arXiv subjects

Chenglong Bao

Publications and source records attributed to Chenglong Bao.

51 records · Page 3Linked to original sources

arXiv2021

Stochastic Anderson Mixing for Nonconvex Stochastic Optimization

Anderson mixing (AM) is an acceleration method for fixed-point iterations. Despite its success and wide usage in scientific computing, the convergence theory of AM remains unclear, and its applications to machine learning problems are not well explored. In this paper, by introducing damped projection and adaptive regularization to classical AM, we propose a Stochastic Anderson Mixing (SAM) scheme to solve nonconvex stochastic optimization problems. Under mild assumptions, we establish the convergence theory of SAM, including the almost sure convergence to stationary points and the worst-case iteration complexity. Moreover, the complexity bound can be improved when randomly choosing an iterate as the output. To further accelerate the convergence, we incorporate a variance reduction technique into the proposed SAM. We also propose a preconditioned mixing strategy for SAM which can empirically achieve faster convergence or better generalization ability. Finally, we apply the SAM method to train various neural networks including the vanilla CNN, ResNets, WideResNet, ResNeXt, DenseNet and RNN. Experimental results on image classification and language model demonstrate the advantages of our method.

cs.LG↗

arXiv2021

An adaptive block Bregman proximal gradient method for computing stationary states of multicomponent phase-field crystal model

In this paper, we compute the stationary states of the multicomponent phase-field crystal model by formulating it as a block constrained minimization problem. The original infinite-dimensional non-convex minimization problem is approximated by a finite-dimensional constrained non-convex minimization problem after an appropriate spatial discretization. To efficiently solve the above optimization problem, we propose a so-called adaptive block Bregman proximal gradient (AB-BPG) algorithm that fully exploits the problem's block structure. The proposed method updates each order parameter alternatively, and the update order of blocks can be chosen in a deterministic or random manner. Besides, we choose the step size by developing a practical linear search approach such that the generated sequence either keeps energy dissipation or has a controllable subsequence with energy dissipation. The convergence property of the proposed method is established without the requirement of global Lipschitz continuity of the derivative of the bulk energy part by using the Bregman divergence. The numerical results on computing stationary ordered structures in binary, ternary, and quinary component coupled-mode Swift-Hohenberg models have shown a significant acceleration over many existing methods.

math.NA↗

arXiv2021

Tightness and Equivalence of Semidefinite Relaxations for MIMO Detection

The multiple-input multiple-output (MIMO) detection problem, a fundamental problem in modern digital communications, is to detect a vector of transmitted symbols from the noisy outputs of a fading MIMO channel. The maximum likelihood detector can be formulated as a complex least-squares problem with discrete variables, which is NP-hard in general. Various semidefinite relaxation (SDR) methods have been proposed in the literature to solve the problem due to their polynomial-time worst-case complexity and good detection error rate performance. In this paper, we consider two popular classes of SDR-based detectors and study the conditions under which the SDRs are tight and the relationship between different SDR models. For the enhanced complex and real SDRs proposed recently by Lu et al., we refine their analysis and derive the necessary and sufficient condition for the complex SDR to be tight, as well as a necessary condition for the real SDR to be tight. In contrast, we also show that another SDR proposed by Mobasher et al. is not tight with high probability under mild conditions. Moreover, we establish a general theorem that shows the equivalence between two subsets of positive semidefinite matrices in different dimensions by exploiting a special "separable" structure in the constraints. Our theorem recovers two existing equivalence results of SDRs defined in different settings and has the potential to find other applications due to its generality.

math.OC↗

arXiv2020

Efficient numerical methods for computing the stationary states of phase field crystal models

Finding the stationary states of a free energy functional is an important problem in phase field crystal (PFC) models. Many efforts have been devoted for designing numerical schemes with energy dissipation and mass conservation properties. However, most existing approaches are time-consuming due to the requirement of small effective step sizes. In this paper, we discretize the energy functional and propose efficient numerical algorithms for solving the constrained non-convex minimization problem. A class of gradient based approaches, which is the so-called adaptive accelerated Bregman proximal gradient (AA-BPG) methods, is proposed and the convergence property is established without the global Lipschitz constant requirements. A practical Newton method is also designed to further accelerate the local convergence with convergence guarantee. One key feature of our algorithms is that the energy dissipation and mass conservation properties hold during the iteration process. Moreover, we develop a hybrid acceleration framework to accelerate the AA-BPG methods and most of existing approaches through coupling with the practical Newton method. Extensive numerical experiments, including two three dimensional periodic crystals in Landau-Brazovskii (LB) model and a two dimensional quasicrystal in Lifshitz-Petrich (LP) model, demonstrate that our approaches have adaptive step sizes which lead to a significant acceleration over many existing methods when computing complex structures.

math.NA↗

arXiv2020

Interpolation between Residual and Non-Residual Networks

Although ordinary differential equations (ODEs) provide insights for designing network architectures, its relationship with the non-residual convolutional neural networks (CNNs) is still unclear. In this paper, we present a novel ODE model by adding a damping term. It can be shown that the proposed model can recover both a ResNet and a CNN by adjusting an interpolation coefficient. Therefore, the damped ODE model provides a unified framework for the interpretation of residual and non-residual networks. The Lyapunov analysis reveals better stability of the proposed model, and thus yields robustness improvement of the learned networks. Experiments on a number of image classification benchmarks show that the proposed model substantially improves the accuracy of ResNet and ResNeXt over the perturbed inputs from both stochastic noise and adversarial attack methods. Moreover, the loss landscape analysis demonstrates the improved robustness of our method along the attack direction.

stat.ML↗

arXiv2020

Exploring Frequency Domain Interpretation of Convolutional Neural Networks

Many existing interpretation methods of convolutional neural networks (CNNs) mainly analyze in spatial domain, yet model interpretability in frequency domain has been rarely studied. To the best of our knowledge, there is no study on the interpretation of modern CNNs from the perspective of the frequency proportion of filters. In this work, we analyze the frequency properties of filters in the first layer as it is the entrance of information and relatively more convenient for analysis. By controlling the proportion of different frequency filters in the training stage, the network classification accuracy and model robustness is evaluated and our results reveal that it has a great impact on the robustness to common corruptions. Moreover, a learnable modulation of frequency proportion with perturbation in power spectrum is proposed from the perspective of frequency domain. Experiments on CIFAR-10-C show 10.97% average robustness gains for ResNet-18 with negligible natural accuracy degradation.

cs.CV↗

arXiv2020

Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation

Existing domain adaptation methods aim at learning features that can be generalized among domains. These methods commonly require to update source classifier to adapt to the target domain and do not properly handle the trade off between the source domain and the target domain. In this work, instead of training a classifier to adapt to the target domain, we use a separable component called data calibrator to help the fixed source classifier recover discrimination power in the target domain, while preserving the source domain's performance. When the difference between two domains is small, the source classifier's representation is sufficient to perform well in the target domain and outperforms GAN-based methods in digits. Otherwise, the proposed method can leverage synthetic images generated by GANs to boost performance and achieve state-of-the-art performance in digits datasets and driving scene semantic segmentation. Our method empirically reveals that certain intriguing hints, which can be mitigated by adversarial attack to domain discriminators, are one of the sources for performance degradation under the domain shift.

cs.CV↗

arXiv2019

An efficient method for computing stationary states of phase field crystal models

Computing stationary states is an important topic for phase field crystal (PFC) models. Great efforts have been made for energy dissipation of the numerical schemes when using gradient flows. However, it is always time-consuming due to the requirement of small effective time steps. In this paper, we propose an adaptive accelerated proximal gradient method for finding the stationary states of PFC models. The energy dissipation is guaranteed and the convergence property is established for the discretized energy functional. Moreover, the connections between generalized proximal operator with classical (semi-)implicit and explicit schemes for gradient flow are given. Extensive numerical experiments, including two three dimensional periodic crystals in Landau-Brazovskii (LB) model and a two dimensional quasicrystal in Lifshitz-Petrich (LP) model, demonstrate that our approach has adaptive time steps which lead to significant acceleration over semi-implicit methods for computing complex structures. Furthermore, our result reveals a deep physical mechanism of the simple LB model via which the sigma phase is first discovered.

math.NA↗

arXiv2019

Wasserstein-Fisher-Rao Document Distance

As a fundamental problem of natural language processing, it is important to measure the distance between different documents. Among the existing methods, the Word Mover's Distance (WMD) has shown remarkable success in document semantic matching for its clear physical insight as a parameter-free model. However, WMD is essentially based on the classical Wasserstein metric, thus it often fails to robustly represent the semantic similarity between texts of different lengths. In this paper, we apply the newly developed Wasserstein-Fisher-Rao (WFR) metric from unbalanced optimal transport theory to measure the distance between different documents. The proposed WFR document distance maintains the great interpretability and simplicity as WMD. We demonstrate that the WFR document distance has significant advantages when comparing the texts of different lengths. In addition, an accelerated Sinkhorn based algorithm with GPU implementation has been developed for the fast computation of WFR distances. The KNN classification results on eight datasets have shown its clear improvement over WMD.

cs.LG↗

arXiv2019

Brain-inspired reverse adversarial examples

A human does not have to see all elephants to recognize an animal as an elephant. On contrast, current state-of-the-art deep learning approaches heavily depend on the variety of training samples and the capacity of the network. In practice, the size of network is always limited and it is impossible to access all the data samples. Under this circumstance, deep learning models are extremely fragile to human-imperceivable adversarial examples, which impose threats to all safety critical systems. Inspired by the association and attention mechanisms of the human brain, we propose reverse adversarial examples method that can greatly improve models' robustness on unseen data. Experiments show that our reverse adversarial method can improve accuracy on average 19.02% on ResNet18, MobileNet, and VGG16 on unseen data transformation. Besides, the proposed method is also applicable to compressed models and shows potential to compensate the robustness drop brought by model quantization - an absolute 30.78% accuracy improvement.

cs.LG↗

arXiv2019

SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models

Remarkable achievements have been attained by deep neural networks in various applications. However, the increasing depth and width of such models also lead to explosive growth in both storage and computation, which has restricted the deployment of deep neural networks on resource-limited edge devices. To address this problem, we propose the so-called SCAN framework for networks training and inference, which is orthogonal and complementary to existing acceleration and compression methods. The proposed SCAN firstly divides neural networks into multiple sections according to their depth and constructs shallow classifiers upon the intermediate features of different sections. Moreover, attention modules and knowledge distillation are utilized to enhance the accuracy of shallow classifiers. Based on this architecture, we further propose a threshold controlled scalable inference mechanism to approach human-like sample-specific inference. Experimental results show that SCAN can be easily equipped on various neural networks without any adjustment on hyper-parameters or neural networks architectures, yielding significant performance gain on CIFAR100 and ImageNet. Codes will be released on github soon.

cs.LG↗

arXiv2019

Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation

Convolutional neural networks have been widely deployed in various application scenarios. In order to extend the applications' boundaries to some accuracy-crucial domains, researchers have been investigating approaches to boost accuracy through either deeper or wider network structures, which brings with them the exponential increment of the computational and storage cost, delaying the responding time. In this paper, we propose a general training framework named self distillation, which notably enhances the performance (accuracy) of convolutional neural networks through shrinking the size of the network rather than aggrandizing it. Different from traditional knowledge distillation - a knowledge transformation methodology among networks, which forces student neural networks to approximate the softmax layer outputs of pre-trained teacher neural networks, the proposed self distillation framework distills knowledge within network itself. The networks are firstly divided into several sections. Then the knowledge in the deeper portion of the networks is squeezed into the shallow ones. Experiments further prove the generalization of the proposed self distillation framework: enhancement of accuracy at average level is 2.65%, varying from 0.61% in ResNeXt as minimum to 4.07% in VGG19 as maximum. In addition, it can also provide flexibility of depth-wise scalable inference on resource-limited edge devices.Our codes will be released on github soon.

cs.LG↗

arXiv2018

Whole Brain Susceptibility Mapping Using Harmonic Incompatibility Removal

Quantitative susceptibility mapping (QSM) aims to visualize the three dimensional susceptibility distribution by solving the field-to-source inverse problem using the phase data in magnetic resonance signal. However, the inverse problem is ill-posed since the Fourier transform of integral kernel has zeroes in the frequency domain. Although numerous regularization based models have been proposed to overcome this problem, the incompatibility in the field data has not received enough attention, which leads to deterioration of the recovery. In this paper, we show that the data acquisition process of QSM inherently generates a harmonic incompatibility in the measured local field. Based on such discovery, we propose a novel regularization based susceptibility reconstruction model with an additional sparsity based regularization term on the harmonic incompatibility. Numerical experiments show that the proposed method achieves better performance than the existing approaches.

math.NA↗

arXiv2018

PET-MRI Joint Reconstruction by Joint Sparsity Based Tight Frame Regularization

Recent technical advances lead to the coupling of PET and MRI scanners, enabling to acquire functional and anatomical data simultaneously. In this paper, we propose a tight frame based PET-MRI joint reconstruction model via the joint sparsity of tight frame coefficients. In addition, a non-convex balanced approach is adopted to take the different regularities of PET and MRI images into account. To solve the nonconvex and nonsmooth model, a proximal alternating minimization algorithm is proposed, and the global convergence is present based on Kurdyka-Lojasiewicz property. Finally, the numerical experiments show that the our proposed models achieve better performance over the existing PET-MRI joint reconstruction models.

math.NA↗

arXiv2017

Coherence retrieval using trace regularization

The mutual intensity and its equivalent phase-space representations quantify an optical field's state of coherence and are important tools in the study of light propagation and dynamics, but they can only be estimated indirectly from measurements through a process called coherence retrieval, otherwise known as phase-space tomography. As practical considerations often rule out the availability of a complete set of measurements, coherence retrieval is usually a challenging high-dimensional ill-posed inverse problem. In this paper, we propose a trace-regularized optimization model for coherence retrieval and a provably-convergent adaptive accelerated proximal gradient algorithm for solving the resulting problem. Applying our model and algorithm to both simulated and experimental data, we demonstrate an improvement in reconstruction quality over previous models as well as an increase in convergence speed compared to existing first-order methods.

physics.optics↗