arXiv subjects

Yuhao Wang

Publications and source records attributed to Yuhao Wang.

At least 235 records · Page 13Linked to original sources

arXiv2020

Joint Intensity-Gradient Guided Generative Modeling for Colorization

This paper proposes an iterative generative model for solving the automatic colorization problem. Although previous researches have shown the capability to generate plausible color, the edge color overflow and the requirement of the reference images still exist. The starting point of the unsupervised learning in this study is the observation that the gradient map possesses latent information of the image. Therefore, the inference process of the generative modeling is conducted in joint intensity-gradient domain. Specifically, a set of intensity-gradient formed high-dimensional tensors, as the network input, are used to train a powerful noise conditional score network at the training phase. Furthermore, the joint intensity-gradient constraint in data-fidelity term is proposed to limit the degree of freedom within generative model at the iterative colorization stage, and it is conducive to edge-preserving. Extensive experiments demonstrated that the system outperformed state-of-the-art methods whether in quantitative comparisons or user study.

cs.CV↗

arXiv2020

Amortized Variational Deep Q Network

Efficient exploration is one of the most important issues in deep reinforcement learning. To address this issue, recent methods consider the value function parameters as random variables, and resort variational inference to approximate the posterior of the parameters. In this paper, we propose an amortized variational inference framework to approximate the posterior distribution of the action value function in Deep Q Network. We establish the equivalence between the loss of the new model and the amortized variational inference loss. We realize the balance of exploration and exploitation by assuming the posterior as Cauchy and Gaussian, respectively in a two-stage training process. We show that the amortized framework can results in significant less learning parameters than existing state-of-the-art method. Experimental results on classical control tasks in OpenAI Gym and chain Markov Decision Process tasks show that the proposed method performs significantly better than state-of-art methods and requires much less training time.

cs.LG↗

arXiv2020

Estimation of the $l_2$-norm and testing in sparse linear regression with unknown variance

We consider the related problems of estimating the $l_2$-norm and the squared $l_2$-norm in sparse linear regression with unknown variance, as well as the problem of testing the hypothesis that the regression parameter is null under sparse alternatives with $l_2$ separation. We establish the minimax optimal rates of estimation (respectively, testing) in these three problems.

math.ST↗

arXiv2020

Joint Inference of Multiple Graphs from Matrix Polynomials

Inferring graph structure from observations on the nodes is an important and popular network science task. Departing from the more common inference of a single graph and motivated by social and biological networks, we study the problem of jointly inferring multiple graphs from the observation of signals at their nodes (graph signals), which are assumed to be stationary in the sought graphs. From a mathematical point of view, graph stationarity implies that the mapping between the covariance of the signals and the sparse matrix representing the underlying graph is given by a matrix polynomial. A prominent example is that of Markov random fields, where the inverse of the covariance yields the sparse matrix of interest. From a modeling perspective, stationary graph signals can be used to model linear network processes evolving on a set of (not necessarily known) networks. Leveraging that matrix polynomials commute, a convex optimization method along with sufficient conditions that guarantee the recovery of the true graphs are provided when perfect covariance information is available. Particularly important from an empirical viewpoint, we provide high-probability bounds on the recovery error as a function of the number of signals observed and other key problem parameters. Numerical experiments using synthetic and real-world data demonstrate the effectiveness of the proposed method with perfect covariance information as well as its robustness in the noisy regime.

stat.ML↗

arXiv2020

High-Dimensional Joint Estimation of Multiple Directed Gaussian Graphical Models

We consider the problem of jointly estimating multiple related directed acyclic graph (DAG) models based on high-dimensional data from each graph. This problem is motivated by the task of learning gene regulatory networks based on gene expression data from different tissues, developmental stages or disease states. We prove that under certain regularity conditions, the proposed $\ell_0$-penalized maximum likelihood estimator converges in Frobenius norm to the adjacency matrices consistent with the data-generating distributions and has the correct sparsity. In particular, we show that this joint estimation procedure leads to a faster convergence rate than estimating each DAG model separately. As a corollary, we also obtain high-dimensional consistency results for causal inference from a mix of observational and interventional data. For practical purposes, we propose \emph{jointGES} consisting of Greedy Equivalence Search (GES) to estimate the union of all DAG models followed by variable selection using lasso to obtain the different DAGs, and we analyze its consistency guarantees. The proposed method is illustrated through an analysis of simulated data as well as epithelial ovarian cancer gene expression data.

math.ST↗

arXiv2020

Permutation-Based Causal Structure Learning with Unknown Intervention Targets

We consider the problem of estimating causal DAG models from a mix of observational and interventional data, when the intervention targets are partially or completely unknown. This problem is highly relevant for example in genomics, since gene knockout technologies are known to have off-target effects. We characterize the interventional Markov equivalence class of DAGs that can be identified from interventional data with unknown intervention targets. In addition, we propose a provably consistent algorithm for learning the interventional Markov equivalence class from such data. The proposed algorithm greedily searches over the space of permutations to minimize a novel score function. The algorithm is nonparametric, which is particularly important for applications to genomics, where the relationships between variables are often non-linear and the distribution non-Gaussian. We demonstrate the performance of our algorithm on synthetic and biological datasets. Links to an implementation of our algorithm and to a reproducible code base for our experiments can be found at https://uhlerlab.github.io/causaldag/utigsp.

stat.ME↗

arXiv2020

Accelerated design of Fe-based soft magnetic materials using machine learning and stochastic optimization

Machine learning was utilized to efficiently boost the development of soft magnetic materials. The design process includes building a database composed of published experimental results, applying machine learning methods on the database, identifying the trends of magnetic properties in soft magnetic materials, and accelerating the design of next-generation soft magnetic nanocrystalline materials through the use of numerical optimization. Machine learning regression models were trained to predict magnetic saturation ($B_S$), coercivity ($H_C$) and magnetostriction ($λ$), with a stochastic optimization framework being used to further optimize the corresponding magnetic properties. To verify the feasibility of the machine learning model, several optimized soft magnetic materials -- specified in terms of compositions and thermomechanical treatments -- have been predicted and then prepared and tested, showing good agreement between predictions and experiments, proving the reliability of the designed model. Two rounds of optimization-testing iterations were conducted to search for better properties.

cond-mat.mtrl-sci↗

arXiv2020

Learning in the Frequency Domain

Deep neural networks have achieved remarkable success in computer vision tasks. Existing neural networks mainly operate in the spatial domain with fixed input sizes. For practical applications, images are usually large and have to be downsampled to the predetermined input size of neural networks. Even though the downsampling operations reduce computation and the required communication bandwidth, it removes both redundant and salient information obliviously, which results in accuracy degradation. Inspired by digital signal processing theories, we analyze the spectral bias from the frequency perspective and propose a learning-based frequency selection method to identify the trivial frequency components which can be removed without accuracy loss. The proposed method of learning in the frequency domain leverages identical structures of the well-known neural networks, such as ResNet-50, MobileNetV2, and Mask R-CNN, while accepting the frequency-domain information as the input. Experiment results show that learning in the frequency domain with static channel selection can achieve higher accuracy than the conventional spatial downsampling approach and meanwhile further reduce the input data size. Specifically for ImageNet classification with the same input size, the proposed method achieves 1.41% and 0.66% top-1 accuracy improvements on ResNet-50 and MobileNetV2, respectively. Even with half input size, the proposed method still improves the top-1 accuracy on ResNet-50 by 1%. In addition, we observe a 0.8% average precision improvement on Mask R-CNN for instance segmentation on the COCO dataset.

cs.CV↗

arXiv2020

Learning High-dimensional Gaussian Graphical Models under Total Positivity without Adjustment of Tuning Parameters

We consider the problem of estimating an undirected Gaussian graphical model when the underlying distribution is multivariate totally positive of order 2 (MTP2), a strong form of positive dependence. Such distributions are relevant for example for portfolio selection, since assets are usually positively dependent. A large body of methods have been proposed for learning undirected graphical models without the MTP2 constraint. A major limitation of these methods is that their structure recovery guarantees in the high-dimensional setting usually require a particular choice of a tuning parameter, which is unknown a priori in real world applications. We here propose a new method to estimate the underlying undirected graphical model under MTP2 and show that it is provably consistent in structure recovery without adjusting the tuning parameters. This is achieved by a constraint-based estimator that infers the structure of the underlying graphical model by testing the signs of the empirical partial correlation coefficients. We evaluate the performance of our estimator in simulations and on financial data.

stat.ME↗

arXiv2020

Causal Discovery from Incomplete Data: A Deep Learning Approach

As systems are getting more autonomous with the development of artificial intelligence, it is important to discover the causal knowledge from observational sensory inputs. By encoding a series of cause-effect relations between events, causal networks can facilitate the prediction of effects from a given action and analyze their underlying data generation mechanism. However, missing data are ubiquitous in practical scenarios. Directly performing existing casual discovery algorithms on partially observed data may lead to the incorrect inference. To alleviate this issue, we proposed a deep learning framework, dubbed Imputated Causal Learning (ICL), to perform iterative missing data imputation and causal structure discovery. Through extensive simulations on both synthetic and real data, we show that ICL can outperform state-of-the-art methods under different missing data mechanisms.

cs.LG↗

arXiv2019

DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks

The rapidly growing parameter volume of deep neural networks (DNNs) hinders the artificial intelligence applications on resource constrained devices, such as mobile and wearable devices. Neural network pruning, as one of the mainstream model compression techniques, is under extensive study to reduce the number of parameters and computations. In contrast to irregular pruning that incurs high index storage and decoding overhead, structured pruning techniques have been proposed as the promising solutions. However, prior studies on structured pruning tackle the problem mainly from the perspective of facilitating hardware implementation, without analyzing the characteristics of sparse neural networks. The neglect on the study of sparse neural networks causes inefficient trade-off between regularity and pruning ratio. Consequently, the potential of structurally pruning neural networks is not sufficiently mined. In this work, we examine the structural characteristics of the irregularly pruned weight matrices, such as the diverse redundancy of different rows, the sensitivity of different rows to pruning, and the positional characteristics of retained weights. By leveraging the gained insights as a guidance, we first propose the novel block-max weight masking (BMWM) method, which can effectively retain the salient weights while imposing high regularity to the weight matrix. As a further optimization, we propose a density-adaptive regular-block (DARB) pruning that outperforms prior structured pruning work with high pruning ratio and decoding efficiency. Our experimental results show that DARB can achieve 13$\times$ to 25$\times$ pruning ratio, which are 2.8$\times$ to 4.3$\times$ improvements than the state-of-the-art counterparts on multiple neural network models and tasks. Moreover, DARB can achieve 14.3$\times$ decoding efficiency than block pruning with higher pruning ratio.

cs.LG↗

arXiv2019

FFDNet-Based Channel Estimation for Massive MIMO Visible Light Communication Systems

Channel estimation is of crucial importance in massive multiple-input multiple-output (m-MIMO) visible light communication (VLC) systems. In order to tackle this problem, a fast and flexible denoising convolutional neural network (FFDNet)-based channel estimation scheme for m-MIMO VLC systems was proposed. The channel matrix of the m-MIMO VLC channel is identified as a two-dimensional natural image since the channel has the characteristic of sparsity. A deep learning-enabled image denoising network FFDNet is exploited to learn from a large number of training data and to estimate the m-MIMO VLC channel. Simulation results demonstrate that our proposed channel estimation based on the FFDNet significantly outperforms the benchmark scheme based on minimum mean square error.

eess.SP↗

arXiv2019

Subcarrier Assignment Schemes Based on Q-Learning in Wideband Cognitive Radio Networks

Subcarrier assignment is of crucial importance in wideband cognitive radio (CR) networks. In order to tackle the challenge that the traditional optimization-based methods are inappropriate in the dynamic spectrum access environment, an independent Q-learning-based scheme is proposed for the case that the secondary users (SUs) cannot exchange information while a collaborative Q-learning-based scheme is proposed for the case that information can be exchange among SUs. Simulation results show that the performance achieved with the proposed collaborative Q-learning-based assignment is better than that obtained with the proposed independent Q-learning-based assignment at the cost of the computation cost.

eess.SP↗

arXiv2019

Computation Efficiency Maximization in OFDMA-Based Mobile Edge Computing Networks

Computation-efficient resource allocation strategies are of crucial importance in mobile edge computing networks. However, few works have focused on this issue. In this letter, weighted sum computation efficiency (CE) maximization problems are formulated in a mobile edge computing (MEC) network with orthogonal frequency division multiple access (OFDMA). Both partial offloading mode and binary offloading mode are considered. The closed-form expressions for the optimal subchannel and power allocation schemes are derived. In order to address the intractable non-convex weighted sum-of ratio problems, an efficiently iterative algorithm is proposed. Simulation results demonstrate that the CE achieved by our proposed resource allocation scheme is better than that obtained by the benchmark schemes.

eess.SP↗

arXiv2019

Learning Priors in High-frequency Domain for Inverse Imaging Reconstruction

Ill-posed inverse problems in imaging remain an active research topic in several decades, with new approaches constantly emerging. Recognizing that the popular dictionary learning and convolutional sparse coding are both essentially modeling the high-frequency component of an image, which convey most of the semantic information such as texture details, in this work we propose a novel multi-profile high-frequency transform-guided denoising autoencoder as prior (HF-DAEP). To achieve this goal, we first extract a set of multi-profile high-frequency components via a specific transformation and add the artificial Gaussian noise to these high-frequency components as training samples. Then, as the high-frequency prior information is learned, we incorporate it into classical iterative reconstruction process by proximal gradient descent technique. Preliminary results on highly under-sampled magnetic resonance imaging and sparse-view computed tomography reconstruction demonstrate that the proposed method can efficiently reconstruct feature details and present advantages over state-of-the-arts.

eess.IV↗

arXiv2019

Performance Analysis on Visible Light Communications With Multi-Eavesdroppers and Practical Amplitude Constraint

In this paper the secure performance for the visible light communication (VLC) system with multiple eavesdroppers is studied. By considering the practical amplitude constraint instead of an average power constraint in the VLC system, the closed-form expressions for the upper and the lower bounds of the secrecy outage probability and the average secrecy capacity are derived. Since the locations for both legitimate receiver and eavesdroppers are unknown as well as random, the stochastic geometry method is introduced for problem formulation. Moreover, accurate expressions with a low computational complexity are obtained with the rigorous derivation. Simulation results verify the correctness of our theoretical analysis.

eess.SP↗

arXiv2019

Mobile Edge Computing in Unmanned Aerial Vehicle Networks

Unmanned aerial vehicle (UAV)-enabled communication networks are promising in the fifth and beyond wireless communication systems. In this paper, we shed light on three UAV-enabled mobile edge computing (MEC) architectures. Those architectures have been receiving ever increasing research attention for improving computation performance and decreasing execution latency by integrating UAV into MEC networks. We present a comprehensive survey for the state-of-the-art research in this domain. Important implementation issues are clarified. Moreover, in order to provide an enlightening guidance for future research directions, key challenges and open issues are discussed.

eess.SP↗

arXiv2019

Anchored Causal Inference in the Presence of Measurement Error

We consider the problem of learning a causal graph in the presence of measurement error. This setting is for example common in genomics, where gene expression is corrupted through the measurement process. We develop a provably consistent procedure for estimating the causal structure in a linear Gaussian structural equation model from corrupted observations on its nodes, under a variety of measurement error models. We provide an estimator based on the method-of-moments, which can be used in conjunction with constraint-based causal structure discovery algorithms. We prove asymptotic consistency of the procedure and also discuss finite-sample considerations. We demonstrate our method's performance through simulations and on real data, where we recover the underlying gene regulatory network from zero-inflated single-cell RNA-seq data.

stat.ME↗