arXiv subjects

Bin Wang

Publications and source records attributed to Bin Wang.

At least 793 records · Page 44Linked to original sources

arXiv2019

Graph Attention Memory for Visual Navigation

Visual navigation in complex environments is inefficient with traditional reactive policy or general-purposed recurrent policy. To address the long-term memory issue, this paper proposes a graph attention memory (GAM) architecture consisting of memory construction module, graph attention module and control module. The memory construction module builds the topological graph based on supervised learning by taking the exploration prior. Then, guided attention features are extracted with the graph attention module. Finally, the deep reinforcement learning based control module makes decisions based on visual observations and guided attention features. Detailed convergence analysis of GAM is presented in this paper. We evaluate GAM-based navigation system in two complex 3D environments. Experimental results show that the GAM-based navigation system significantly improves learning efficiency and outperforms all baselines in average success rate.

cs.CV↗

arXiv2019

Analytical Solution for Stochastic Unit Commitment Considering Wind Power Uncertainty with Gaussian Mixture Model

To capture the stochastic characteristics of renewable energy generation output, the chance-constrained unit commitment (CCUC) model is widely used. Conventionally, analytical solution for CCUC is usually based on simplified probability assumption or neglecting some operational constraints, otherwise scenar-io-based methods are used to approximate probability with heavy computation burden. In this paper, Gaussian mixture model (GMM) is employed to characterize the correlation between wind farms and probability distribution of their forecast errors. In our model, chance constraints including reserve sufficiency and branch power flow bounds are ensured to be satisfied with pre-determined probability. To solve this CCUC problem, we propose a Newton method based procedure to acquire the quantiles and transform chance constraints into deterministic constraints. Therefore, the CCUC model is efficiently solved as a mixed-integer quadratic programming problem. Numerical tests are performed on several systems to illustrate efficiency and scalability of the proposed method.

math.OC↗

arXiv2019

Stochastic Real-time Power Dispatch with Large-scale Wind Power Integration and its Analytical solution

Real-time power dispatch (RTD) can coordinate wind farms, automatic generation control (AGC) units and non AGC units. In RTD, the probable wind power forecast errors (WPFE) should be appropriately formulated to ensure system security with high probability and minimize operational cost. Previous studies and our onsite tests show that Cauchy distribution (CD) effectively fits the leptokurtic feature of small timescale WPFE distributions. In this paper, we propose a chance-constrained real time dispatch (CCRTD) model with the WPFE represented by CD. Since the CD is stable and has promising mathematical characteristics, the proposed CCRTD model can be analytically transformed to a convex optimization problem considering the dependence among wind farms outputs. Moreover, the proposed model incorporates an affine control strategy compatible with AGC systems. This strategy makes the CCRTD adaptively take into account both the additional power ramping requirement and power variation on transmission lines caused by WPFE in RTD stage. Numerical test results show that the proposed method is reliable and effective. Meanwhile it is very efficient and suitable for real-time application.

math.OC↗

arXiv2019

Strong Cosmic Censorship in Charged de Sitter spacetime with Scalar Field Non-minimally Coupled to Curvature

We examine the stability and the strong cosmic censorship in the Reissner-Nordstrom-de Sitter (RN-dS) black hole by investigating the evolution of a scalar field non-minimally coupled to the curvature. We find that when the coupling parameter is negative, the RN-dS black hole experiences instability. The instability disappears when the coupling parameter becomes non-negative. With the increase of the coupling parameter, the violation of the strong cosmic censorship occurs at a larger critical charge ratio. But such an increase of the critical charge is suppressed by the increase of the cosmological constant. Different from the minimal coupling situation, it is possible to accommodate $β\ge1$ in the near extremal black hole when the scalar field is non-minimally coupled to curvature. The increase of the cosmological constant can allow $β\ge1$ to be satisfied for even smaller value of the coupling parameter. The existence of $β\ge1$ implies that the resulting curvature can continuously cross the Cauchy horizon.

gr-qc↗

arXiv2019

Improving Aspect Term Extraction with Bidirectional Dependency Tree Representation

Aspect term extraction is one of the important subtasks in aspect-based sentiment analysis. Previous studies have shown that using dependency tree structure representation is promising for this task. However, most dependency tree structures involve only one directional propagation on the dependency tree. In this paper, we first propose a novel bidirectional dependency tree network to extract dependency structure features from the given sentences. The key idea is to explicitly incorporate both representations gained separately from the bottom-up and top-down propagation on the given dependency syntactic tree. An end-to-end framework is then developed to integrate the embedded representations and BiLSTM plus CRF to learn both tree-structured and sequential features to solve the aspect term extraction problem. Experimental results demonstrate that the proposed model outperforms state-of-the-art baseline models on four benchmark SemEval datasets.

cs.CL↗

arXiv2019

A Holomorphic Embedding Based Continuation Method for Identifying Multiple Power Flow Solutions

In this paper, we propose an efficient continuation method for locating multiple power flow solutions. We adopt the holomorphic embedding technique to represent solution curves as holomorphic functions in the complex plane. The holomorphicity, which provides global information of the curve at any regular point, enables large step sizes in the path-following procedure such that non-singular curve segments can be traversed with very few steps. When approaching singular points, we switch to the traditional predictor-corrector routine to pass through them and switch back afterward to the holomorphic embedding routine. We also propose a warm starter when switching to the predictor-corrector routine, i.e. a large initial step size based on the poles of the Padé approximation of the derived holomorphic function, since these poles reveal the locations of singularities on the curve. Numerical analysis and experiments on many standard IEEE test cases are presented, along with the comparison to the full predictor-corrector routine, confirming the efficiency of the method.

eess.SY↗

arXiv2019

Evolving Deep Neural Networks by Multi-objective Particle Swarm Optimization for Image Classification

In recent years, convolutional neural networks (CNNs) have become deeper in order to achieve better classification accuracy in image classification. However, it is difficult to deploy the state-of-the-art deep CNNs for industrial use due to the difficulty of manually fine-tuning the hyperparameters and the trade-off between classification accuracy and computational cost. This paper proposes a novel multi-objective optimization method for evolving state-of-the-art deep CNNs in real-life applications, which automatically evolves the non-dominant solutions at the Pareto front. Three major contributions are made: Firstly, a new encoding strategy is designed to encode one of the best state-of-the-art CNNs; With the classification accuracy and the number of floating point operations as the two objectives, a multi-objective particle swarm optimization method is developed to evolve the non-dominant solutions; Last but not least, a new infrastructure is designed to boost the experiments by concurrently running the experiments on multiple GPUs across multiple machines, and a Python library is developed and released to manage the infrastructure. The experimental results demonstrate that the non-dominant solutions found by the proposed algorithm form a clear Pareto front, and the proposed infrastructure is able to almost linearly reduce the running time.

cs.NE↗

arXiv2019

Single-photon computational 3D imaging at 45 km

Long-range active imaging has a variety of applications in remote sensing and target recognition. Single-photon LiDAR (light detection and ranging) offers single-photon sensitivity and picosecond timing resolution, which is desirable for high-precision three-dimensional (3D) imaging over long distances. Despite important progress, further extending the imaging range presents enormous challenges because only weak echo photons return and are mixed with strong noise. Herein, we tackled these challenges by constructing a high-efficiency, low-noise confocal single-photon LiDAR system, and developing a long-range-tailored computational algorithm that provides high photon efficiency and super-resolution in the transverse domain. Using this technique, we experimentally demonstrated active single-photon 3D-imaging at a distance of up to 45 km in an urban environment, with a low return-signal level of $\sim$1 photon per pixel. Our system is feasible for imaging at a few hundreds of kilometers by refining the setup, and thus represents a significant milestone towards rapid, low-power, and high-resolution LiDAR over extra-long ranges.

eess.IV↗

arXiv2019

The first constraint from SDSS galaxy-galaxy weak lensing measurements on interacting dark energy models

We combine constraints from linear and nonlinear scales, for the first time, to study the interaction between dark matter and dark energy. We devise a novel N-body simulation pipeline for cosmological models beyond $Λ$CDM. This pipeline is fully self-consistent and opens a new window to study the nonlinear structure formation in general phenomenological interacting dark energy models. By comparing our simulation results with the SDSS galaxy-galaxy weak lensing measurements, we are able to constrain the strength of interaction between dark energy and dark matter. Compared with the previous studies using linear examinations, we point to plausible improvements on the constraints of interaction strength by using small scale information from weak lensing. This improvement is mostly due to the sensitivity of weak lensing measurements on nonlinear structure formation at low redshift. With this new pipeline, it is possible to look for smoking gun signatures of dark matter-dark energy interaction.

astro-ph.CO↗

arXiv2019

Distributional Compatibility for Change of Measures

In this paper, we characterize compatibility of distributions and probability measures on a measurable space. For a set of indices $\mathcal J$, we say that the tuples of probability measures $(Q_i)_{i\in \mathcal J} $ and distributions $(F_i)_{i\in \mathcal J} $ are {compatible} if there exists a random variable having distribution $F_i$ under $Q_i$ for each $i\in \mathcal J$. We first establish an equivalent condition using conditional expectations for general (possibly uncountable) $\mathcal J$. For a finite $n$, it turns out that compatibility of $(Q_1,\dots,Q_n)$ and $(F_1,\dots,F_n)$ depends on the heterogeneity among $Q_1,\dots,Q_n$ compared with that among $F_1,\dots,F_n$. We show that, under an assumption that the measurable space is rich enough, $(Q_1,\dots,Q_n)$ and $(F_1,\dots,F_n)$ are compatible if and only if $(Q_1,\dots,Q_n)$ dominates $(F_1,\dots,F_n)$ in a notion of heterogeneity order, defined via multivariate convex order between the Radon-Nikodym derivatives of $(Q_1,\dots,Q_n)$ and $(F_1,\dots,F_n)$ with respect to some reference measures. We then proceed to generalize our results to stochastic processes, and conclude the paper with an application to portfolio selection problems under multiple constraints.

math.PR↗

arXiv2019

Compatible Matrices of Spearman's Rank Correlation

In this paper, we provide a negative answer to a long-standing open problem on the compatibility of Spearman's rho matrices. Following an equivalence of Spearman's rho matrices and linear correlation matrices for dimensions up to 9 in the literature, we show non-equivalence for dimensions 12 or higher. In particular, we connect this problem with the existence of a random vector under some linear projection restrictions in two characterization results.

math.ST↗

arXiv2019

Strong Cosmic Censorship in higher-dimensional Reissner-Nordström-de Sitter spacetime

It was recently shown that Strong Cosmic Censorship might be violated for near-extremally-charged black holes in 4-dimensional de Sitter space under scalar perturbations. Here, we extend the study of neutral massless scalar perturbations in higher dimensions and discuss the dimensional influence on the validity of Strong Cosmic Censorship hypothesis. By giving an elaborate description of neutral massless scalar perturbations of Reissner-Nordström-de Sitter black holes in $d=4,5$ and $6$ dimensions we conclude that Strong Cosmic Censorship is violated near extremality.

gr-qc↗

arXiv2019

A Hybrid GA-PSO Method for Evolving Architecture and Short Connections of Deep Convolutional Neural Networks

Image classification is a difficult machine learning task, where Convolutional Neural Networks (CNNs) have been applied for over 20 years in order to solve the problem. In recent years, instead of the traditional way of only connecting the current layer with its next layer, shortcut connections have been proposed to connect the current layer with its forward layers apart from its next layer, which has been proved to be able to facilitate the training process of deep CNNs. However, there are various ways to build the shortcut connections, it is hard to manually design the best shortcut connections when solving a particular problem, especially given the design of the network architecture is already very challenging. In this paper, a hybrid evolutionary computation (EC) method is proposed to \textit{automatically} evolve both the architecture of deep CNNs and the shortcut connections. Three major contributions of this work are: Firstly, a new encoding strategy is proposed to encode a CNN, where the architecture and the shortcut connections are encoded separately; Secondly, a hybrid two-level EC method, which combines particle swarm optimisation and genetic algorithms, is developed to search for the optimal CNNs; Lastly, an adjustable learning rate is introduced for the fitness evaluations, which provides a better learning rate for the training process given a fixed number of epochs. The proposed algorithm is evaluated on three widely used benchmark datasets of image classification and compared with 12 peer Non-EC based competitors and one EC based competitor. The experimental results demonstrate that the proposed method outperforms all of the peer competitors in terms of classification accuracy.

cs.CV↗

arXiv2019

Post-Processing of Word Representations via Variance Normalization and Dynamic Embedding

Although embedded vector representations of words offer impressive performance on many natural language processing (NLP) applications, the information of ordered input sequences is lost to some extent if only context-based samples are used in the training. For further performance improvement, two new post-processing techniques, called post-processing via variance normalization (PVN) and post-processing via dynamic embedding (PDE), are proposed in this work. The PVN method normalizes the variance of principal components of word vectors while the PDE method learns orthogonal latent variables from ordered input sequences. The PVN and the PDE methods can be integrated to achieve better performance. We apply these post-processing techniques to two popular word embedding methods (i.e., word2vec and GloVe) to yield their post-processed representations. Extensive experiments are conducted to demonstrate the effectiveness of the proposed post-processing techniques.

cs.CL↗

arXiv2019

Deep Uncertainty Quantification: A Machine Learning Approach for Weather Forecasting

Weather forecasting is usually solved through numerical weather prediction (NWP), which can sometimes lead to unsatisfactory performance due to inappropriate setting of the initial states. In this paper, we design a data-driven method augmented by an effective information fusion mechanism to learn from historical data that incorporates prior knowledge from NWP. We cast the weather forecasting problem as an end-to-end deep learning problem and solve it by proposing a novel negative log-likelihood error (NLE) loss function. A notable advantage of our proposed method is that it simultaneously implements single-value forecasting and uncertainty quantification, which we refer to as deep uncertainty quantification (DUQ). Efficient deep ensemble strategies are also explored to further improve performance. This new approach was evaluated on a public dataset collected from weather stations in Beijing, China. Experimental results demonstrate that the proposed NLE loss significantly improves generalization compared to mean squared error (MSE) loss and mean absolute error (MAE) loss. Compared with NWP, this approach significantly improves accuracy by 47.76%, which is a state-of-the-art result on this benchmark dataset. The preliminary version of the proposed method won 2nd place in an online competition for daily weather forecasting.

cs.LG↗

arXiv2019

Evaluating Word Embedding Models: Methods and Experimental Results

Extensive evaluation on a large number of word embedding models for language processing applications is conducted in this work. First, we introduce popular word embedding models and discuss desired properties of word models and evaluation methods (or evaluators). Then, we categorize evaluators into intrinsic and extrinsic two types. Intrinsic evaluators test the quality of a representation independent of specific natural language processing tasks while extrinsic evaluators use word embeddings as input features to a downstream task and measure changes in performance metrics specific to that task. We report experimental results of intrinsic and extrinsic evaluators on six word embedding models. It is shown that different evaluators focus on different aspects of word models, and some are more correlated with natural language processing tasks. Finally, we adopt correlation analysis to study performance consistency of extrinsic and intrinsic evalutors.

cs.CL↗

arXiv2019

Gravitational wave forms, polarizations, response functions and energy losses of triple systems in Einstein-Aether theory

Gravitationally bound hierarchies containing three or more components are very common in our Universe. In this paper we study {\em periodic} gravitational wave (GW) form, their polarizations, response function, its Fourier transform, and energy loss rate of a triple system through three different channels of radiation, the scalar, vector and tensor modes, in Einstein-aether theory of gravity. In the weak-field approximations and with the recently obtained constraints of the theory, we first analyze the energy loss rate of a binary system, and find that the dipole contributions from the scalar and vector modes could be of the order of ${\cal{O}}\left(c_{14}\right){\cal{O}}\left(G_Nm/d\right)^2$, where $c_{14} \; (\equiv c_{1} + c_{4})$ is constrained to $c_{14} \lesssim {\cal{O}}\left(10^{-5}\right)$ by current observations, where $c_i$'s are the four coupling constants of the theory. On the other hand, the "strong-field" effects for a binary system of neutron stars are about six orders lower than that of GR. So, in this paper we ignore these "strong-field" effects and first develop the general formulas to the lowest post-Newtonian order, by taking the coupling of the aether field with matter into account. Within this approximation, we find that the scalar breather mode and the scalar longitudinal mode are all suppressed by a factor of ${\cal{O}}\left(c_{14}\right)$ with respect to the transverse-traceless modes ($h_{+}$ and $h_{\times}$), while the vectorial modes $(h_{X}$ and $h_{Y}$) are suppressed by a factor of $c_{13} \lesssim {\cal{O}}\left(10^{-15}\right)$. Applying the general formulas to a triple system with periodic orbits, we find that the corresponding GW form, response function, and its Fourier transform depend sensitively on both the configuration of the triple system and their orientations with respect to the detectors.

astro-ph.GA↗

arXiv2019

Strong cosmic censorship for the massless Dirac field in the Reissner-Nordstrom-de Sitter spacetime

We present the Fermi story of strong cosmic censorship in the near-extremal Reissner-Nordstrom-de Sitter black hole. To this end, we first derive from scratch the criterion for the quasi-normal modes of Dirac field to violate strong cosmic censorship in such a background, which turns out to be exactly the same as those for Bose fields, although the involved energy momentum tensor is qualitatively different from that for Bose fields. Then to extract the low-lying quasi-normal modes by Prony method, we apply Crank-Nicolson method to evolve our Dirac field in the double null coordinates. As a result, it shows that for a fixed near-extremal black hole, strong cosmic censorship can be recovered by the $l=\frac{1}{2}$ black hole family mode once the charge of our Dirac field is greater than some critical value, which is increased as one approaches the extremal black hole.

gr-qc↗