arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 1,675 records · Page 93Linked to original sources

arXiv2017

Cluster-based Kriging Approximation Algorithms for Complexity Reduction

Kriging or Gaussian Process Regression is applied in many fields as a non-linear regression model as well as a surrogate model in the field of evolutionary computation. However, the computational and space complexity of Kriging, that is cubic and quadratic in the number of data points respectively, becomes a major bottleneck with more and more data available nowadays. In this paper, we propose a general methodology for the complexity reduction, called cluster Kriging, where the whole data set is partitioned into smaller clusters and multiple Kriging models are built on top of them. In addition, four Kriging approximation algorithms are proposed as candidate algorithms within the new framework. Each of these algorithms can be applied to much larger data sets while maintaining the advantages and power of Kriging. The proposed algorithms are explained in detail and compared empirically against a broad set of existing state-of-the-art Kriging approximation methods on a well-defined testing framework. According to the empirical study, the proposed algorithms consistently outperform the existing algorithms. Moreover, some practical suggestions are provided for using the proposed algorithms.

cs.LG↗

arXiv2016

A high performance Nb nano-SQUID with a three-dimensional structure

A superconducting quantum interference device (SQUID) miniaturized into nanoscale is promising in the inductive detection of a single electron spin. A nano-SQUID with a strong spin coupling coefficient, a low flux noise, and a wide working magnetic field range is highly desired in a single spin resonance measurement. Nano-SQUIDs with Dayem-bridge junctions excel in a high working field range and in the direct coupling from spins to the bridge. However, the common planar structure of nano-SQUIDs is known for problems such as a shallow flux modulation depth and a troublesome hysteresis in current-voltage curves. Here, we developed a fabrication process for creating three-dimensional (3-D) niobium (Nb) nano-SQUIDs with nano-bridge junctions that can be tuned independently. Characterization of the device shows up to 45.9 % modulation depth with a reversible current-voltage curve. Owning to the large modulation depth, the measured flux noise is as low as 0.34 μΦ$_0$/Hz$^{1/2}$. The working field range of the SQUID is greater than 0.5 T parallel to the SQUID plane. We believe that 3-D Nb nano-SQUIDs provide a promising step toward effective single-spin inductive detection.

cond-mat.mes-hall↗

arXiv2016

On impulsive reaction-diffusion models in higher dimensions

Assume that $N_m(x)$ denotes the density of the population at a point $x$ at the beginning of the reproductive season in the $m$th year. We study the following impulsive reaction-diffusion model for any $m\in \mathbb Z^+$ \begin{eqnarray*}\label{} \ \ \ \ \ \left\{ \begin{array}{lcl} u^{(m)}_t = div(A\nabla u^{(m)}-a u^{(m)}) + f(u^{(m)}) \quad \text{for} \ \ (x,t)\inΩ\times (0,1] u^{(m)}(x,0)=g(N_m(x)) \quad \text{for} \ \ x\in Ω N_{m+1}(x):=u^{(m)}(x,1) \quad \text{for} \ \ x\in Ω\end{array}\right. \end{eqnarray*} for functions $f,g$, a drift $a$ and a diffusion matrix $A$ and $Ω\subset \mathbb R^n$. Study of this model requires a simultaneous analysis of the differential equation and the recurrence relation. When boundary conditions are hostile we provide critical domain results showing how extinction versus persistence of the species arises, depending on the size and geometry of the domain. We show that there exists an {\it extreme volume size} such that if $|Ω|$ falls below this size the species is driven extinct, regardless of the geometry of the domain. To construct such extreme volume sizes and critical domain sizes, we apply Schwarz symmetrization rearrangement arguments, the classical Rayleigh-Faber-Krahn inequality and the spectrum of uniformly elliptic operators. The critical domain results provide qualitative insight regarding long-term dynamics for the model. Lastly, we provide applications of our main results to certain biological reaction-diffusion models regarding marine reserve, terrestrial reserve, insect pest outbreak and population subject to climate change.

math.AP↗

arXiv2016

Natural-Parameter Networks: A Class of Probabilistic Neural Networks

Neural networks (NN) have achieved state-of-the-art performance in various applications. Unfortunately in applications where training data is insufficient, they are often prone to overfitting. One effective way to alleviate this problem is to exploit the Bayesian approach by using Bayesian neural networks (BNN). Another shortcoming of NN is the lack of flexibility to customize different distributions for the weights and neurons according to the data, as is often done in probabilistic graphical models. To address these problems, we propose a class of probabilistic neural networks, dubbed natural-parameter networks (NPN), as a novel and lightweight Bayesian treatment of NN. NPN allows the usage of arbitrary exponential-family distributions to model the weights and neurons. Different from traditional NN and BNN, NPN takes distributions as input and goes through layers of transformation before producing distributions to match the target output distributions. As a Bayesian treatment, efficient backpropagation (BP) is performed to learn the natural parameters for the distributions over both the weights and neurons. The output distributions of each layer, as byproducts, may be used as second-order representations for the associated tasks such as link prediction. Experiments on real-world datasets show that NPN can achieve state-of-the-art performance.

cs.LG↗

arXiv2016

Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks

Hybrid methods that utilize both content and rating information are commonly used in many recommender systems. However, most of them use either handcrafted features or the bag-of-words representation as a surrogate for the content information but they are neither effective nor natural enough. To address this problem, we develop a collaborative recurrent autoencoder (CRAE) which is a denoising recurrent autoencoder (DRAE) that models the generation of content sequences in the collaborative filtering (CF) setting. The model generalizes recent advances in recurrent deep learning from i.i.d. input to non-i.i.d. (CF-based) input and provides a new denoising scheme along with a novel learnable pooling scheme for the recurrent autoencoder. To do this, we first develop a hierarchical Bayesian model for the DRAE and then generalize it to the CF setting. The synergy between denoising and CF enables CRAE to make accurate recommendations while learning to fill in the blanks in sequences. Experiments on real-world datasets from different domains (CiteULike and Netflix) show that, by jointly modeling the order-aware generation of sequences for the content information and performing CF for the ratings, CRAE is able to significantly outperform the state of the art on both the recommendation task based on ratings and the sequence generation task based on content information.

cs.LG↗

arXiv2016

Evolving the Structure of Evolution Strategies

Various variants of the well known Covariance Matrix Adaptation Evolution Strategy (CMA-ES) have been proposed recently, which improve the empirical performance of the original algorithm by structural modifications. However, in practice it is often unclear which variation is best suited to the specific optimization problem at hand. As one approach to tackle this issue, algorithmic mechanisms attached to CMA-ES variants are considered and extracted as functional \emph{modules}, allowing for combinations of them. This leads to a configuration space over ES structures, which enables the exploration of algorithm structures and paves the way toward novel algorithm generation. Specifically, eleven modules are incorporated in this framework with two or three alternative configurations for each module, resulting in $4\,608$ algorithms. A self-adaptive Genetic Algorithm (GA) is used to efficiently evolve effective ES-structures for given classes of optimization problems, outperforming any classical CMA-ES variants from literature. The proposed approach is evaluated on noiseless functions from BBOB suite. Furthermore, such an observation is again confirmed on different function groups and dimensionality, indicating the feasibility of ES configuration on real-world problem classes.

cs.NE↗

arXiv2016

Incentivizing Energy Trading for Interconnected Microgrids

In this paper, we study the interactions among interconnected autonomous microgrids, and propose a joint energy trading and scheduling strategy. Each interconnected microgrid not only schedules its local power supply and demand, but also trades energy with other microgrids in a distribution network. Specifically, microgrids with excessive renewable generations can trade with other microgrids in deficit of power supplies for mutual benefits. Since interconnected microgrids operate autonomously, they aim to optimize their own performance and expect to gain benefits through energy trading. We design an incentive mechanism using Nash bargaining theory to encourage proactive energy trading and fair benefit sharing. We solve the bargaining problem by decomposing it into two sequential problems on social cost minimization and trading benefit sharing, respectively. For practical implementation, we propose a decentralized solution method with minimum information exchange overhead. Numerical studies based on realistic data demonstrate that the total cost of the interconnected-microgrids operation can be reduced by up to 13.2% through energy trading, and an individual participating microgrid can achieve up to 29.4% reduction in its cost through energy trading.

cs.GT↗

arXiv2016

Towards Bayesian Deep Learning: A Framework and Some Existing Methods

While perception tasks such as visual object recognition and text understanding play an important role in human intelligence, the subsequent tasks that involve inference, reasoning and planning require an even higher level of intelligence. The past few years have seen major advances in many perception tasks using deep learning models. For higher-level inference, however, probabilistic graphical models with their Bayesian nature are still more powerful and flexible. To achieve integrated intelligence that involves both perception and inference, it is naturally desirable to tightly integrate deep learning and Bayesian models within a principled probabilistic framework, which we call Bayesian deep learning. In this unified framework, the perception of text or images using deep learning can boost the performance of higher-level inference and in return, the feedback from the inference process is able to enhance the perception of text or images. This paper proposes a general framework for Bayesian deep learning and reviews its recent applications on recommender systems, topic models, and control. In this paper, we also discuss the relationship and differences between Bayesian deep learning and other related topics like Bayesian treatment of neural networks.

stat.ML↗

arXiv2016

Bayesian quantile additive regression trees

Ensemble of regression trees have become popular statistical tools for the estimation of conditional mean given a set of predictors. However, quantile regression trees and their ensembles have not yet garnered much attention despite the increasing popularity of the linear quantile regression model. This work proposes a Bayesian quantile additive regression trees model that shows very good predictive performance illustrated using simulation studies and real data applications. Further extension to tackle binary classification problems is also considered.

stat.ML↗

arXiv2016

On Capacity and Delay of Multi-channel Wireless Networks with Infrastructure Support

In this paper, we propose a novel multi-channel network with infrastructure support, called an MC-IS network, which has not been studied in the literature. To the best of our knowledge, we are the first to study such an MC-IS network. Our proposed MC-IS network has a number of advantages over three existing conventional networks, namely a single-channel wireless ad hoc network (called an SC-AH network), a multi-channel wireless ad hoc network (called an MC-AH network) and a single-channel network with infrastructure support (called an SC-IS network). In particular, the network capacity of our proposed MC-IS network is $\sqrt{n \log n}$ times higher than that of an SC-AH network and an MC-AH network and the same as that of an SC-IS network, where $n$ is the number of nodes in the network. The average delay of our MC-IS network is $\sqrt{\log n/n}$ times lower than that of an SC-AH network and an MC-AH network, and $\min\{C_I,m\}$ times lower than the average delay of an SC-IS network, where $C_I$ and $m$ denote the number of channels dedicated for infrastructure communications and the number of interfaces mounted at each infrastructure node, respectively. Our analysis on an MC-IS network equipped with omni-directional antennas only has been extended to an MC-IS network equipped with directional antennas only, which are named as an MC-IS-DA network. We show that an MC-IS-DA network has an even lower delay of $\frac{c}{\lfloor \frac{2π}θ\rfloor \cdot C_I}$ compared with an SC-IS network and our MC-IS network. For example, when $C_I=12$ and $θ=\fracπ{12}$, an MC-IS-DA network can further reduce the delay by 24 times lower that of an MC-IS network and reduce the delay by 288 times lower than that of an SC-IS network.

cs.NI↗

arXiv2016

Cooperative Planning of Renewable Generations for Interconnected Microgrids

We study the renewable energy generations in Hong Kong based on realistic meteorological data, and find that different renewable sources exhibit diverse time-varying and location-dependent profiles. To efficiently explore and utilize the diverse renewable energy generations, we propose a theoretical framework for the cooperative planning of renewable generations in a system of interconnected microgrids. The cooperative framework considers the self-interested behaviors of microgrids, and incorporates both their long-term investment costs and short-term operational costs over the planning horizon. Specifically, interconnected microgrids jointly decide where and how much to deploy renewable energy generations, and how to split the associated investment cost. We show that the cooperative framework minimizes the overall system cost. We also design a fair cost sharing method based on Nash bargaining to incentivize cooperative planning, such that all microgrids will benefit from cooperative planning. Using realistic data obtained from the Hong Kong observatory, we validate the cooperative planning framework, and demonstrate that all microgrids benefit through the cooperation, and the overall system cost is reduced by 35.9% compared to the noncooperative planning benchmark.

cs.GT↗

arXiv2016

Nematic quantum critical point without magnetism in FeSe1-xSx superconductors

The importance of antiferromagnetic fluctuations are widely acknowledged in most unconventional superconductors. In addition, cuprates and iron pnictides often exhibit unidirectional (nematic) electronic correlations, including stripe and orbital orders, whose fluctuations may also play a key role for electron pairing. However, these nematic correlations are intertwined with antiferromagnetic or charge orders, preventing us to identify the essential role of nematic fluctuations. This calls for new materials having only nematicity without competing or coexisting orders. Here we report systematic elastoresistance measurements in FeSe$_{1-x}$S$_{x}$ superconductors, which, unlike other iron-based families, exhibit an electronic nematic order without accompanying antiferromagnetic order. We find that the nematic transition temperature decreases with sulphur content $x$, whereas the nematic fluctuations are strongly enhanced. Near $x\approx0.17$, the nematic susceptibility diverges towards absolute zero, revealing a nematic quantum critical point. This highlights FeSe$_{1-x}$S$_{x}$ as a unique nonmagnetic system suitable for studying the impact of nematicity on superconductivity.

cond-mat.supr-con↗

arXiv2016

Error Bounds for the Krylov Subspace Methods for Computations of Matrix Exponentials

In this paper, we present new a posteriori and a priori error bounds for the Krylov subspace methods for computing $e^{-τA}v$ for a given $τ>0$ and $v \in C^n$, where $A$ is a large sparse non-Hermitian matrix. The {\em a priori} error bounds relate the convergence to $λ_{\min}\left(\frac{A+A^*}{2}\right)$, $λ_{\max}\left(\frac{A+A^*}{2}\right)$ (the smallest and the largest eigenvalue of the Hermitian part of $A$) and $|λ_{\max}\left(\frac{A-A^*}{2}\right)|$ (the largest eigenvalue in absolute value of the skew-Hermitian part of $A$), which define a rectangular region enclosing the field of values of $A$. In particular, our bounds explain an observed superlinear convergence behavior where the error may first stagnate for certain iterations before it starts to converge. The special case that $A$ is skew-Hermitian is also considered. Numerical examples are given to demonstrate the theoretical bounds.

math.NA↗

arXiv2016

MPBART - Multinomial Probit Bayesian Additive Regression Trees

This article proposes Multinomial Probit Bayesian Additive Regression Trees (MPBART) as a multinomial probit extension of BART - Bayesian Additive Regression Trees (Chipman et al (2010)). MPBART is flexible to allow inclusion of predictors that describe the observed units as well as the available choice alternatives. Through two simulation studies and four real data examples, we show that MPBART exhibits very good predictive performance in comparison to other discrete choice and multiclass classification methods. To implement MPBART, we have developed an R package mpbart available freely from CRAN repositories.

stat.ML↗

arXiv2015

A System for Extracting Sentiment from Large-Scale Arabic Social Data

Social media data in Arabic language is becoming more and more abundant. It is a consensus that valuable information lies in social media data. Mining this data and making the process easier are gaining momentum in the industries. This paper describes an enterprise system we developed for extracting sentiment from large volumes of social data in Arabic dialects. First, we give an overview of the Big Data system for information extraction from multilingual social data from a variety of sources. Then, we focus on the Arabic sentiment analysis capability that was built on top of the system including normalizing written Arabic dialects, building sentiment lexicons, sentiment classification, and performance evaluation. Lastly, we demonstrate the value of enriching sentiment results with user profiles in understanding sentiments of a specific user group.

cs.CL↗

arXiv2015

Sentiment Expression via Emoticons on Social Media

Emoticons (e.g., :) and :( ) have been widely used in sentiment analysis and other NLP tasks as features to ma- chine learning algorithms or as entries of sentiment lexicons. In this paper, we argue that while emoticons are strong and common signals of sentiment expression on social media the relationship between emoticons and sentiment polarity are not always clear. Thus, any algorithm that deals with sentiment polarity should take emoticons into account but extreme cau- tion should be exercised in which emoticons to depend on. First, to demonstrate the prevalence of emoticons on social media, we analyzed the frequency of emoticons in a large re- cent Twitter data set. Then we carried out four analyses to examine the relationship between emoticons and sentiment polarity as well as the contexts in which emoticons are used. The first analysis surveyed a group of participants for their perceived sentiment polarity of the most frequent emoticons. The second analysis examined clustering of words and emoti- cons to better understand the meaning conveyed by the emoti- cons. The third analysis compared the sentiment polarity of microblog posts before and after emoticons were removed from the text. The last analysis tested the hypothesis that removing emoticons from text hurts sentiment classification by training two machine learning models with and without emoticons in the text respectively. The results confirms the arguments that: 1) a few emoticons are strong and reliable signals of sentiment polarity and one should take advantage of them in any senti- ment analysis; 2) a large group of the emoticons conveys com- plicated sentiment hence they should be treated with extreme caution.

cs.CL↗

arXiv2015

Joint Investment and Operation of Microgrid

In this paper, we propose a theoretical framework for the joint optimization of investment and operation of a microgrid, taking the impact of energy storage, renewable energy integration, and demand response into consideration. We first study the renewable energy generations in Hong kong, and identify the potential benefit of mixed deployment of solar and wind energy generations. Then we model the joint investment and operation as a two-period stochastic programming program. In period-1, the microgrid operator makes the optimal investment decisions on the capacities of solar power generation, wind power generation, and energy storage. In period-2, the operator coordinates the power supply and demand in the microgrid to minimize the operating cost. We design a decentralized algorithm for computing the optimal pricing and power consumption in period-2, based on which we solve the optimal investment problem in period-1. We also study the impact of prediction error of renewable energy generation on the portfolio investment using robust optimization framework. Using realistic meteorological data obtained from the Hong Kong observatory, we numerically characterize the optimal portfolio investment decisions, optimal day-ahead pricing and power scheduling, and demonstrate the advantage of using mixed renewable energy and demand response in terms of reducing investment cost.

eess.SY↗

arXiv2015

Proactive Demand Response for Data Centers: A Win-Win Solution

In order to reduce the energy cost of data centers, recent studies suggest distributing computation workload among multiple geographically dispersed data centers, by exploiting the electricity price difference. However, the impact of data center load redistribution on the power grid is not well understood yet. This paper takes the first step towards tackling this important issue, by studying how the power grid can take advantage of the data centers' load distribution proactively for the purpose of power load balancing. We model the interactions between power grid and data centers as a two-stage problem, where the utility company chooses proper pricing mechanisms to balance the electric power load in the first stage, and the data centers seek to minimize their total energy cost by responding to the prices in the second stage. We show that the two-stage problem is a bilevel quadratic program, which is NP-hard and cannot be solved using standard convex optimization techniques. We introduce benchmark problems to derive upper and lower bounds for the solution of the two-stage problem. We further propose a branch and bound algorithm to attain the globally optimal solution, and propose a heuristic algorithm with low computational complexity to obtain an alternative close-to-optimal solution. We also study the impact of background load prediction error using the theoretical framework of robust optimization. The simulation results demonstrate that our proposed scheme can not only improve the power grid reliability but also reduce the energy cost of data centers.

eess.SY↗