October 18, 2019

3293 words 16 mins read

Paper Group ANR 496

Local, algebraic simplifications of Gaussian random fields. IGNOR: Image-guided Neural Object Rendering. One Single Deep Bidirectional LSTM Network for Word Sense Disambiguation of Text Data. Causal Discovery in the Presence of Missing Data. Unlabeled Compression Schemes Exceeding the VC-dimension. Approximate Inference for Multiplicative Latent Fo …

Local, algebraic simplifications of Gaussian random fields


Title	Local, algebraic simplifications of Gaussian random fields
Authors	Theodor Bjorkmo, M. C. David Marsh
Abstract	Many applications of Gaussian random fields and Gaussian random processes are limited by the computational complexity of evaluating the probability density function, which involves inverting the relevant covariance matrix. In this work, we show how that problem can be completely circumvented for the local Taylor coefficients of a Gaussian random field with a Gaussian (or `square exponential') covariance function. Our results hold for any dimension of the field and to any order in the Taylor expansion. We present two applications. First, we show that this method can be used to explicitly generate non-trivial potential energy landscapes with many fields. This application is particularly useful when one is concerned with the field locally around special points (e.g.~maxima or minima), as we exemplify by the problem of cosmic` manyfield’ inflation in the early universe. Second, we show that this method has applications in machine learning, and greatly simplifies the regression problem of determining the hyperparameters of the covariance function given a training data set consisting of local Taylor coefficients at single point. An accompanying Mathematica notebook is available at https://doi.org/10.17863/CAM.22859 .
Tasks
Published	2018-05-08
URL	http://arxiv.org/abs/1805.03117v1
PDF	http://arxiv.org/pdf/1805.03117v1.pdf
PWC	https://paperswithcode.com/paper/local-algebraic-simplifications-of-gaussian
Repo
Framework

IGNOR: Image-guided Neural Object Rendering


Title	IGNOR: Image-guided Neural Object Rendering
Authors	Justus Thies, Michael Zollhöfer, Christian Theobalt, Marc Stamminger, Matthias Nießner
Abstract	We propose a learned image-guided rendering technique that combines the benefits of image-based rendering and GAN-based image synthesis. The goal of our method is to generate photo-realistic re-renderings of reconstructed objects for virtual and augmented reality applications (e.g., virtual showrooms, virtual tours & sightseeing, the digital inspection of historical artifacts). A core component of our work is the handling of view-dependent effects. Specifically, we directly train an object-specific deep neural network to synthesize the view-dependent appearance of an object. As input data we are using an RGB video of the object. This video is used to reconstruct a proxy geometry of the object via multi-view stereo. Based on this 3D proxy, the appearance of a captured view can be warped into a new target view as in classical image-based rendering. This warping assumes diffuse surfaces, in case of view-dependent effects, such as specular highlights, it leads to artifacts. To this end, we propose EffectsNet, a deep neural network that predicts view-dependent effects. Based on these estimations, we are able to convert observed images to diffuse images. These diffuse images can be projected into other views. In the target view, our pipeline reinserts the new view-dependent effects. To composite multiple reprojected images to a final output, we learn a composition network that outputs photo-realistic results. Using this image-guided approach, the network does not have to allocate capacity on ``remembering’’ object appearance, instead it learns how to combine the appearance of captured images. We demonstrate the effectiveness of our approach both qualitatively and quantitatively on synthetic as well as on real data. \|
Tasks	Image Generation, Novel View Synthesis
Published	2018-11-26
URL	https://arxiv.org/abs/1811.10720v2
PDF	https://arxiv.org/pdf/1811.10720v2.pdf
PWC	https://paperswithcode.com/paper/ignor-image-guided-neural-object-rendering
Repo
Framework

One Single Deep Bidirectional LSTM Network for Word Sense Disambiguation of Text Data


Title	One Single Deep Bidirectional LSTM Network for Word Sense Disambiguation of Text Data
Authors	Ahmad Pesaranghader, Ali Pesaranghader, Stan Matwin, Marina Sokolova
Abstract	Due to recent technical and scientific advances, we have a wealth of information hidden in unstructured text data such as offline/online narratives, research articles, and clinical reports. To mine these data properly, attributable to their innate ambiguity, a Word Sense Disambiguation (WSD) algorithm can avoid numbers of difficulties in Natural Language Processing (NLP) pipeline. However, considering a large number of ambiguous words in one language or technical domain, we may encounter limiting constraints for proper deployment of existing WSD models. This paper attempts to address the problem of one-classifier-per-one-word WSD algorithms by proposing a single Bidirectional Long Short-Term Memory (BLSTM) network which by considering senses and context sequences works on all ambiguous words collectively. Evaluated on SensEval-3 benchmark, we show the result of our model is comparable with top-performing WSD algorithms. We also discuss how applying additional modifications alleviates the model fault and the need for more training data.
Tasks	Word Sense Disambiguation
Published	2018-02-25
URL	http://arxiv.org/abs/1802.09059v1
PDF	http://arxiv.org/pdf/1802.09059v1.pdf
PWC	https://paperswithcode.com/paper/one-single-deep-bidirectional-lstm-network
Repo
Framework

Causal Discovery in the Presence of Missing Data


Title	Causal Discovery in the Presence of Missing Data
Authors	Ruibo Tu, Cheng Zhang, Paul Ackermann, Karthika Mohan, Clark Glymour, Hedvig Kjellström, Kun Zhang
Abstract	Missing data are ubiquitous in many domains such as healthcare. When these data entries are not missing completely at random, the (conditional) independence relations in the observed data may be different from those in the complete data generated by the underlying causal process. Consequently, simply applying existing causal discovery methods to the observed data may lead to wrong conclusions. In this paper, we aim at developing a causal discovery method to recover the underlying causal structure from observed data that are missing under different mechanisms, including missing completely at random (MCAR), missing at random (MAR), and missing not at random (MNAR). With missingness mechanisms represented by missingness graphs (m-graphs), we analyze conditions under which additional correction is needed to derive conditional independence/dependence relations in the complete data. Based on our analysis, we propose Missing Value PC (MVPC), which extends the PC algorithm to incorporate additional corrections. Our proposed MVPC is shown in theory to give asymptotically correct results even on data that are MAR or MNAR. Experimental results on both synthetic data and real healthcare applications illustrate that the proposed algorithm is able to find correct causal relations even in the general case of MNAR.
Tasks	Causal Discovery
Published	2018-07-11
URL	http://arxiv.org/abs/1807.04010v3
PDF	http://arxiv.org/pdf/1807.04010v3.pdf
PWC	https://paperswithcode.com/paper/causal-discovery-in-the-presence-of-missing
Repo
Framework

Unlabeled Compression Schemes Exceeding the VC-dimension


Title	Unlabeled Compression Schemes Exceeding the VC-dimension
Authors	Dömötör Pálvölgyi, Gábor Tardos
Abstract	In this note we disprove a conjecture of Kuzmin and Warmuth claiming that every family whose VC-dimension is at most d admits an unlabeled compression scheme to a sample of size at most d. We also study the unlabeled compression schemes of the joins of some families and conjecture that these give a larger gap between the VC-dimension and the size of the smallest unlabeled compression scheme for them.
Tasks
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12471v1
PDF	http://arxiv.org/pdf/1811.12471v1.pdf
PWC	https://paperswithcode.com/paper/unlabeled-compression-schemes-exceeding-the
Repo
Framework

Approximate Inference for Multiplicative Latent Force Models


Title	Approximate Inference for Multiplicative Latent Force Models
Authors	Daniel J. Tait, Bruce J. Worton
Abstract	Latent force models are a class of hybrid models for dynamic systems, combining simple mechanistic models with flexible Gaussian process (GP) perturbations. An extension of this framework to include multiplicative interactions between the state and GP terms allows strong a priori control of the model geometry at the expense of tractable inference. In this paper we consider two methods of carrying out inference within this broader class of models. The first is based on an adaptive gradient matching approximation, and the second is constructed around mixtures of local approximations to the solution. We compare the performance of both methods on simulated data, and also demonstrate an application of the multiplicative latent force model on motion capture data.
Tasks	Motion Capture
Published	2018-12-31
URL	http://arxiv.org/abs/1812.11755v1
PDF	http://arxiv.org/pdf/1812.11755v1.pdf
PWC	https://paperswithcode.com/paper/approximate-inference-for-multiplicative
Repo
Framework

Deeply Supervised Depth Map Super-Resolution as Novel View Synthesis


Title	Deeply Supervised Depth Map Super-Resolution as Novel View Synthesis
Authors	Xibin Song, Yuchao Dai, Xueying Qin
Abstract	Deep convolutional neural network (DCNN) has been successfully applied to depth map super-resolution and outperforms existing methods by a wide margin. However, there still exist two major issues with these DCNN based depth map super-resolution methods that hinder the performance: i) The low-resolution depth maps either need to be up-sampled before feeding into the network or substantial deconvolution has to be used; and ii) The supervision (high-resolution depth maps) is only applied at the end of the network, thus it is difficult to handle large up-sampling factors, such as $\times 8, \times 16$. In this paper, we propose a new framework to tackle the above problems. First, we propose to represent the task of depth map super-resolution as a series of novel view synthesis sub-tasks. The novel view synthesis sub-task aims at generating (synthesizing) a depth map from different camera pose, which could be learned in parallel. Second, to handle large up-sampling factors, we present a deeply supervised network structure to enforce strong supervision in each stage of the network. Third, a multi-scale fusion strategy is proposed to effectively exploit the feature maps at different scales and handle the blocking effect. In this way, our proposed framework could deal with challenging depth map super-resolution efficiently under large up-sampling factors (e.g. $\times 8, \times 16$). Our method only uses the low-resolution depth map as input, and the support of color image is not needed, which greatly reduces the restriction of our method. Extensive experiments on various benchmarking datasets demonstrate the superiority of our method over current state-of-the-art depth map super-resolution methods.
Tasks	Depth Map Super-Resolution, Novel View Synthesis, Super-Resolution
Published	2018-08-27
URL	http://arxiv.org/abs/1808.08688v1
PDF	http://arxiv.org/pdf/1808.08688v1.pdf
PWC	https://paperswithcode.com/paper/deeply-supervised-depth-map-super-resolution
Repo
Framework

Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data


Title	Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data
Authors	Yuanzhi Li, Yingyu Liang
Abstract	Neural networks have many successful applications, while much less theoretical understanding has been gained. Towards bridging this gap, we study the problem of learning a two-layer overparameterized ReLU neural network for multi-class classification via stochastic gradient descent (SGD) from random initialization. In the overparameterized setting, when the data comes from mixtures of well-separated distributions, we prove that SGD learns a network with a small generalization error, albeit the network has enough capacity to fit arbitrary labels. Furthermore, the analysis provides interesting insights into several aspects of learning neural networks and can be verified based on empirical studies on synthetic data and on the MNIST dataset.
Tasks
Published	2018-08-03
URL	https://arxiv.org/abs/1808.01204v3
PDF	https://arxiv.org/pdf/1808.01204v3.pdf
PWC	https://paperswithcode.com/paper/learning-overparameterized-neural-networks
Repo
Framework

Extractive Text Summarization using Neural Networks


Title	Extractive Text Summarization using Neural Networks
Authors	Aakash Sinha, Abhishek Yadav, Akshay Gahlot
Abstract	Text Summarization has been an extensively studied problem. Traditional approaches to text summarization rely heavily on feature engineering. In contrast to this, we propose a fully data-driven approach using feedforward neural networks for single document summarization. We train and evaluate the model on standard DUC 2002 dataset which shows results comparable to the state of the art models. The proposed model is scalable and is able to produce the summary of arbitrarily sized documents by breaking the original document into fixed sized parts and then feeding it recursively to the network.
Tasks	Document Summarization, Feature Engineering, Text Summarization
Published	2018-02-27
URL	http://arxiv.org/abs/1802.10137v1
PDF	http://arxiv.org/pdf/1802.10137v1.pdf
PWC	https://paperswithcode.com/paper/extractive-text-summarization-using-neural
Repo
Framework

Content based Weighted Consensus Summarization


Title	Content based Weighted Consensus Summarization
Authors	Parth Mehta, Prasenjit Majumder
Abstract	Multi-document summarization has received a great deal of attention in the past couple of decades. Several approaches have been proposed, many of which perform equally well and it is becoming in- creasingly difficult to choose one particular system over another. An ensemble of such systems that is able to leverage the strengths of each individual systems can build a better and more robust summary. Despite this, few attempts have been made in this direction. In this paper, we describe a category of ensemble systems which use consensus between the candidate systems to build a better meta-summary. We highlight two major shortcomings of such systems: the inability to take into account relative performance of individual systems and overlooking content of candidate summaries in favour of the sentence rankings. We propose an alternate method, content-based weighted consensus summarization, which address these concerns. We use pseudo-relevant summaries to estimate the performance of individual candidate systems, and then use this information to generate a better aggregate ranking. Experiments on DUC 2003 and DUC 2004 datasets show that the proposed system outperforms existing consensus-based techniques by a large margin.
Tasks	Document Summarization, Multi-Document Summarization
Published	2018-02-03
URL	http://arxiv.org/abs/1802.00946v1
PDF	http://arxiv.org/pdf/1802.00946v1.pdf
PWC	https://paperswithcode.com/paper/content-based-weighted-consensus
Repo
Framework

Robust Accelerated Gradient Methods for Smooth Strongly Convex Functions


Title	Robust Accelerated Gradient Methods for Smooth Strongly Convex Functions
Authors	Necdet Serhat Aybat, Alireza Fallah, Mert Gurbuzbalaban, Asuman Ozdaglar
Abstract	We study the trade-offs between convergence rate and robustness to gradient errors in designing a first-order algorithm. We focus on gradient descent (GD) and accelerated gradient (AG) methods for minimizing strongly convex functions when the gradient has random errors in the form of additive white noise. With gradient errors, the function values of the iterates need not converge to the optimal value; hence, we define the robustness of an algorithm to noise as the asymptotic expected suboptimality of the iterate sequence to input noise power. For this robustness measure, we provide exact expressions for the quadratic case using tools from robust control theory and tight upper bounds for the smooth strongly convex case using Lyapunov functions certified through matrix inequalities. We use these characterizations within an optimization problem which selects parameters of each algorithm to achieve a particular trade-off between rate and robustness. Our results show that AG can achieve acceleration while being more robust to random gradient errors. This behavior is quite different than previously reported in the deterministic gradient noise setting. We also establish some connections between the robustness of an algorithm and how quickly it can converge back to the optimal solution if it is perturbed from the optimal point with deterministic noise. Our framework also leads to practical algorithms that can perform better than other state-of-the-art methods in the presence of random gradient noise.
Tasks
Published	2018-05-27
URL	https://arxiv.org/abs/1805.10579v4
PDF	https://arxiv.org/pdf/1805.10579v4.pdf
PWC	https://paperswithcode.com/paper/robust-accelerated-gradient-methods-for
Repo
Framework

Two-Stream Binocular Network: Accurate Near Field Finger Detection Based On Binocular Images


Title	Two-Stream Binocular Network: Accurate Near Field Finger Detection Based On Binocular Images
Authors	Yi Wei, Guijin Wang, Cairong Zhang, Hengkai Guo, Xinghao Chen, Huazhong Yang
Abstract	Fingertip detection plays an important role in human computer interaction. Previous works transform binocular images into depth images. Then depth-based hand pose estimation methods are used to predict 3D positions of fingertips. Different from previous works, we propose a new framework, named Two-Stream Binocular Network (TSBnet) to detect fingertips from binocular images directly. TSBnet first shares convolutional layers for low level features of right and left images. Then it extracts high level features in two-stream convolutional networks separately. Further, we add a new layer: binocular distance measurement layer to improve performance of our model. To verify our scheme, we build a binocular hand image dataset, containing about 117k pairs of images in training set and 10k pairs of images in test set. Our methods achieve an average error of 10.9mm on our test set, outperforming previous work by 5.9mm (relatively 35.1%).
Tasks	Hand Pose Estimation, Pose Estimation
Published	2018-04-26
URL	http://arxiv.org/abs/1804.10160v1
PDF	http://arxiv.org/pdf/1804.10160v1.pdf
PWC	https://paperswithcode.com/paper/two-stream-binocular-network-accurate-near
Repo
Framework

Fast Point Spread Function Modeling with Deep Learning


Title	Fast Point Spread Function Modeling with Deep Learning
Authors	Jörg Herbel, Tomasz Kacprzak, Adam Amara, Alexandre Refregier, Aurelien Lucchi
Abstract	Modeling the Point Spread Function (PSF) of wide-field surveys is vital for many astrophysical applications and cosmological probes including weak gravitational lensing. The PSF smears the image of any recorded object and therefore needs to be taken into account when inferring properties of galaxies from astronomical images. In the case of cosmic shear, the PSF is one of the dominant sources of systematic errors and must be treated carefully to avoid biases in cosmological parameters. Recently, forward modeling approaches to calibrate shear measurements within the Monte-Carlo Control Loops ($MCCL$) framework have been developed. These methods typically require simulating a large amount of wide-field images, thus, the simulations need to be very fast yet have realistic properties in key features such as the PSF pattern. Hence, such forward modeling approaches require a very flexible PSF model, which is quick to evaluate and whose parameters can be estimated reliably from survey data. We present a PSF model that meets these requirements based on a fast deep-learning method to estimate its free parameters. We demonstrate our approach on publicly available SDSS data. We extract the most important features of the SDSS sample via principal component analysis. Next, we construct our model based on perturbations of a fixed base profile, ensuring that it captures these features. We then train a Convolutional Neural Network to estimate the free parameters of the model from noisy images of the PSF. This allows us to render a model image of each star, which we compare to the SDSS stars to evaluate the performance of our method. We find that our approach is able to accurately reproduce the SDSS PSF at the pixel level, which, due to the speed of both the model evaluation and the parameter estimation, offers good prospects for incorporating our method into the $MCCL$ framework.
Tasks
Published	2018-01-23
URL	http://arxiv.org/abs/1801.07615v2
PDF	http://arxiv.org/pdf/1801.07615v2.pdf
PWC	https://paperswithcode.com/paper/fast-point-spread-function-modeling-with-deep
Repo
Framework

Cross-lingual Short-text Matching with Deep Learning


Title	Cross-lingual Short-text Matching with Deep Learning
Authors	Asmelash Teka Hadgu
Abstract	The problem of short text matching is formulated as follows: given a pair of sentences or questions, a matching model determines whether the input pair mean the same or not. Models that can automatically identify questions with the same meaning have a wide range of applications in question answering sites and modern chatbots. In this article, we describe the approach by team hahu to solve this problem in the context of the “CIKM AnalytiCup 2018 - Cross-lingual Short-text Matching of Question Pairs” that is sponsored by Alibaba. Our solution is an end-to-end system based on current advances in deep learning which avoids heavy feature-engineering and achieves improved performance over traditional machine-learning approaches. The log-loss scores for the first and second rounds of the contest are 0.35 and 0.39 respectively. The team was ranked 7th from 1027 teams in the overall ranking scheme by the organizers that consisted of the two contest scores as well as: innovation and system integrity, understanding data as well as practicality of the solution for business.
Tasks	Feature Engineering, Question Answering, Text Matching
Published	2018-11-13
URL	http://arxiv.org/abs/1811.05569v1
PDF	http://arxiv.org/pdf/1811.05569v1.pdf
PWC	https://paperswithcode.com/paper/cross-lingual-short-text-matching-with-deep
Repo
Framework

Agent Embeddings: A Latent Representation for Pole-Balancing Networks


Title	Agent Embeddings: A Latent Representation for Pole-Balancing Networks
Authors	Oscar Chang, Robert Kwiatkowski, Siyuan Chen, Hod Lipson
Abstract	We show that it is possible to reduce a high-dimensional object like a neural network agent into a low-dimensional vector representation with semantic meaning that we call agent embeddings, akin to word or face embeddings. This can be done by collecting examples of existing networks, vectorizing their weights, and then learning a generative model over the weight space in a supervised fashion. We investigate a pole-balancing task, Cart-Pole, as a case study and show that multiple new pole-balancing networks can be generated from their agent embeddings without direct access to training data from the Cart-Pole simulator. In general, the learned embedding space is helpful for mapping out the space of solutions for a given task. We observe in the case of Cart-Pole the surprising finding that good agents make different decisions despite learning similar representations, whereas bad agents make similar (bad) decisions while learning dissimilar representations. Linearly interpolating between the latent embeddings for a good agent and a bad agent yields an agent embedding that generates a network with intermediate performance, where the performance can be tuned according to the coefficient of interpolation. Linear extrapolation in the latent space also results in performance boosts, up to a point.
Tasks
Published	2018-11-12
URL	http://arxiv.org/abs/1811.04516v4
PDF	http://arxiv.org/pdf/1811.04516v4.pdf
PWC	https://paperswithcode.com/paper/agent-embeddings-a-latent-representation-for
Repo
Framework