arXiv subjects

Lei Ying

Publications and source records attributed to Lei Ying.

At least 91 records · Page 5Linked to original sources

arXiv2019

Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning

We study two time-scale linear stochastic approximation algorithms, which can be used to model well-known reinforcement learning algorithms such as GTD, GTD2, and TDC. We present finite-time performance bounds for the case where the learning rate is fixed. The key idea in obtaining these bounds is to use a Lyapunov function motivated by singular perturbation theory for linear differential equations. We use the bound to design an adaptive learning rate scheme which significantly improves the convergence rate over the known optimal polynomial decay rule in our experiments, and can be used to potentially improve the performance of any other schedule where the learning rate is changed at pre-determined time instants.

cs.LG↗

arXiv2019

Nanophotonic Media for Artificial Neural Inference

We show optical waves passing through a nanophotonic medium can perform artificial neural computing. Complex information, is encoded in the wave front of an input light. The medium transforms the wave front to realize sophisticated computing tasks such as image recognition. At the output, the optical energy is concentrated to well-defined locations, which for example can be interpreted as the identity of the object in the image. These computing media can be as small as tens of wavelengths and offer ultra-high computing density. They exploit sub-wavelength scatterers to realize complex input output mapping beyond the capabilities of traditional nanophotonic devices.

physics.optics↗

arXiv2019

Finite-Time Error Bounds For Linear Stochastic Approximation and TD Learning

We consider the dynamics of a linear stochastic approximation algorithm driven by Markovian noise, and derive finite-time bounds on the moments of the error, i.e., deviation of the output of the algorithm from the equilibrium point of an associated ordinary differential equation (ODE). We obtain finite-time bounds on the mean-square error in the case of constant step-size algorithms by considering the drift of an appropriately chosen Lyapunov function. The Lyapunov function can be interpreted either in terms of Stein's method to obtain bounds on steady-state performance or in terms of Lyapunov stability theory for linear ODEs. We also provide a comprehensive treatment of the moments of the square of the 2-norm of the approximation error. Our analysis yields the following results: (i) for a given step-size, we show that the lower-order moments can be made small as a function of the step-size and can be upper-bounded by the moments of a Gaussian random variable; (ii) we show that the higher-order moments beyond a threshold may be infinite in steady-state; and (iii) we characterize the number of samples needed for the finite-time bounds to be of the same order as the steady-state bounds. As a by-product of our analysis, we also solve the open problem of obtaining finite-time bounds for the performance of temporal difference learning algorithms with linear function approximation and a constant step-size, without requiring a projection step or an i.i.d. noise assumption.

cs.LG↗

arXiv2018

Strong magneto-optical response enabled by quantum two level systems

The magneto-optical effect breaks time-reversal symmetry, a unique property that makes it indispensable in nonreciprocal optics and topological photonics. Unfortunately, all natural materials have a rather weak magneto-optical response in the optical frequency range, posing a significant challenge to the practical application of many emerging device concepts. Here we theoretically propose a composite material system that exhibits an intrinsic magneto-optical response orders of magnitude stronger than most magneto-optical materials used today. This is achieved by tailoring the resonant interplay between the quantum electrodynamics of electronic transitions in two-level systems and the classical electromagnetic response of local plasmon resonance.

physics.optics↗

arXiv2018

Empty-car routing in ridesharing systems

This paper considers a closed queueing network model of ridesharing systems such as Didi Chuxing, Lyft, and Uber. We focus on empty-car routing, a mechanism by which we control car flow in the network to optimize system-wide utility functions, e.g. the availability of empty cars when a passenger arrives. We establish both process-level and steady-state convergence of the queueing network to a fluid limit in a large market regime where demand for rides and supply of cars tend to infinity, and use this limit to study a fluid-based optimization problem. We prove that the optimal network utility obtained from the fluid-based optimization is an upper bound on the utility in the finite car system for any routing policy, both static and dynamic, under which the closed queueing network has a stationary distribution. This upper bound is achieved asymptotically under the fluid-based optimal routing policy. Simulation results with real-world data released by Didi Chuxing demonstrate the benefit of using the fluid-based optimal routing policy compared to various other policies.

math.PR↗

arXiv2018

A Simple Steady-State Analysis of Load Balancing Algorithms in the Sub-Halfin-Whitt Regime

This paper studies a class of load balancing algorithms for many-server ($N$ servers) systems assuming finite buffer with size $b-1$ (i.e. a server can have at most one job in service and $b-1$ jobs in queue). We focus on steady-state performance of load balancing algorithms in the heavy traffic regime such that the load of system is $λ= 1 - N^{-α}$ for $0<α<0.5,$ which we call sub-Halfin-Whitt regime ($α=0.5$ is the so-called the Halfin-Whitt regime). We establish a sufficient condition under which the probability that an incoming job is routed to an idle server is one asymptotically. The class of load balancing algorithms that satisfy the condition includes join-the-shortest-queue (JSQ), idle-one-first (I1F), join-the-idle-queue (JIQ), and power-of-$d$-choices (Po$d$) with $d=N^α\log N$. The proof of the main result is based on the framework of Stein's method. A key contribution is to use a simple generator approximation based on state space collapse.

math.PR↗

arXiv2017

Robustness of persistent currents in two-dimensional Dirac systems with disorders

We consider two-dimensional (2D) Dirac quantum ring systems formed by the infinite mass constraint. When an Aharonov-Bohm magnetic flux is present, e.g., through the center of the ring domain, persistent currents, i.e., permanent currents without dissipation, can arise. In real materials, impurities and defects are inevitable, raising the issue of robustness of the persistent currents. Using localized random potential to simulate the disorders, we investigate how the ensemble averaged current magnitude varies with the disorder density. For comparison, we study the nonrelativistic quantum counterpart by analyzing the solutions of the Schrödinger equation under the same geometrical and disorder settings. We find that, for the Dirac ring system, as the disorder density is systematically increased, the average current decreases slowly initially and then plateaus at a finite nonzero value, indicating remarkable robustness of the persistent currents. The physical mechanism responsible for the robustness is the emergence of a class of boundary states - whispering gallery modes. In contrast, in the Schrödinger ring system, such boundary states cannot form and the currents diminish rapidly to zero with increase in the disorder density. We develop a physical theory based on a quasi one-dimensional approximation to understand the striking contrast in the behaviors of the persistent currents in the Dirac and Schrödinger rings. Our 2D Dirac ring systems with disorders can be experimentally realized, e.g., on the surface of a topological insulator with natural or deliberately added impurities from the fabrication process.

cond-mat.mes-hall↗

arXiv2017

Electromagnetic Scattering Laws in Weyl Systems

Wavelength determines the length scale of the cross section when electromagnetic waves are scattered by an electrically small object. The cross section diverges for resonant scattering, and diminishes for non-resonant scattering, when wavelength approaches infinity. This scattering law explains the color of the sky as well as the strength of a mobile phone signal. We show that such wavelength scaling comes from free space's conical dispersion at zero frequency. Emerging Weyl systems, offering similar dispersion at non-zero frequencies, lead to new laws of electromagnetic scattering that allow cross sections to be decoupled from the wavelength limit. Diverging and diminishing cross sections can be realized at any target wavelength in a Weyl system, providing unprecedented ability to tailor the strength of wave-matter interactions for radio-frequency and optical applications.

physics.optics↗

arXiv2017

Power Control and Relay Selection in Full-Duplex Cognitive Relay Networks: Coherent versus Non-coherent Scenarios

This paper investigates power control and relay selection in Full Duplex Cognitive Relay Networks (FDCRNs), where the secondary-user (SU) relays can simultaneously receive and forward the signal from the SU source. We study both non-coherent and coherent scenarios. In the non-coherent case, the SU relay forwards the signal from the SU source without regulating the phase, while in the coherent scenario, the SU relay regulates the phase when forwarding the signal to minimize the interference at the primary-user (PU) receiver. We consider the problem of maximizing the transmission rate from the SU source to the SU destination subject to the interference constraint at the PU receiver and power constraints at both the SU source and SU relay. We develop low-complexity and high-performance joint power control and relay selection algorithms. The superior performance of the proposed algorithms are confirmed using extensive numerical evaluation. In particular, we demonstrate the significant gain of phase regulation at the SU relay (i.e., the gain of the coherent mechanism over the noncoherent mechanism).

cs.IT↗

arXiv2017

Power Allocation for Full-Duplex Relay Selection in Underlay Cognitive Radio Networks: Coherent versus Non-Coherent Scenarios

This paper investigates power control and relay selection in Full Duplex Cognitive Relay Networks (FDCRNs), where the secondary-user (SU) relays can simultaneously receive data from the SU source and forward them to the SU destination. We study both non-coherent and coherent scenarios. In the non-coherent case, the SU relay forwards the signal from the SU source without regulating the phase; while in the coherent scenario, the SU relay regulates the phase when forwarding the signal to minimize the interference at the primary-user (PU) receiver. We consider the problem of maximizing the transmission rate from the SU source to the SU destination subject to the interference constraint at the PU receiver and power constraints at both the SU source and SU relay. We then develop a mathematical model to analyze the data rate performance of the FDCRN considering the self-interference effects at the FD relay. We develop low-complexity and high-performance joint power control and relay selection algorithms. Extensive numerical results are presented to illustrate the impacts of power level parameters and the self-interference cancellation quality on the rate performance. Moreover, we demonstrate the significant gain of phase regulation at the SU relay.

cs.IT↗

arXiv2016

Catch'Em All: Locating Multiple Diffusion Sources in Networks with Partial Observations

This paper studies the problem of locating multiple diffusion sources in networks with partial observations. We propose a new source localization algorithm, named Optimal-Jordan-Cover (OJC). The algorithm first extracts a subgraph using a candidate selection algorithm that selects source candidates based on the number of observed infected nodes in their neighborhoods. Then, in the extracted subgraph, OJC finds a set of nodes that "cover" all observed infected nodes with the minimum radius. The set of nodes is called the Jordan cover, and is regarded as the set of diffusion sources. Considering the heterogeneous susceptible-infected-recovered (SIR) diffusion in the Erdos-Renyi (ER) random graph, we prove that OJC can locate all sources with probability one asymptotically with partial observations. OJC is a polynomial-time algorithm in terms of network size. However, the computational complexity increases exponentially in $m,$ the number of sources. We further propose a low-complexity heuristic based on the K-Means for approximating the Jordan cover, named Approximate-Jordan-Cover (AJC). Simulations on random graphs and real networks demonstrate that both AJC and OJC significantly outperform other heuristic algorithms.

cs.SI↗

arXiv2016

On the Rate of Convergence of the Power-of-Two-Choices to its Mean-Field Limit

This paper studies the rate of convergence of the power-of-two-choices, a celebrated randomized load balancing algorithm for many-server queueing systems, to its mean field limit. The convergence to the mean-field limit has been proved in the literature, but the rate of convergence remained to be an open problem. This paper establishes that the sequence of stationary distributions, indexed by $M,$ the number of servers in the system, converges in mean-square to its mean-field limit with rate $O\left(\frac{(\log M)^3 (\log\log M)^2}{M}\right).$

cs.NI↗

arXiv2016

The Value of Privacy: Strategic Data Subjects, Incentive Mechanisms and Fundamental Limits

We study the value of data privacy in a game-theoretic model of trading private data, where a data collector purchases private data from strategic data subjects (individuals) through an incentive mechanism. The private data of each individual represents her knowledge about an underlying state, which is the information that the data collector desires to learn. Different from most of the existing work on privacy-aware surveys, our model does not assume the data collector to be trustworthy. Then, an individual takes full control of its own data privacy and reports only a privacy-preserving version of her data. In this paper, the value of $ε$ units of privacy is measured by the minimum payment of all nonnegative payment mechanisms, under which an individual's best response at a Nash equilibrium is to report the data with a privacy level of $ε$. The higher $ε$ is, the less private the reported data is. We derive lower and upper bounds on the value of privacy which are asymptotically tight as the number of data subjects becomes large. Specifically, the lower bound assures that it is impossible to use less amount of payment to buy $ε$ units of privacy, and the upper bound is given by an achievable payment mechanism that we designed. Based on these fundamental limits, we further derive lower and upper bounds on the minimum total payment for the data collector to achieve a given learning accuracy target, and show that the total payment of the designed mechanism is at most one individual's payment away from the minimum.

cs.GT↗

arXiv2015

Distributed Rate and Power Control in Vehicular Networks

The focus of this paper is on the rate and power control algorithms in Dedicated Short Range Communication (DSRC) for vehicular networks. We first propose a utility maximization framework by leveraging the well-developed network congestion control, and formulate two subproblems, one on rate control with fixed transmit powers and the other on power control with fixed rates. Distributed rate control and power control algorithms are developed to solve these two subproblems, respectively, and are proved to be asymptotically optimal. Joint rate and power control can be done by using the two algorithms in an alternating fashion. The performance enhancement of our algorithms compared with a recent rate control algorithm, called EMBARC, is evaluated by using the network simulator ns2.

eess.SY↗

arXiv2015

Source Localization in Networks: Trees and Beyond

Information diffusion in networks can be used to model many real-world phenomena, including rumor spreading on online social networks, epidemics in human beings, and malware on the Internet. Informally speaking, the source localization problem is to identify a node in the network that provides the best explanation of the observed diffusion. Despite significant efforts and successes over last few years, theoretical guarantees of source localization algorithms were established only for tree networks due to the complexity of the problem. This paper presents a new source localization algorithm, called the Short-Fat Tree (SFT) algorithm. Loosely speaking, the algorithm selects the node such that the breadth-first search (BFS) tree from the node has the minimum depth but the maximum number of leaf nodes. Performance guarantees of SFT under the independent cascade (IC) model are established for both tree networks and the Erdos-Renyi (ER) random graph. On tree networks, SFT is the maximum a posterior (MAP) estimator. On the ER random graph, the following fundamental limits have been obtained: $(i)$ when the infection duration $<\frac{2}{3}t_u,$ SFT identifies the source with probability one asymptotically, where $t_u=\left\lceil\frac{\log n}{\log μ}\right\rceil+2$ and $μ$ is the average node degree, $(ii)$ when the infection duration $>t_u,$ the probability of identifying the source approaches zero asymptotically under any algorithm; and $(iii)$ when infection duration $<t_u,$ the BFS tree starting from the source is a fat tree. Numerical experiments on tree networks, the ER random graphs and real world networks with different evaluation metrics show that the SFT algorithm outperforms existing algorithms.

cs.SI↗

arXiv2015

On the Rate of Convergence of Mean-Field Models: Stein's Method Meets the Perturbation Theory

This paper studies the rate of convergence of a family of continuous-time Markov chains (CTMC) to a mean-field model. When the mean-field model is a finite-dimensional dynamical system with a unique equilibrium point, an analysis based on Stein's method and the perturbation theory shows that under some mild conditions, the stationary distributions of CTMCs converge (in the mean-square sense) to the equilibrium point of the mean-field model if the mean-field model is globally asymptotically stable and locally exponentially stable. In particular, the mean square difference between the $M$th CTMC in the steady state and the equilibrium point of the mean-field system is $O(1/M),$ where $M$ is the size of the $M$th CTMC. This approach based on Stein's method provides a new framework for studying the convergence of CTMCs to their mean-field limit by mainly looking into the stability of the mean-field model, which is a deterministic system and is often easier to analyze than the CTMCs. More importantly, this approach quantifies the rate of convergence, which reveals the approximation error of using mean-field models for approximating finite-size systems.

cs.PF↗

arXiv2015

On the Relation Between Identifiability, Differential Privacy and Mutual-Information Privacy

This paper investigates the relation between three different notions of privacy: identifiability, differential privacy and mutual-information privacy. Under a unified privacy-distortion framework, where the distortion is defined to be the Hamming distance of the input and output databases, we establish some fundamental connections between these three privacy notions. Given a distortion level $D$, define $ε_{\mathrm{i}}^*(D)$ to be the smallest (best) identifiability level, and $ε_{\mathrm{d}}^*(D)$ to be the smallest differential privacy level. We characterize $ε_{\mathrm{i}}^*(D)$ and $ε_{\mathrm{d}}^*(D)$, and prove that $ε_{\mathrm{i}}^*(D)-ε_X\leε_{\mathrm{d}}^*(D)\leε_{\mathrm{i}}^*(D)$ for $D$ in some range, where $ε_X$ is a constant depending on the distribution of the original database $X$, and diminishes to zero when the distribution of $X$ is uniform. Furthermore, we show that identifiability and mutual-information privacy are consistent in the sense that given distortion level $D$, the mechanism that optimizes the mutual-information privacy also minimizes the identifiability level.

cs.CR↗

arXiv2014

Locating Contagion Sources in Networks with Partial Timestamps

This paper studies the problem of identifying the contagion source when partial timestamps of a contagion process are available. We formulate the source localization problem as a ranking problem on graphs, where infected nodes are ranked according to their likelihood of being the source. Two ranking algorithms, cost-based ranking (CR) and tree-based ranking (TR), are proposed in this paper. Experimental evaluations with synthetic and real-world data show that our algorithms significantly improve the ranking accuracy compared with four existing algorithms.

cs.SI↗