2020

Differentially Private ADMM Algorithms for Machine Learning

In this paper, we study efficient differentially private alternating direction methods of multipliers (ADMM) via gradient perturbation for many machine learning problems. For smooth convex loss functions with (non)-smooth regularization, we propose the first differentially private ADMM (DP-ADMM) algorithm with performance guarantee of $(ε,δ)$-differential privacy ($(ε,δ)$-DP). From the viewpoint of theoretical analysis, we use the Gaussian mechanism and the conversion relationship between Rényi Differential Privacy (RDP) and DP to perform a comprehensive privacy analysis for our algorithm. Then we establish a new criterion to prove the convergence of the proposed algorithms including DP-ADMM. We also give the utility analysis of our DP-ADMM. Moreover, we propose an accelerated DP-ADMM (DP-AccADMM) with the Nesterov's acceleration technique. Finally, we conduct numerical experiments on many real-world datasets to show the privacy-utility tradeoff of the two proposed algorithms, and all the comparative analysis shows that DP-AccADMM converges faster and has a better utility than DP-ADMM, when the privacy budget $ε$ is larger than a threshold.

cs.LG↗

arXiv2020

Boosting Gradient for White-Box Adversarial Attacks

Deep neural networks (DNNs) are playing key roles in various artificial intelligence applications such as image classification and object recognition. However, a growing number of studies have shown that there exist adversarial examples in DNNs, which are almost imperceptibly different from original samples, but can greatly change the network output. Existing white-box attack algorithms can generate powerful adversarial examples. Nevertheless, most of the algorithms concentrate on how to iteratively make the best use of gradients to improve adversarial performance. In contrast, in this paper, we focus on the properties of the widely-used ReLU activation function, and discover that there exist two phenomena (i.e., wrong blocking and over transmission) misleading the calculation of gradients in ReLU during the backpropagation. Both issues enlarge the difference between the predicted changes of the loss function from gradient and corresponding actual changes, and mislead the gradients which results in larger perturbations. Therefore, we propose a universal adversarial example generation method, called ADV-ReLU, to enhance the performance of gradient based white-box attack algorithms. During the backpropagation of the network, our approach calculates the gradient of the loss function versus network input, maps the values to scores, and selects a part of them to update the misleading gradients. Comprehensive experimental results on \emph{ImageNet} demonstrate that our ADV-ReLU can be easily integrated into many state-of-the-art gradient-based white-box attack algorithms, as well as transferred to black-box attack attackers, to further decrease perturbations in the ${\ell _2}$-norm.

cs.LG↗