arXiv subjects

Yong Ren

Publications and source records attributed to Yong Ren.

At least 73 records · Page 4Linked to original sources

arXiv2020

Access Strategy in Super WiFi Network Powered by Solar Energy Harvesting: A POMDP Method

The recently announced Super Wi-Fi Network proposal in United States is aiming to enable Internet access in a nation-wide area. As traditional cable-connected power supply system becomes impractical or costly for a wide range wireless network, new infrastructure deployment for Super Wi-Fi is required. The fast developing Energy Harvesting (EH) techniques receive global attentions for their potential of solving the above power supply problem. It is a critical issue, from the user's perspective, how to make efficient network selection and access strategies. Unlike traditional wireless networks, the battery charge state and tendency in EH based networks have to be taken into account when making network selection and access, which has not been well investigated. In this paper, we propose a practical and efficient framework for multiple base stations access strategy in an EH powered Super Wi-Fi network. We consider the access strategy from the user's perspective, who exploits downlink transmission opportunities from one base station. To formulate the problem, we used Partially Observable Markov Decision Process (POMDP) to model users' observations on the base stations' battery situation and decisions on the base station selection and access. Simulation results show that our methods are efficacious and significantly outperform the traditional widely used CSMA method.

cs.IT↗

arXiv2020

Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks

Future wireless networks have a substantial potential in terms of supporting a broad range of complex compelling applications both in military and civilian fields, where the users are able to enjoy high-rate, low-latency, low-cost and reliable information services. Achieving this ambitious goal requires new radio techniques for adaptive learning and intelligent decision making because of the complex heterogeneous nature of the network structures and wireless services. Machine learning (ML) algorithms have great success in supporting big data analytics, efficient parameter estimation and interactive decision making. Hence, in this article, we review the thirty-year history of ML by elaborating on supervised learning, unsupervised learning, reinforcement learning and deep learning. Furthermore, we investigate their employment in the compelling applications of wireless networks, including heterogeneous networks (HetNets), cognitive radios (CR), Internet of things (IoT), machine to machine networks (M2M), and so on. This article aims for assisting the readers in clarifying the motivation and methodology of the various ML algorithms, so as to invoke them for hitherto unexplored services as well as scenarios of future wireless networks.

cs.NI↗

arXiv2019

Dynamics of a mean-reverting stochastic volatility model with regime switching

In this paper, we consider a mean-reverting stochastic volatility equation with regime switching, and present some sufficient conditions for the existence of global positive solution, asymptotic boundedness in pth moment, positive recurrence and existence of stationary distribution of this equation. Some results obtained in this paper extend the ones in literature. Example is given to verify the results by simulation.

math.PR↗

arXiv2019

Stochastic Nicholson's blowflies delay differential equation with regime switching

In this paper, we investigate the global existence of almost surely positive solution to a stochastic Nicholson's blowflies delay differential equation with regime switching, and give the estimation of the path. The results presented in this paper extend some corresponding results in Wang et al. Stochastic Nicholson's Blowflies Delayed Differential Equations, Appl. Math. Lett. 87 (2019) 20-26.

math.PR↗

arXiv2018

Smooth Neighbors on Teacher Graphs for Semi-supervised Learning

The recently proposed self-ensembling methods have achieved promising results in deep semi-supervised learning, which penalize inconsistent predictions of unlabeled data under different perturbations. However, they only consider adding perturbations to each single data point, while ignoring the connections between data samples. In this paper, we propose a novel method, called Smooth Neighbors on Teacher Graphs (SNTG). In SNTG, a graph is constructed based on the predictions of the teacher model, i.e., the implicit self-ensemble of models. Then the graph serves as a similarity measure with respect to which the representations of "similar" neighboring points are learned to be smooth on the low-dimensional manifold. We achieve state-of-the-art results on semi-supervised learning benchmarks. The error rates are 9.89%, 3.99% for CIFAR-10 with 4000 labels, SVHN with 500 labels, respectively. In particular, the improvements are significant when the labels are fewer. For the non-augmented MNIST with only 20 labels, the error rate is reduced from previous 4.81% to 1.36%. Our method also shows robustness to noisy labels.

cs.LG↗

arXiv2017

Real-Time Robot Localization, Vision, and Speech Recognition on Nvidia Jetson TX1

Robotics systems are complex, often consisted of basic services including SLAM for localization and mapping, Convolution Neural Networks for scene understanding, and Speech Recognition for user interaction, etc. Meanwhile, robots are mobile and usually have tight energy constraints, integrating these services onto an embedded platform with around 10 W of power consumption is critical to the proliferation of mobile robots. In this paper, we present a case study on integrating real-time localization, vision, and speech recognition services on a mobile SoC, Nvidia Jetson TX1, within about 10 W of power envelope. In addition, we explore whether offloading some of the services to cloud platform can lead to further energy efficiency while meeting the real-time requirements

cs.RO↗

arXiv2016

Kernel Bayesian Inference with Posterior Regularization

We propose a vector-valued regression problem whose solution is equivalent to the reproducing kernel Hilbert space (RKHS) embedding of the Bayesian posterior distribution. This equivalence provides a new understanding of kernel Bayesian inference. Moreover, the optimization problem induces a new regularization for the posterior embedding estimator, which is faster and has comparable performance to the squared regularization in kernel Bayes' rule. This regularization coincides with a former thresholding approach used in kernel POMDPs whose consistency remains to be established. Our theoretical work solves this open problem and provides consistency analysis in regression settings. Based on our optimizational formulation, we propose a flexible Bayesian posterior regularization framework which for the first time enables us to put regularization at the distribution level. We apply this method to nonparametric state-space filtering tasks with extremely nonlinear dynamics and show performance gains over all other baselines.

stat.ML↗

arXiv2016

Conditional Generative Moment-Matching Networks

Maximum mean discrepancy (MMD) has been successfully applied to learn deep generative models for characterizing a joint distribution of variables via kernel mean embedding. In this paper, we present conditional generative moment- matching networks (CGMMN), which learn a conditional distribution given some input variables based on a conditional maximum mean discrepancy (CMMD) criterion. The learning is performed by stochastic gradient descent with the gradient calculated by back-propagation. We evaluate CGMMN on a wide range of tasks, including predictive modeling, contextual generation, and Bayesian dark knowledge, which distills knowledge from a Bayesian model by learning a relatively small CGMMN student network. Our results demonstrate competitive performance in all the tasks.

cs.LG↗

arXiv2016

Spectral Learning for Supervised Topic Models

Supervised topic models simultaneously model the latent topic structure of large collections of documents and a response variable associated with each document. Existing inference methods are based on variational approximation or Monte Carlo sampling, which often suffers from the local minimum defect. Spectral methods have been applied to learn unsupervised topic models, such as latent Dirichlet allocation (LDA), with provable guarantees. This paper investigates the possibility of applying spectral methods to recover the parameters of supervised LDA (sLDA). We first present a two-stage spectral method, which recovers the parameters of LDA followed by a power update method to recover the regression model parameters. Then, we further present a single-phase spectral algorithm to jointly recover the topic distribution matrix as well as the regression weights. Our spectral algorithms are provably correct and computationally efficient. We prove a sample complexity bound for each algorithm and subsequently derive a sufficient condition for the identifiability of sLDA. Thorough experiments on synthetic and real-world datasets verify the theory and demonstrate the practical effectiveness of the spectral algorithms. In fact, our results on a large-scale review rating dataset demonstrate that our single-phase spectral algorithm alone gets comparable or even better performance than state-of-the-art methods, while previous work on spectral methods has rarely reported such promising performance.

cs.LG↗

arXiv2015

Electromagnetic, stress and thermal analysis of the Superconducting Magnet

Within the framework of the National Special Project for Magnetic Confined Nuclear Fusion Energy of China, the design of a superconducting magnet project as a test facility of the Nb3Sn coil or NbTi coil for the Chinese Fusion Engineering Test Reactor (CFETR) has been carried out not only to estimate the relevant conductor performance but also to implement a background magnetic field for CFETR CS insert and toroidal field (TF) insert coils. The superconducting magnet is composed of two parts: the inner part with Nb3Sn cable-in-conduit conductor (CICC) and the outer part with NbTi CICC. Both parts are connected in series and powered by a single DC power supply. The superconducting magnet can be cooled with supercritical helium at inlet temperature of 4.5 K. The total inductance and stored energy of the superconducting magnet are about 0.278 H and 436.6 MJ at an operating current of 56 kA respectively. An active quench protection circuit was adopted to transfer the stored magnetic energy of the superconducting magnet during a dump operation. In this paper, the design of the superconducting magnet and the main analysis results of the electromagnetic, structural and thermal-hydraulic performance are described.

physics.acc-ph↗

arXiv2015

Reflected backward stochastic differential equations with jumps in time-dependent random convex domains

In this paper, we study a class of multi-dimensional reflected backward stochastic differential equations when the noise is driven by a Brownian motion and an independent Poisson point process, and when the solution is forced to stay in a time-dependent adapted and continuous convex domain ${\cal{D}}=\{D_t, t\in[0,T]\}$. We prove the existence an uniqueness of the solution, and we also show that the solution of such equations may be approximated by backward stochastic differential equations with jumps reflected in appropriately defined discretizations of $\cal{D}$, via a penalization method.

math.PR↗

arXiv2015

Mean-field backward stochastic differential equations on Markov chains

In this paper, we deal with a class of mean-field backward stochastic differential equations (BSDEs) related to finite state, continuous time Markov chains. We obtain the existence and uniqueness theorem and a comparison theorem for solutions of one-dimensional mean-field BSDEs under Lipschitz condition.

math.PR↗

arXiv2014

Continuous dependence property of BSDE with constraints

In this paper, we study continuous properties of adapted solutions for backward stochastic differential equations with constraints (CBSDEs in short). Comparing with many existing literatures about this topic, our case is very general in the sense that constraints are formulated by general non-negative real functions. In general case, we proved a continuous property from below and a lower semi-continuous property of the minimal super-solution of CBSDE in its effective domain. Furthermore, in the special convex case, we obtained a continuous property with the help of convex analysis.

math.PR↗

arXiv2014

Non-smooth analysis method in optimal investment- a BSDE approach

In this paper, our aim is to investigate necessary conditions for optimal investment. We model the wealth process by Backward differential stochastic equations (shortly for BSDE) with or without constraints on wealth and portfolio process. The constraints can be very general thanks the non-smooth analysis method we adopted.

math.PR↗

arXiv2013

Mean-field backward stochastic differential equations with subdifferrential operator and its applications

In this paper, we deal with a class of mean-field backward stochastic differential equations with subdifferrential operator corresponding to a lower semi-continuous convex function. By means of Yosida approximation, the existence and uniqueness of the solution is established. As an application, we give a probability interpretation for the viscosity solutions of a class of nonlocal parabolic variational inequalities.

math.PR↗

arXiv2013

Multivalued backward doubly stochastic differential equations with time delayed coefficients

In this paper, we deal with a class of multivalued backward doubly stochastic differential equations with time delayed coefficients. Based on a slight extension of the existence and uniqueness of solutions for backward doubly stochastic differential equations with time delayed coefficients, we establish the existence and uniqueness of solutions for these equations by means of Yosida approximation.

math.PR↗

arXiv2011

Renewal-Theoretical Dynamic Spectrum Access in Cognitive Radio Networks with Unknown Primary Behavior

Dynamic spectrum access in cognitive radio networks can greatly improve the spectrum utilization efficiency. Nevertheless, interference may be introduced to the Primary User (PU) when the Secondary Users (SUs) dynamically utilize the PU's licensed channels. If the SUs can be synchronous with the PU's time slots, the interference is mainly due to their imperfect spectrum sensing of the primary channel. However, if the SUs have no knowledge about the PU's exact communication mechanism, additional interference may occur. In this paper, we propose a dynamic spectrum access protocol for the SUs confronting with unknown primary behavior and study the interference caused by their dynamic access. Through analyzing the SUs' dynamic behavior in the primary channel which is modeled as an ON-OFF process, we prove that the SUs' communication behavior is a renewal process. Based on the Renewal Theory, we quantify the interference caused by the SUs and derive the corresponding close-form expressions. With the interference analysis, we study how to optimize the SUs' performance under the constraints of the PU's communication quality of service (QoS) and the secondary network's stability. Finally, simulation results are shown to verify the effectiveness of our analysis.

cs.NI↗

arXiv2011

Multivalued stochastic Dirichlet-Neumann problems and generalized backward doubly stochastic differential equations

In this paper, a class of generalized backward doubly stochastic differential equations whose coefficient contains the subdifferential operators of two convex functions (also called generalized backward doubly stochastic variational inequalities) are considered. By means of a penalization argument based on Yosida approximation, we establish the existence and uniqueness of the solution. As an application, this result is used to derive existence result of stochastic viscosity solution for a class of multivalued stochastic Dirichlet-Neumann problems.

math.PR↗