Searcharxiv⌕ Search

arXiv subjects

An Chen

Publications and source records attributed to An Chen.

At least 37 records · Page 2Linked to original sources
arXiv2023

Zone-based Federated Learning for Mobile Sensing Data

Mobile apps, such as mHealth and wellness applications, can benefit from deep learning (DL) models trained with mobile sensing data collected by smart phones or wearable devices. However, currently there is no mobile sensing DL system that simultaneously achieves good model accuracy while adapting to user mobility behavior, scales well as the number of users increases, and protects user data privacy. We propose Zone-based Federated Learning (ZoneFL) to address these requirements. ZoneFL divides the physical space into geographical zones mapped to a mobile-edge-cloud system architecture for good model accuracy and scalability. Each zone has a federated training model, called a zone model, which adapts well to data and behaviors of users in that zone. Benefiting from the FL design, the user data privacy is protected during the ZoneFL training. We propose two novel zone-based federated training algorithms to optimize zone models to user mobility behavior: Zone Merge and Split (ZMS) and Zone Gradient Diffusion (ZGD). ZMS optimizes zone models by adapting the zone geographical partitions through merging of neighboring zones or splitting of large zones into smaller ones. Different from ZMS, ZGD maintains fixed zones and optimizes a zone model by incorporating the gradients derived from neighboring zones' data. ZGD uses a self-attention mechanism to dynamically control the impact of one zone on its neighbors. Extensive analysis and experimental results demonstrate that ZoneFL significantly outperforms traditional FL in two models for heart rate prediction and human activity recognition. In addition, we developed a ZoneFL system using Android phones and AWS cloud. The system was used in a heart rate prediction field study with 63 users for 4 months, and we demonstrated the feasibility of ZoneFL in real-life.

cs.LG↗
arXiv2023

A Surrogate-Assisted Highly Cooperative Coevolutionary Algorithm for Hyperparameter Optimization in Deep Convolutional Neural Network

Convolutional neural networks (CNNs) have gained remarkable success in recent years. However, their performance highly relies on the architecture hyperparameters, and finding proper hyperparameters for a deep CNN is a challenging optimization problem owing to its high-dimensional and computationally expensive characteristics. Given these difficulties, this study proposes a surrogate-assisted highly cooperative hyperparameter optimization (SHCHO) algorithm for chain-styled CNNs. To narrow the large search space, SHCHO first decomposes the whole CNN into several overlapping sub-CNNs in accordance with the overlapping hyperparameter interaction structure and then cooperatively optimizes these hyperparameter subsets. Two cooperation mechanisms are designed during this process. One coordinates all the sub-CNNs to reproduce the information flow in the whole CNN and achieve macro cooperation among them, and the other tackles the overlapping components by simultaneously considering the involved two sub-CNNs and facilitates micro cooperation between them. As a result, a proper hyperparameter configuration can be effectively located for the whole CNN. Besides, SHCHO also employs the well-performing surrogate technique to assist in the hyperparameter optimization of each sub-CNN, thereby greatly reducing the expensive computational cost. Extensive experimental results on two widely-used image classification datasets indicate that SHCHO can significantly improve the performance of CNNs.

cs.NE↗
arXiv2023

Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators

Analog in-memory computing (AIMC) -- a promising approach for energy-efficient acceleration of deep learning workloads -- computes matrix-vector multiplications (MVMs) but only approximately, due to nonidealities that often are non-deterministic or nonlinear. This can adversely impact the achievable deep neural network (DNN) inference accuracy as compared to a conventional floating point (FP) implementation. While retraining has previously been suggested to improve robustness, prior work has explored only a few DNN topologies, using disparate and overly simplified AIMC hardware models. Here, we use hardware-aware (HWA) training to systematically examine the accuracy of AIMC for multiple common artificial intelligence (AI) workloads across multiple DNN topologies, and investigate sensitivity and robustness to a broad set of nonidealities. By introducing a new and highly realistic AIMC crossbar-model, we improve significantly on earlier retraining approaches. We show that many large-scale DNNs of various topologies, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers, can in fact be successfully retrained to show iso-accuracy on AIMC. Our results further suggest that AIMC nonidealities that add noise to the inputs or outputs, not the weights, have the largest impact on DNN accuracy, and that RNNs are particularly robust to all nonidealities.

cs.LG↗
arXiv2022

Downlink Massive MIMO Channel Estimation via Deep Unrolling : Sparsity Exploitations in Angular Domain

In frequency division duplex (FDD) massive MIMO systems, reliable downlink channel estimation is essential for the subsequent data transmission but is realized at the cost of massive pilot overhead due to hundreds of antennas at base station (BS). In order to reduce the pilot overhead without compromising the estimation, compressive sensing (CS) based methods have been widely applied for channel estimation by exploiting the inherent sparse structure of massive MIMO channel in angular domain. However, they still suffer from high complexity during optimization process and the requirement of prior knowledge on sparsity information. To overcome these challenges, this paper develops a novel hybrid channel estimation framework by integrating the model-driven CS and data-driven deep unrolling techniques. The proposed framework is composed of a coarse estimation part and a fine correction part, which is implemented in a two-stage manner to exploit both inter- and intra-frame sparsities of channels in angular domain. Then, two estimation schemes are designed depending on whether priori sparsity information is required, where the second scheme designs a new thresholding function to eliminate such requirement. Numerical results are provided to verify that our schemes can achieve high accuracy with low pilot overhead and low complexity.

eess.SP↗
arXiv2022

On the equivalence between Value-at-Risk- and Expected Shortfall-based risk measures in non-concave optimization

We study a non-concave optimization problem in which a financial company maximizes the expected utility of the surplus under a risk-based regulatory constraint. For this problem, we consider four different prevalent risk constraints (Expected Shortfall, Expected Discounted Shortfall, Value-at-Risk, and Average Value-at-Risk), and investigate their effects on the optimal solution. Our main contributions are in obtaining an analytical solution under each of the four risk constraints, in the form of the optimal terminal wealth. We show that the four risk constraints lead to the same optimal solution, which differs from previous conclusions obtained from the corresponding concave optimization problem under a risk constraint. Compared with the benchmark (unconstrained) non-concave utility maximization problem, all four risk constraints effectively and equivalently reduce the set of zero terminal wealth, but do not fully eliminate this set, indicating the success and failure of the respective financial regulations.

math.OC↗
arXiv2022

Optimal investment with time-varying stochastic endowments

This paper considers a utility maximization and optimal asset allocation problem in the presence of a stochastic endowment that cannot be fully hedged through trading in the financial market. After studying continuity properties of the value function for general utility functions, we rely on the dynamic programming approach to solve the optimization problem for power utility investors including the empirically relevant and mathematically challenging case of relative risk aversion larger than one. For this, we argue that the value function is the unique viscosity solution of the Hamilton-Jacobi-Bellman (HJB) equation. The homogeneity of the value function is then used to reduce the HJB equation by one dimension, which allows us to prove that the value function is even a classical solution thereof. Using this, an optimal strategy is derived and its asymptotic behavior in the large wealth regime is discussed.

q-fin.PM↗
arXiv2021

Experimental Realization of Weyl Exceptional Rings in a Synthetic Three-Dimensional Non-Hermitian Phononic Crystal

Weyl points (WPs) are isolated degeneracies carrying quantized topological charges, and are therefore robust against Hermitian perturbations. WPs are predicted to spread to the Weyl exceptional rings (WERs) in the presence of non-Hermiticity. Here, we use a one-dimensional (1D) Aubry-Andre-Harper (AAH) model to construct a Weyl semimetal in a 3D parameter space comprised of one reciprocal dimension and two synthetic dimensions. The inclusion of non-Hermiticity in the form of gain and loss produces a WER. The topology of the WER is characterized by both its topological charge and non-Hermitian winding numbers. The WER is experimentally observed in a 1D phononic crystal with the non-Hermiticity introduced by active acoustic components. In addition, Fermi arcs are observed to survive the presence of non-Hermitian effect. We envision our findings to pave the way for studying the high-dimensional non-Hermitian topological physics in acoustics.

cond-mat.mes-hall↗
arXiv2021

On the Investment Strategies in Occupational Pension Plans

Demographic changes increase the necessity to base the pension system more and more on the second and the third pillar, namely the occupational and private pension plans; this paper deals with Target Date Funds (TDFs), which are a typical investment opportunity for occupational pension planners. TDFs are usually identified with a decreasing fraction of wealth invested in equity (a so-called glide path) as retirement comes closer, i.e., wealth is invested more risky the younger the saver is. We investigate whether this is actually optimal in the presence of non-tradable income risk in a stochastic volatility environment. The retirement planning procedure is formulated as a stochastic optimization problem. We find it is the (random) contributions that induce the optimal path exhibiting a glide path structure, both in the constant and stochastic volatility environment. Moreover, the initial wealth and the initial contribution made to a retirement account strongly influence the fractional amount of wealth to be invested in risky assets. The risk aversion of an individual mainly determines the steepness of the glide path.

q-fin.PM↗
arXiv2021

Enhancing hierarchical surrogate-assisted evolutionary algorithm for high-dimensional expensive optimization via random projection

By remarkably reducing real fitness evaluations, surrogate-assisted evolutionary algorithms (SAEAs), especially hierarchical SAEAs, have been shown to be effective in solving computationally expensive optimization problems. The success of hierarchical SAEAs mainly profits from the potential benefit of their global surrogate models known as "blessing of uncertainty" and the high accuracy of local models. However, their performance leaves room for improvement on highdimensional problems since now it is still challenging to build accurate enough local models due to the huge solution space. Directing against this issue, this study proposes a new hierarchical SAEA by training local surrogate models with the help of the random projection technique. Instead of executing training in the original high-dimensional solution space, the new algorithm first randomly projects training samples onto a set of low-dimensional subspaces, then trains a surrogate model in each subspace, and finally achieves evaluations of candidate solutions by averaging the resulting models. Experimental results on six benchmark functions of 100 and 200 dimensions demonstrate that random projection can significantly improve the accuracy of local surrogate models and the new proposed hierarchical SAEA possesses an obvious edge over state-of-the-art SAEAs

cs.NE↗
arXiv2021

A Surrogate-Assisted Variable Grouping Algorithm for General Large Scale Global Optimization Problems

Problem decomposition plays a vital role when applying cooperative coevolution (CC) to large scale global optimization problems. However, most learning-based decomposition algorithms either only apply to additively separable problems or face the issue of false separability detections. Directing against these limitations, this study proposes a novel decomposition algorithm called surrogate-assisted variable grouping (SVG). SVG first designs a general-separability-oriented detection criterion according to whether the optimum of a variable changes with other variables. This criterion is consistent with the separability definition and thus endows SVG with broad applicability and high accuracy. To reduce the fitness evaluation requirement, SVG seeks the optimum of a variable with the help of a surrogate model rather than the original expensive high-dimensional model. Moreover, it converts the variable grouping process into a dynamic-binary-tree search one, which facilitates reutilizing historical separability detection information and thus reducing detection times. To evaluate the performance of SVG, a suite of benchmark functions with up to 2000 dimensions, including additively and non-additively separable ones, were designed. Experimental results on these functions indicate that, compared with six state-of-the-art decomposition algorithms, SVG possesses broader applicability and competitive efficiency. Furthermore, it can significantly enhance the optimization performance of CC.

cs.NE↗
arXiv2020

Distinguishing high-mass binary neutron stars from binary black holes with second- and third-generation gravitational wave observatories

(Abridged) While the gravitational-wave (GW) signal GW170817 was accompanied by a variety of electromagnetic (EM) counterparts, sufficiently high-mass binary neutron star (BNS) mergers are expected to be unable to power bright EM counterparts. The putative high-mass binary BNS merger GW190425, for which no confirmed EM counterpart has been identified, may be an example of such a system. It is thus important to understand how well we will be able to distinguish high-mass BNSs and low-mass binary black holes (BBHs) solely from their GW signals. To do this, we consider the imprint of the tidal deformability of the neutron stars on the GW signal for systems undergoing prompt black hole formation after merger. We model the BNS signals using hybrid numerical relativity -- tidal effective-one-body waveforms. Specifically, we consider a set of five nonspinning equal-mass BNS signals with masses of 2.7, 3.0, 3.2 Msun and with three different equations of state, as well as the analogous BBH signals. We perform parameter estimation on these signals in three networks: Advanced LIGO-Advanced Virgo and Advanced LIGO-Advanced Virgo-KAGRA with sensitivities similar to O3 and O4, respectively, and a 3G network of two Cosmic Explorers (CEs) and one Einstein Telescope, with a CE sensitivity similar to Stage 2. Our analysis suggests that we cannot distinguish the signals from high-mass BNSs and BBHs at a 90% credible level with the O3-like network even at 40 Mpc. However, we can distinguish all but the most compact BNSs that we consider in our study from BBHs at 40 Mpc at a >= 95% credible level using the O4-like network, and can even distinguish them at a > 99.2% (>= 97%) credible level at 369 (835) Mpc using the 3G network. Additionally, we present a simple method to compute the leading effect of the Earth's rotation on the response of a gravitational wave detector in the frequency domain.

astro-ph.HE↗
arXiv2020

An Eigenspace Divide-and-Conquer Approach for Large-Scale Optimization

Divide-and-conquer-based (DC-based) evolutionary algorithms (EAs) have achieved notable success in dealing with large-scale optimization problems (LSOPs). However, the appealing performance of this type of algorithms generally requires a high-precision decomposition of the optimization problem, which is still a challenging task for existing decomposition methods. This study attempts to address the above issue from a different perspective and proposes an eigenspace divide-and-conquer (EDC) approach. Different from existing DC-based algorithms that perform decomposition and optimization in the original decision space, EDC first establishes an eigenspace by conducting singular value decomposition on a set of high-quality solutions selected from recent generations. Then it transforms the optimization problem into the eigenspace, and thus significantly weakens the dependencies among the corresponding eigenvariables. Accordingly, these eigenvariables can be efficiently grouped by a simple random strategy and each of the resulting subproblems can be addressed more easily by a traditional EA. To verify the efficiency of EDC, comprehensive experimental studies were conducted on two sets of benchmark functions. Experimental results indicate that EDC is robust to its parameters and has good scalability to the problem dimension. The comparison with several state-of-the-art algorithms further confirms that EDC is pretty competitive and performs better on complicated LSOPs.

cs.NE↗
arXiv2019

Laypunov Irregular Points With Distributional Chaos

It follows from Oseledec Multiplicative Ergodic Theorem (or Kingmans Subadditional Ergodic Theorem) that the Lyapunov-irregular set of points for which the Oseledec averages of a given continuous cocycle diverge has zero measure with respect to any invariant probability measure. In strong contrast, for any dynamical system f with exponential specification property and a Holder continuous matrix cocycle A, we show here that if there exist ergodic measures with different Lyapunov spectrum, then the Lyapunov-irregular set of A displays distributional chaos of type 1.

math.DS↗
arXiv2019

A Fast Differential Grouping Algorithm for Large Scale Black-Box Optimization

Decomposition plays a significant role in cooperative co-evolution which shows great potential in large scale black-box optimization. However, current popular decomposition algorithms generally require to sample and evaluate a large number of solutions for interdependency detection, which is very time-consuming. To address this issue, this study proposes a new decomposition algorithm named fast differential grouping (FDG). FDG first identifies the type of an instance by detecting the interdependencies of a few pairs of variable subsets selected according to certain rules, and thus can rapidly complete the decomposition of a fully separable or nonseparable instance. For an identified partially separable instance, FDG converts the key decomposition process into a search process in a binary tree by taking corresponding variable subsets as tree nodes. This enables it to directly deduce the interdependency related to a child node by reutilizing the solutions sampled for corresponding parent and brother nodes. To support the above operations, this study designs a normalized variable-subset-oriented interdependency indicator, which can adaptively generate decomposition thresholds according to its distribution and thus enhances decomposition accuracy. Computational complexity analysis and experimental results verify that FDG outperforms popular decomposition algorithms. Further tests indicate that FDG embedded in a cooperative co-evolution framework can achieve highly competitive optimization results as compared with some state-of-the-art algorithms for large scale black-box optimization.

math.OC↗
arXiv2018

A Scoring Method for Driving Safety Credit Using Trajectory Data

Urban traffic systems worldwide are suffering from severe traffic safety problems. Traffic safety is affected by many complex factors, and heavily related to all drivers' behaviors involved in traffic system. Drivers with aggressive driving behaviors increase the risk of traffic accidents. In order to manage the safety level of traffic system, we propose Driving Safety Credit inspired by credit score in financial security field, and design a scoring method using trajectory data and violation records. First, we extract driving habits, aggressive driving behaviors and traffic violation behaviors from driver's trajectories and traffic violation records. Next, we train a classification model to filtered out irrelevant features. And at last, we score each driver with selected features. We verify our proposed scoring method using 40 days of traffic simulation, and proves the effectiveness of our scoring method.

cs.CY↗
arXiv2018

Enhancing Gaussian Estimation of Distribution Algorithm by Exploiting Evolution Direction with Archive

As a typical model-based evolutionary algorithm (EA), estimation of distribution algorithm (EDA) possesses unique characteristics and has been widely applied to global optimization. However, the common-used Gaussian EDA (GEDA) usually suffers from premature convergence which severely limits its search efficiency. This study first systematically analyses the reasons for the deficiency of the traditional GEDA, then tries to enhance its performance by exploiting its evolution direction, and finally develops a new GEDA variant named EDA2. Instead of only utilizing some good solutions produced in the current generation when estimating the Gaussian model, EDA2 preserves a certain number of high-quality solutions generated in previous generations into an archive and takes advantage of these historical solutions to assist estimating the covariance matrix of Gaussian model. By this means, the evolution direction information hidden in the archive is naturally integrated into the estimated model which in turn can guide EDA2 towards more promising solution regions. Moreover, the new estimation method significantly reduces the population size of EDA2 since it needs fewer individuals in the current population for model estimation. As a result, a fast convergence can be achieved. To verify the efficiency of EDA2, we tested it on a variety of benchmark functions and compared it with several state-of-the-art EAs, including IPOP-CMAES, AMaLGaM, three high-powered DE algorithms, and a new PSO algorithm. The experimental results demonstrate that EDA2 is efficient and competitive.

cs.NE↗
arXiv2018

Visual Path Tracking Control for Park Scene

Autonomous driving application is developing towards specific scenes. Park scene has features such as low speed, fixed routes, short connection, less complex traffic, and hence is suitable for bringing autonomous driving technology into reality. This paper targets park scene, and proposes a visual path tracking lateral control method using only one webcam. First, we calculate error of distance and error of angle from camera images, and then use fuzzy logic to fuzzify them into a combined error degree. The PID control algorithm takes it as input, and outputs steering wheel angle control command. Fuzzification could tolerate the error brought by image transformation and lane detection, making PID control more stably. Our experiments in both virtual and real scene show that our method can accurately and robustly follow the path, even at night. Compared with pure pursuit, our method can make 5 meters turning.

eess.SY↗