arXiv subjects

Zhuo Sun

Publications and source records attributed to Zhuo Sun.

30 records · Page 2Linked to original sources

arXiv2023

Meta-learning Control Variates: Variance Reduction with Limited Data

Control variates can be a powerful tool to reduce the variance of Monte Carlo estimators, but constructing effective control variates can be challenging when the number of samples is small. In this paper, we show that when a large number of related integrals need to be computed, it is possible to leverage the similarity between these integration tasks to improve performance even when the number of samples per task is very small. Our approach, called meta learning CVs (Meta-CVs), can be used for up to hundreds or thousands of tasks. Our empirical assessment indicates that Meta-CVs can lead to significant variance reduction in such settings, and our theoretical analysis establishes general conditions under which Meta-CVs can be successfully trained.

stat.ME↗

arXiv2022

Age of Information of Multi-user Mobile Edge Computing Systems

In this paper, we analyze the average age of information (AoI) and the average peak AoI (PAoI) of a multiuser mobile edge computing (MEC) system where a base station (BS) generates and transmits computation-intensive packets to user equipments (UEs). In this MEC system, we focus on three computing schemes: (i) The local computing scheme where all computational tasks are computed by the local server at the UE, (ii) The edge computing scheme where all computational tasks are computed by the edge server at the BS, and (iii) The partial computing scheme where computational tasks are partially allocated at the edge server and the rest are computed by the local server. Considering exponentially distributed transmission time and computation time and adopting the first come first serve (FCFS) queuing policy, we derive closed-form expressions for the average AoI and average PAoI. To address the complexity of the average AoI expression, we derive simple upper and lower bounds on the average AoI, which allow us to explicitly examine the dependence of the optimal offloading decision on the MEC system parameters. Aided by simulation results, we verify our analysis and illustrate the impact of system parameters on the AoI performance.

cs.IT↗

arXiv2022

Equivalence between Time Series Predictability and Bayes Error Rate

Predictability is an emerging metric that quantifies the highest possible prediction accuracy for a given time series, being widely utilized in assessing known prediction algorithms and characterizing intrinsic regularities in human behaviors. Lately, increasing criticisms aim at the inaccuracy of the estimated predictability, caused by the original entropy-based method. In this brief report, we strictly prove that the time series predictability is equivalent to a seemingly unrelated metric called Bayes error rate that explores the lowest error rate unavoidable in classification. This proof bridges two independently developed fields, and thus each can immediately benefit from the other. For example, based on three theoretical models with known and controllable upper bounds of prediction accuracy, we show that the estimation based on Bayes error rate can largely solve the inaccuracy problem of predictability.

cs.IT↗

arXiv2021

Whittle Index Based Scheduling Policy for Minimizing the Cost of Age of Information

We design a new scheduling policy to minimize the general non-decreasing cost function of age of information (AoI) in a multiuser system. In this system, the base station stochastically generates time-sensitive packets and transmits them to corresponding user equipments via an unreliable channel. We first formulate the transmission scheduling problem as an average cost constrained Markov decision process problem. Through introducing the service charge, we derive the closed-form expression for the Whittle index, based on which we design the scheduling policy. Using numerical results, we demonstrate the performance gain of our designed scheduling policy compared to the existing policies, such as the optimal policy, the on-demand Whittle index policy, and the age greedy policy.

cs.IT↗

arXiv2021

Dual MINE-based Neural Secure Communications under Gaussian Wiretap Channel

Recently, some researches are devoted to the topic of end-to-end learning a physical layer secure communication system based on autoencoder under Gaussian wiretap channel. However, in those works, the reliability and security of the encoder model were learned through necessary decoding outputs of not only legitimate receiver but also the eavesdropper. In fact, the assumption of known eavesdropper's decoder or its output is not practical. To address this issue, in this paper we propose a dual mutual information neural estimation (MINE) based neural secure communications model. The security constraints of this method is constructed only with the input and output signal samples of the legal and eavesdropper channels and benefit that training the encoder is completely independent of the decoder. Moreover, since the design of secure coding does not rely on the eavesdropper's decoding results, the security performance would not be affected by the eavesdropper's decoding means. Numerical results show that the performance of our model is guaranteed whether the eavesdropper learns the decoder himself or uses the legal decoder.

cs.IT↗

arXiv2020

BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification

Few-shot learning for fine-grained image classification has gained recent attention in computer vision. Among the approaches for few-shot learning, due to the simplicity and effectiveness, metric-based methods are favorably state-of-the-art on many tasks. Most of the metric-based methods assume a single similarity measure and thus obtain a single feature space. However, if samples can simultaneously be well classified via two distinct similarity measures, the samples within a class can distribute more compactly in a smaller feature space, producing more discriminative feature maps. Motivated by this, we propose a so-called \textit{Bi-Similarity Network} (\textit{BSNet}) that consists of a single embedding module and a bi-similarity module of two similarity measures. After the support images and the query images pass through the convolution-based embedding module, the bi-similarity module learns feature maps according to two similarity measures of diverse characteristics. In this way, the model is enabled to learn more discriminative and less similarity-biased features from few shots of fine-grained images, such that the model generalization ability can be significantly improved. Through extensive experiments by slightly modifying established metric/similarity based networks, we show that the proposed approach produces a substantial improvement on several fine-grained image benchmark datasets. Codes are available at: https://github.com/spraise/BSNet

cs.CV↗

arXiv2020

Sum-Rate Maximization for IRS-Assisted UAV OFDMA Communication Systems

In this paper, we consider the application of intelligent reflecting surface (IRS) in unmanned aerial vehicle (UAV)-based orthogonal frequency division multiple access (OFDMA) communication systems, which exploits both the significant beamforming gain brought by the IRS and the high mobility of UAV for improving the system sum-rate. The joint design of UAV's trajectory, IRS scheduling, and communication resource allocation for the proposed system is formulated as a non-convex optimization problem to maximize the system sum-rate while taking into account the heterogeneous quality-of-service (QoS) requirement of each user. The existence of an IRS introduces both frequency-selectivity and spatial-selectivity in the fading of the composite channel from the UAV to ground users. To facilitate the design, we first derive the expression of the composite channels and propose a parametric approximation approach to establish an upper and a lower bound for the formulated problem. An alternating optimization algorithm is devised to handle the lower bound optimization problem and its performance is compared with the benchmark performance achieved by solving the upper bound problem. Simulation results unveil the small gap between the developed bounds and the promising sum-rate gain achieved by the deployment of an IRS in UAV-based communication systems.

cs.IT↗

arXiv2020

A Concise Review of Recent Few-shot Meta-learning Methods

Few-shot meta-learning has been recently reviving with expectations to mimic humanity's fast adaption to new concepts based on prior knowledge. In this short communication, we give a concise review on recent representative methods in few-shot meta-learning, which are categorized into four branches according to their technical characteristics. We conclude this review with some vital current challenges and future prospects in few-shot meta-learning.

cs.LG↗

arXiv2020

Coverage Analysis for 3D Terahertz Communication Systems with Blockage and Directional Antennas

The scarcity of spectrum resources in current wireless communication systems has sparked enormous research interest in the terahertz (THz) frequency band. This band is characterized by fundamentally different propagation properties resulting in different interference structures from what we have observed so far at lower frequencies. In this paper, we derive a new expression for the coverage probability of downlink transmission in THz communication systems within a three-dimensional (3D) environment. First, we establish a 3D propagation model which considers the molecular absorption loss, 3D directional antennas at both access points (APs) and user equipments (UEs), interference from nearby APs, and dynamic blockages caused by moving humans. Then, we develop a novel easy-to-use analytical framework based on the dominant interferer analysis to evaluate the coverage probability, the novelty of which lies in the incorporation of the instantaneous interference and the vertical height of THz devices. Our numerical results demonstrate the accuracy of our analysis and reveal that the coverage probability significantly decreases when the transmission distance increases. We also show the increasing blocker density and increasing AP density impose different impacts on the coverage performance when the UE-AP link of interest is in line-of-sight. We further show that the coverage performance improvement brought by increasing the antenna directivity at APs is higher than that brought by increasing the antenna directivity at UEs.

eess.SP↗

arXiv2019

CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation

Histopathology image analysis plays a critical role in cancer diagnosis and treatment. To automatically segment the cancerous regions, fully supervised segmentation algorithms require labor-intensive and time-consuming labeling at the pixel level. In this research, we propose CAMEL, a weakly supervised learning framework for histopathology image segmentation using only image-level labels. Using multiple instance learning (MIL)-based label enrichment, CAMEL splits the image into latticed instances and automatically generates instance-level labels. After label enrichment, the instance-level labels are further assigned to the corresponding pixels, producing the approximate pixel-level labels and making fully supervised training of segmentation models possible. CAMEL achieves comparable performance with the fully supervised approaches in both instance-level classification and pixel-level segmentation on CAMELYON16 and a colorectal adenoma dataset. Moreover, the generality of the automatic labeling methodology may benefit future weakly supervised learning studies for histopathology image analysis.

eess.IV↗

arXiv2019

Random Access for Massive Machine-Type Communications

The thesis is dedicated to studying methods to improve the efficiency of random access schemes and to facilitate their deployment in machine-type communications (MTC). First, a joint user activity identification and channel estimation scheme is designed for grant-free random access systems. We propose a decentralized transmission control and design a compressed sensing (CS)-based user identification and channel estimation scheme. We analyze the packet delay and throughput of the proposed scheme. We also optimize the transmission control scheme to maximize the system throughput. Second, a random access scheme, i.e., the coded slotted ALOHA (CSA) scheme, is designed for erasure channels to improve the system throughput. By deriving the extrinsic information transfer (EXIT) functions and optimizing their convergence behavior, we design the code probability distributions for CSA schemes with repetition codes and maximum distance separable (MDS) codes to maximize the expected traffic load, under packet erasure and slot erasure channels. We derive the asymptotic throughput of CSA schemes over the erasure channels for an infinite frame length, which is verified to well approximate the throughput for a practical frame length. Third, an efficient data decoding algorithm for the CSA scheme is proposed to further improve the system efficiency. We present a low-complexity physical-layer network coding (PNC) method to obtain linear combinations of collided packets and design an enhanced message-level successive interference cancellation (SIC) algorithm to exploit the linear combinations of collided packets. We propose an analytical framework and derive the system throughput for the proposed scheme. The CSA scheme is further optimized to maximize the system throughput and energy efficiency.

cs.IT↗

arXiv2010

Buffer Management Algorithm Design and Implementation Based on Network Processors

To solve the parameter sensitive issue of the traditional RED (random early detection) algorithm, an adaptive buffer management algorithm called PAFD (packet adaptive fair dropping) is proposed. This algorithm supports DiffServ (differentiated services) model of QoS (quality of service). In this algorithm, both of fairness and throughput are considered. The smooth buffer occupancy rate function is adopted to adjust the parameters. By implementing buffer management and packet scheduling on Intel IXP2400, the viability of QoS mechanisms on NPs (network processors) is verified. The simulation shows that the PAFD smoothes the flow curve, and achieves better balance between fairness and network throughput. It also demonstrates that this algorithm meets the requirements of fast data packet processing, and the hardware resource utilization of NPs is higher.

cs.NI↗