arXiv subjects

Wenqi Wang

Publications and source records attributed to Wenqi Wang.

30 records · Page 2Linked to original sources

arXiv2018

Tensor Train Neighborhood Preserving Embedding

In this paper, we propose a Tensor Train Neighborhood Preserving Embedding (TTNPE) to embed multi-dimensional tensor data into low dimensional tensor subspace. Novel approaches to solve the optimization problem in TTNPE are proposed. For this embedding, we evaluate novel trade-off gain among classification, computation, and dimensionality reduction (storage) for supervised learning. It is shown that compared to the state-of-the-arts tensor embedding methods, TTNPE achieves superior trade-off in classification, computation, and dimensionality reduction in MNIST handwritten digits and Weizmann face datasets.

cs.LG↗

arXiv2018

Topic Compositional Neural Language Model

We propose a Topic Compositional Neural Language Model (TCNLM), a novel method designed to simultaneously capture both the global semantic meaning and the local word ordering structure in a document. The TCNLM learns the global semantic coherence of a document via a neural topic model, and the probability of each learned latent topic is further used to build a Mixture-of-Experts (MoE) language model, where each expert (corresponding to one topic) is a recurrent neural network (RNN) that accounts for learning the local structure of a word sequence. In order to train the MoE model efficiently, a matrix factorization method is applied, by extending each weight matrix of the RNN to be an ensemble of topic-dependent weight matrices. The degree to which each member of the ensemble is used is tied to the document-dependent probability of the corresponding topics. Experimental results on several corpora show that the proposed approach outperforms both a pure RNN-based model and other topic-guided language models. Further, our model yields sensible topics, and also has the capacity to generate meaningful sentences conditioned on given topics.

cs.LG↗

arXiv2018

Wide Compression: Tensor Ring Nets

Deep neural networks have demonstrated state-of-the-art performance in a variety of real-world applications. In order to obtain performance gains, these networks have grown larger and deeper, containing millions or even billions of parameters and over a thousand layers. The trade-off is that these large architectures require an enormous amount of memory, storage, and computation, thus limiting their usability. Inspired by the recent tensor ring factorization, we introduce Tensor Ring Networks (TR-Nets), which significantly compress both the fully connected layers and the convolutional layers of deep neural networks. Our results show that our TR-Nets approach {is able to compress LeNet-5 by $11\times$ without losing accuracy}, and can compress the state-of-the-art Wide ResNet by $243\times$ with only 2.3\% degradation in {Cifar10 image classification}. Overall, this compression scheme shows promise in scientific computing and deep learning, especially for emerging resource-constrained devices such as smartphones, wearables, and IoT devices.

cs.LG↗

arXiv2017

Efficient Low Rank Tensor Ring Completion

Using the matrix product state (MPS) representation of the recently proposed tensor ring decompositions, in this paper we propose a tensor completion algorithm, which is an alternating minimization algorithm that alternates over the factors in the MPS representation. This development is motivated in part by the success of matrix completion algorithms that alternate over the (low-rank) factors. In this paper, we propose a spectral initialization for the tensor ring completion algorithm and analyze the computational complexity of the proposed algorithm. We numerically compare it with existing methods that employ a low rank tensor train approximation for data completion and show that our method outperforms the existing ones for a variety of real computer vision settings, and thus demonstrate the improved expressive power of tensor ring as compared to tensor train.

cs.LG↗

arXiv2016

Earliness-Aware Deep Convolutional Networks for Early Time Series Classification

We present Earliness-Aware Deep Convolutional Networks (EA-ConvNets), an end-to-end deep learning framework, for early classification of time series data. Unlike most existing methods for early classification of time series data, that are designed to solve this problem under the assumption of the availability of a good set of pre-defined (often hand-crafted) features, our framework can jointly perform feature learning (by learning a deep hierarchy of \emph{shapelets} capturing the salient characteristics in each time series), along with a dynamic truncation model to help our deep feature learning architecture focus on the early parts of each time series. Consequently, our framework is able to make highly reliable early predictions, outperforming various state-of-the-art methods for early time series classification, while also being competitive when compared to the state-of-the-art time series classification algorithms that work with \emph{fully observed} time series data. To the best of our knowledge, the proposed framework is the first to perform data-driven (deep) feature learning in the context of early classification of time series data. We perform a comprehensive set of experiments, on several benchmark data sets, which demonstrate that our method yields significantly better predictions than various state-of-the-art methods designed for early time series classification. In addition to obtaining high accuracies, our experiments also show that the learned deep shapelets based features are also highly interpretable and can help gain better understanding of the underlying characteristics of time series data.

cs.LG↗

arXiv2016

Unsupervised clustering under the Union of Polyhedral Cones (UOPC) model

In this paper, we consider clustering data that is assumed to come from one of finitely many pointed convex polyhedral cones. This model is referred to as the Union of Polyhedral Cones (UOPC) model. Similar to the Union of Subspaces (UOS) model where each data from each subspace is generated from a (unknown) basis, in the UOPC model each data from each cone is assumed to be generated from a finite number of (unknown) \emph{extreme rays}.To cluster data under this model, we consider several algorithms - (a) Sparse Subspace Clustering by Non-negative constraints Lasso (NCL), (b) Least squares approximation (LSA), and (c) K-nearest neighbor (KNN) algorithm to arrive at affinity between data points. Spectral Clustering (SC) is then applied on the resulting affinity matrix to cluster data into different polyhedral cones. We show that on an average KNN outperforms both NCL and LSA and for this algorithm we provide the deterministic conditions for correct clustering. For an affinity measure between the cones it is shown that as long as the cones are not very coherent and as long as the density of data within each cone exceeds a threshold, KNN leads to accurate clustering. Finally, simulation results on real datasets (MNIST and YaleFace datasets) depict that the proposed algorithm works well on real data indicating the utility of the UOPC model and the proposed algorithm.

stat.ML↗

arXiv2016

Tensor Completion by Alternating Minimization under the Tensor Train (TT) Model

Using the matrix product state (MPS) representation of tensor train decompositions, in this paper we propose a tensor completion algorithm which alternates over the matrices (tensors) in the MPS representation. This development is motivated in part by the success of matrix completion algorithms which alternate over the (low-rank) factors. We comment on the computational complexity of the proposed algorithm and numerically compare it with existing methods employing low rank tensor train approximation for data completion as well as several other recently proposed methods. We show that our method is superior to existing ones for a variety of real settings.

math.NA↗

arXiv2016

Acoustic Holographic Rendering with Two-dimensional Metamaterial-based Passive Phased Array

Acoustic holographic rendering in complete analogy with optical holography are useful for various applications, ranging from multi-focal lensing, multiplexed sensing and synthesizing three-dimensional complex sound fields. Conventional approaches rely on a large number of active transducers and phase shifting circuits. In this paper we show that by using passive metamaterials as subwavelength pixels, holographic rendering can be achieved without cumbersome circuitry and with only a single transducer, thus significantly reducing system complexity. Such metamaterial-based holograms can serve as versatile platforms for various advanced acoustic wave manipulation and signal modulation, leading to new possibilities in acoustic sensing, energy deposition and medical diagnostic imaging.

cond-mat.mtrl-sci↗

arXiv2016

On Deterministic Conditions for Subspace Clustering under Missing Data

In this paper we present deterministic conditions for success of sparse subspace clustering (SSC) under missing data, when data is assumed to come from a Union of Subspaces (UoS) model. We consider two algorithms, which are variants of SSC with entry-wise zero-filling that differ in terms of the optimization problems used to find affinity matrix for spectral clustering. For both the algorithms, we provide deterministic conditions for any pattern of missing data such that perfect clustering can be achieved. We provide extensive sets of simulation results for clustering as well as completion of data at missing entries, under the UoS model. Our experimental results indicate that in contrast to the full data case, accurate clustering does not imply accurate subspace identification and completion, indicating the natural order of relative hardness of these problems.

cs.IT↗

arXiv2016

On deterministic conditions for subspace clustering under missing data

In this paper we present deterministic analysis of sufficient conditions for sparse subspace clustering under missing data, when data is assumed to come from a Union of Subspaces (UoS) model. In this context we consider two cases, namely Case I when all the points are sampled at the same co-ordinates, and Case II when points are sampled at different locations. We show that results for Case I directly follow from several existing results in the literature, while results for Case II are not as straightforward and we provide a set of dual conditions under which, perfect clustering holds true. We provide extensive set of simulation results for clustering as well as completion of data under missing entries, under the UoS model. Our experimental results indicate that in contrast to the full data case, accurate clustering does not imply accurate subspace identification and completion, indicating the natural order of relative hardness of these problems.

cs.IT↗

arXiv2015

Broad-band acoustic hyperbolic metamaterial

Acoustic metamaterials (AMMs) are engineered materials, made from subwavelength structures, that exhibit useful or unusual constitutive properties. There has been intense research interest in AMMs since its first realization in 2000 by Liu et al. A number of functionalities and applications have been proposed and achieved using AMMs. Hyperbolic metamaterials are one of the most important types of metamaterials due to their extreme anisotropy and numerous possible applications, including negative refraction, backward waves, spatial filtering, and subwavelength imaging. Although the importance of acoustic hyperbolic metamaterials (AHMMs) as a tool for achieving full control of acoustic waves is substantial, the realization of a broad-band and truly hyperbolic AMM has not been reported so far. Here, we demonstrate the design and experimental characterization of a broadband AHMM that operates between 1.0 kHz and 2.5 kHz.

physics.class-ph↗

arXiv2014

Wavefront Modulation and Subwavelength Diffractive Acoustics with an Acoustic Metasurface

Metasurfaces are a family of novel wavefront shaping devices with planar profile and subwavelength thickness. Acoustic metasurfaces with ultralow profile yet extraordinary wave manipulating properties would be highly desirable for improving the performance of many acoustic wave-based applications. However, designing acoustic metasurfaces with similar functionality as their electromagnetic counterparts remains challenging with traditional metamaterial design approaches. Here we present a design and realization of an acoustic metasurface based on tapered labyrinthine metamaterials. The demonstrated metasurface can not only can steer an acoustic beam as expected from the generalized Snell s law, but also exhibits various unique properties including surface wave conversion, extraordinary beam-steering and apparent negative refraction through higher-order diffraction. Such designer acoustic metasurfaces provide a new design methodology for acoustic signal modulation devices and may be useful for applications such as beam-steering, surface wave manipulation, high efficiency sound absorption, acoustic imaging and ultrasound lens design.

cond-mat.mtrl-sci↗