arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 1,549 records · Page 86Linked to original sources

arXiv2020

Sequential vs. Integrated Algorithm Selection and Configuration: A Case Study for the Modular CMA-ES

When faced with a specific optimization problem, choosing which algorithm to use is always a tough task. Not only is there a vast variety of algorithms to select from, but these algorithms often are controlled by many hyperparameters, which need to be tuned in order to achieve the best performance possible. Usually, this problem is separated into two parts: algorithm selection and algorithm configuration. With the significant advances made in Machine Learning, however, these problems can be integrated into a combined algorithm selection and hyperparameter optimization task, commonly known as the CASH problem. In this work we compare sequential and integrated algorithm selection and configuration approaches for the case of selecting and tuning the best out of 4608 variants of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) tested on the Black Box Optimization Benchmark (BBOB) suite. We first show that the ranking of the modular CMA-ES variants depends to a large extent on the quality of the hyperparameters. This implies that even a sequential approach based on complete enumeration of the algorithm space will likely result in sub-optimal solutions. In fact, we show that the integrated approach manages to provide competitive results at a much smaller computational cost. We also compare two different mixed-integer algorithm configuration techniques, called irace and Mixed-Integer Parallel Efficient Global Optimization (MIP-EGO). While we show that the two methods differ significantly in their treatment of the exploration-exploitation balance, their overall performances are very similar.

cs.NE↗

arXiv2019

Analysis of propagation for impulsive reaction-diffusion models

We study a hybrid impulsive reaction-advection-diffusion model given by a reaction-advection-diffusion equation composed with a discrete-time map in space dimension $n\in\mathbb N$. The reaction-advection-diffusion equation takes the form \begin{equation*}\label{} u^{(m)}_t = \text{div}(A\nabla u^{(m)}-q u^{(m)}) + f(u^{(m)}) \quad \text{for} \ \ (x,t)\in\mathbb R^n \times (0,1] , \end{equation*} for some function $f$, a drift $q$ and a diffusion matrix $A$. When the discrete-time map is local in space we use $N_m(x)$ to denote the density of population at a point $x$ at the beginning of reproductive season in the $m$th year and when the map is nonlocal we use $u_m(x)$. The local discrete-time map is \begin{eqnarray*}\label{}\left\{ \begin{array}{lcl} u^{(m)}(x,0) = g(N_m(x)) \quad \text{for} \ \ x\in \mathbb R^n , \\ N_{m+1}(x):=u^{(m)}(x,1) \quad \text{for} \ \ x\in \mathbb R^n , \end{array}\right. \end{eqnarray*} for some function $g$. The nonlocal discrete time map is \begin{eqnarray*}\label{}\left\{ \begin{array}{lcl} u^{(m)}(x,0) = u_{m}(x) \quad \text{for} \ \ x\in \mathbb R^n , \\ \label{mainb2} u_{m+1}(x) := g\left(\int_{\mathbb R^n} K(x-y)u^{(m)}(y,1) dy\right) \quad \text{for} \ \ x\in \mathbb R^n, \end{array}\right. \end{eqnarray*} when $K$ is a nonnegative normalized kernel. SEE THE ARTICLE FOR COMPLETE ABSTRACT.

math.AP↗

arXiv2019

Interlayer correlated fractional quantum Hall state in the ν = 4/5 bilayer system

We perform exact diagonalization studies for fractional quantum Hall states at filing factor 4/5 in a bilayer system, on a torus with various aspect ratios and angles. We find that in the absence of tunneling, two weakly coupled 2/5-layers undergo a phase transition into an interlayer-correlated regime, which is also Abelian with the five-fold degeneracy on the torus. In the limit of zero layer separation, this phase becomes a singlet in the pseudospin variable describing the layer degree-of-freedom. By studying the Chern-number matrix, we show that the K-matrix describing the interlayer-correlated regime requires matrix dimension larger than two and this regime is in particular not described by a Halperin state. A detailed analysis of possible 4 X 4 K-matrices having the requisite symmetries and quantum numbers shows that there is only one equivalence class of such matrices. A model wave function representing this universality class is constructed. The role of separate particle number conservation in both layers is discussed, and it is argued that this additional symmetry allows for the further distinction of two different symmetry protected Abelian phases in the interlayer correlated regime. Interlayer tunneling breaks this symmetry, and can drive the system into a single-layer regime when strong enough. A qualitative phase diagram in the tunneling-layer separation parameter space is proposed based on our numerical results.

cond-mat.str-el↗

arXiv2019

Magnetic Skyrmions are Quasi-Magnetic Monopoles in Two-Dimensional Magnetic Materials

Using $su(N)$ Cartan subalgebra local bases parametrization of density operator $ρ$, we prove that the Wu-Yang potentials of a general $N$-level quantum system are completely expressed by $SU(N)$ gauge transformation. By taking the $SU(2)$ Cartan subalgebra local basis as a local normalized magnetization vector, we find that magnetic skyrmion and Wu-Yang magnetic monopole have the same algebraic structure. Moreover, by taking the adiabatic unitary evolution of magnetization as local gauge transformation, we verify that the Wu-Yang potential of magnetic skyrmions is proportional to the Berry connection, this means that magnetic skyrmion is quasi-magnetic monopole. The exact relation between Wu-Yang potentials and Berry connection is discussed in detail for the general $SU(N)$ case, i.e. the Berry connection for the pure or mixed state is the weighted average of the $(N-1)$ Wu-Yang potentials.

quant-ph↗

arXiv2019

Enhancing Relation Extraction Using Syntactic Indicators and Sentential Contexts

State-of-the-art methods for relation extraction consider the sentential context by modeling the entire sentence. However, syntactic indicators, certain phrases or words like prepositions that are more informative than other words and may be beneficial for identifying semantic relations. Other approaches using fixed text triggers capture such information but ignore the lexical diversity. To leverage both syntactic indicators and sentential contexts, we propose an indicator-aware approach for relation extraction. Firstly, we extract syntactic indicators under the guidance of syntactic knowledge. Then we construct a neural network to incorporate both syntactic indicators and the entire sentences into better relation representations. By this way, the proposed model alleviates the impact of noisy information from entire sentences and breaks the limit of text triggers. Experiments on the SemEval-2010 Task 8 benchmark dataset show that our model significantly outperforms the state-of-the-art methods.

cs.CL↗

arXiv2019

Relating lp regularization and reweighted l1 regularization

We propose a general framework of iteratively reweighted l1 methods for solving lp regularization problems. We prove that after some iteration k, the iterates generated by the proposed methods have the same support and sign as the limit points, and are bounded away from 0, so that the algorithm behaves like solving a smooth problem in the reduced space. As a result, the global convergence can be easily obtained and an update strategy for the smoothing parameter is proposed which can automatically terminate the updates for zero components. We show that lp regularization problems are locally equivalent to a weighted l1 regularization problem and every optimal point corresponds to a Maximum A Posterior estimation for independently and non-identically distributed Laplace prior parameters. Numerical experiments exhibit the behaviors and the efficiency of our proposed methods.

math.OC↗

arXiv2019

Chinese Spelling Error Detection Using a Fusion Lattice LSTM

Spelling error detection serves as a crucial preprocessing in many natural language processing applications. Due to the characteristics of Chinese Language, Chinese spelling error detection is more challenging than error detection in English. Existing methods are mainly under a pipeline framework, which artificially divides error detection process into two steps. Thus, these methods bring error propagation and cannot always work well due to the complexity of the language environment. Besides existing methods only adopt character or word information, and ignore the positive effect of fusing character, word, pinyin1 information together. We propose an LF-LSTM-CRF model, which is an extension of the LSTMCRF with word lattices and character-pinyin-fusion inputs. Our model takes advantage of the end-to-end framework to detect errors as a whole process, and dynamically integrates character, word and pinyin information. Experiments on the SIGHAN data show that our LF-LSTM-CRF outperforms existing methods with similar external resources consistently, and confirm the feasibility of adopting the end-to-end framework and the availability of integrating of character, word and pinyin information.

cs.CL↗

arXiv2019

All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting

Recently, end-to-end text spotting that aims to detect and recognize text from cluttered images simultaneously has received particularly growing interest in computer vision. Different from the existing approaches that formulate text detection as bounding box extraction or instance segmentation, we localize a set of points on the boundary of each text instance. With the representation of such boundary points, we establish a simple yet effective scheme for end-to-end text spotting, which can read the text of arbitrary shapes. Experiments on three challenging datasets, including ICDAR2015, TotalText and COCO-Text demonstrate that the proposed method consistently surpasses the state-of-the-art in both scene text detection and end-to-end text recognition tasks.

cs.CV↗

arXiv2019

An Inexact First-order Method for Constrained Nonlinear Optimization

The primary focus of this paper is on designing an inexact first-order algorithm for solving constrained nonlinear optimization problems. By controlling the inexactness of the subproblem solution, we can significantly reduce the computational cost needed for each iteration. A penalty parameter updating strategy during the process of solving the subproblem enables the algorithm to automatically detect infeasibility. Global convergence for both feasible and infeasible cases are proved. Complexity analysis for the KKT residual is also derived under mild assumptions. Numerical experiments exhibit the ability of the proposed algorithm to rapidly find inexact optimal solution through cheap computational cost.

math.OC↗

arXiv2019

Inexact Primal-Dual Gradient Projection Methods for Nonlinear Optimization on Convex Set

In this paper, we propose a novel primal-dual inexact gradient projection method for nonlinear optimization problems with convex-set constraint. This method only needs inexact computation of the projections onto the convex set for each iteration, consequently reducing the computational cost for projections per iteration. This feature is attractive especially for solving problems where the projections are computationally not easy to calculate. Global convergence guarantee and O(1/k) ergodic convergence rate of the optimality residual are provided under loose assumptions. We apply our proposed strategy to l1-ball constrained problems. Numerical results exhibit that our inexact gradient projection methods for solving l1-ball constrained problems are more efficient than the exact methods.

math.OC↗

arXiv2019

Causality-based Feature Selection: Methods and Evaluations

Feature selection is a crucial preprocessing step in data analytics and machine learning. Classical feature selection algorithms select features based on the correlations between predictive features and the class variable and do not attempt to capture causal relationships between them. It has been shown that the knowledge about the causal relationships between features and the class variable has potential benefits for building interpretable and robust prediction models, since causal relationships imply the underlying mechanism of a system. Consequently, causality-based feature selection has gradually attracted greater attentions and many algorithms have been proposed. In this paper, we present a comprehensive review of recent advances in causality-based feature selection. To facilitate the development of new algorithms in the research area and make it easy for the comparisons between new methods and existing ones, we develop the first open-source package, called CausalFS, which consists of most of the representative causality-based feature selection algorithms (available at https://github.com/kuiy/CausalFS). Using CausalFS, we conduct extensive experiments to compare the representative algorithms with both synthetic and real-world data sets. Finally, we discuss some challenging problems to be tackled in future causality-based feature selection research.

cs.LG↗

arXiv2019

A unified approach for projections onto the intersection of $\ell_1$ and $\ell_2$ balls or spheres

This paper focuses on designing a unified approach for computing the projection onto the intersection of an $\ell_1$ ball/sphere and an $\ell_2$ ball/sphere. We show that the major computational efforts of solving these problems all rely on finding the root of the same piecewisely quadratic function, and then propose a unified numerical method to compute the root. In particular, we design breakpoint search methods with/without sorting incorporated with bisection, secant and Newton methods to find the interval containing the root, on which the root has a closed form. It can be shown that our proposed algorithms without sorting possess $O(n log n)$ worst-case complexity and $O(n)$ in practice. The efficiency of our proposed algorithms are demonstrated in numerical experiments.

math.OC↗

arXiv2019

Data augmentation in microscopic images for material data mining

Recent progress in material data mining has been driven by high-capacity models trained on large datasets. However, collecting experimental data (real data) has been extremely costly since the amount of human effort and expertise required. Here, we develop a novel transfer learning strategy to address small or insufficient data problem. This strategy realizes the fusion of real and simulated data, and the augmentation of training data in data mining procedure. For a specific task of image segmentation, this strategy can generate synthetic images by fusing physical mechanism of simulated images and "image style" of real images. The result shows that the model trained with the acquired synthetic images and 35% of the real images outperforms the model trained on all real images. As the time required to generate synthetic data is almost negligible, this strategy is able to reduce the time cost of real data preparation by roughly 65%.

cond-mat.mtrl-sci↗

arXiv2019

Semi-supervised representation learning via dual autoencoders for domain adaptation

Domain adaptation aims to exploit the knowledge in source domain to promote the learning tasks in target domain, which plays a critical role in real-world applications. Recently, lots of deep learning approaches based on autoencoders have achieved a significance performance in domain adaptation. However, most existing methods focus on minimizing the distribution divergence by putting the source and target data together to learn global feature representations, while they do not consider the local relationship between instances in the same category from different domains. To address this problem, we propose a novel Semi-Supervised Representation Learning framework via Dual Autoencoders for domain adaptation, named SSRLDA. More specifically, we extract richer feature representations by learning the global and local feature representations simultaneously using two novel autoencoders, which are referred to as marginalized denoising autoencoder with adaptation distribution (MDAad) and multi-class marginalized denoising autoencoder (MMDA) respectively. Meanwhile, we make full use of label information to optimize feature representations. Experimental results show that our proposed approach outperforms several state-of-the-art baseline methods.

cs.LG↗

arXiv2019

Stacked Semantic-Guided Network for Zero-Shot Sketch-Based Image Retrieval

Zero-shot sketch-based image retrieval (ZS-SBIR) is a task of cross-domain image retrieval from a natural image gallery with free-hand sketch under a zero-shot scenario. Previous works mostly focus on a generative approach that takes a highly abstract and sparse sketch as input and then synthesizes the corresponding natural image. However, the intrinsic visual sparsity and large intra-class variance of the sketch make the learning of the conditional decoder more difficult and hence achieve unsatisfactory retrieval performance. In this paper, we propose a novel stacked semantic-guided network to address the unique characteristics of sketches in ZS-SBIR. Specifically, we devise multi-layer feature fusion networks that incorporate different intermediate feature representation information in a deep neural network to alleviate the intrinsic sparsity of sketches. In order to improve visual knowledge transfer from seen to unseen classes, we elaborate a coarse-to-fine conditional decoder that generates coarse-grained category-specific corresponding features first (taking auxiliary semantic information as conditional input) and then generates fine-grained instance-specific corresponding features (taking sketch representation as conditional input). Furthermore, regression loss and classification loss are utilized to preserve the semantic and discriminative information of the synthesized features respectively. Extensive experiments on the large-scale Sketchy dataset and TU-Berlin dataset demonstrate that our proposed approach outperforms state-of-the-art methods by more than 20\% in retrieval performance.

cs.CV↗

arXiv2019

Semantic Adversarial Network for Zero-Shot Sketch-Based Image Retrieval

Zero-shot sketch-based image retrieval (ZS-SBIR) is a specific cross-modal retrieval task for retrieving natural images with free-hand sketches under zero-shot scenario. Previous works mostly focus on modeling the correspondence between images and sketches or synthesizing image features with sketch features. However, both of them ignore the large intra-class variance of sketches, thus resulting in unsatisfactory retrieval performance. In this paper, we propose a novel end-to-end semantic adversarial approach for ZS-SBIR. Specifically, we devise a semantic adversarial module to maximize the consistency between learned semantic features and category-level word vectors. Moreover, to preserve the discriminability of synthesized features within each training category, a triplet loss is employed for the generative module. Additionally, the proposed model is trained in an end-to-end strategy to exploit better semantic features suitable for ZS-SBIR. Extensive experiments conducted on two large-scale popular datasets demonstrate that our proposed approach remarkably outperforms state-of-the-art approaches by more than 12\% on Sketchy dataset and about 3\% on TU-Berlin dataset in the retrieval.

cs.CV↗

arXiv2019

Storage or No Storage: Duopoly Competition Between Renewable Energy Suppliers in a Local Energy Market

This paper studies the duopoly competition between renewable energy suppliers with or without energy storage in a local energy market. The storage investment brings the benefits of stabilizing renewable energy suppliers' outputs, but it also leads to substantial investment costs as well as some surprising changes in the market outcome. To study the equilibrium decisions of storage investment in the renewable energy suppliers' competition, we model the interactions between suppliers and consumers using a three-stage game-theoretic model. In Stage I, at the beginning of the investment horizon, suppliers decide whether to invest in storage. Once such decisions have been made, in the day-ahead market of each day, suppliers decide on their bidding prices and quantities in Stage II, based on which consumers decide the electricity quantity purchased from each supplier in Stage III. In the real-time market, a supplier is penalized if his actual generation falls short of his commitment. We characterize a price-quantity competition equilibrium of Stage II, and we further characterize a storage-investment equilibrium in Stage I incorporating electricity-selling revenue and storage cost. Counter-intuitively, we show that the uncertainty of renewable energy without storage investment can lead to higher supplier profits compared with the stable generations with storage investment due to the reduced market competition under random energy generation. Simulations further illustrate results due to the market competition. For example, a higher penalty for not meeting the commitment, a higher storage cost, or a lower consumer demand can sometimes increase a supplier's profit. We also show that although storage investment can increase a supplier 's profit, the first-mover supplier who invests in storage may benefit less than the free-rider competitor who chooses not to invest.

eess.SY↗

arXiv2019

Optimal Delivery with Budget Constraint in E-Commerce Advertising

Online advertising in E-commerce platforms provides sellers an opportunity to achieve potential audiences with different target goals. Ad serving systems (like display and search advertising systems) that assign ads to pages should satisfy objectives such as plenty of audience for branding advertisers, clicks or conversions for performance-based advertisers, at the same time try to maximize overall revenue of the platform. In this paper, we propose an approach based on linear programming subjects to constraints in order to optimize the revenue and improve different performance goals simultaneously. We have validated our algorithm by implementing an offline simulation system in Alibaba E-commerce platform and running the auctions from online requests which takes system performance, ranking and pricing schemas into account. We have also compared our algorithm with related work, and the results show that our algorithm can effectively improve campaign performance and revenue of the platform.

cs.LG↗