May 5, 2019

2958 words 14 mins read

Paper Group ANR 514

Learning Preferences for Manipulation Tasks from Online Coactive Feedback. Causal Discovery from Subsampled Time Series Data by Constraint Optimization. Learning in Implicit Generative Models. Reordering rules for English-Hindi SMT. Correspondence Insertion for As-Projective-As-Possible Image Stitching. Hankel Matrix Nuclear Norm Regularized Tensor …

Learning Preferences for Manipulation Tasks from Online Coactive Feedback


Title	Learning Preferences for Manipulation Tasks from Online Coactive Feedback
Authors	Ashesh Jain, Shikhar Sharma, Thorsten Joachims, Ashutosh Saxena
Abstract	We consider the problem of learning preferences over trajectories for mobile manipulators such as personal robots and assembly line robots. The preferences we learn are more intricate than simple geometric constraints on trajectories; they are rather governed by the surrounding context of various objects and human interactions in the environment. We propose a coactive online learning framework for teaching preferences in contextually rich environments. The key novelty of our approach lies in the type of feedback expected from the user: the human user does not need to demonstrate optimal trajectories as training data, but merely needs to iteratively provide trajectories that slightly improve over the trajectory currently proposed by the system. We argue that this coactive preference feedback can be more easily elicited than demonstrations of optimal trajectories. Nevertheless, theoretical regret bounds of our algorithm match the asymptotic rates of optimal trajectory algorithms. We implement our algorithm on two high degree-of-freedom robots, PR2 and Baxter, and present three intuitive mechanisms for providing such incremental feedback. In our experimental evaluation we consider two context rich settings – household chores and grocery store checkout – and show that users are able to train the robot with just a few feedbacks (taking only a few minutes).\footnote{Parts of this work has been published at NIPS and ISRR conferences~\citep{Jain13,Jain13b}. This journal submission presents a consistent full paper, and also includes the proof of regret bounds, more details of the robotic system, and a thorough related work.}
Tasks
Published	2016-01-05
URL	http://arxiv.org/abs/1601.00741v1
PDF	http://arxiv.org/pdf/1601.00741v1.pdf
PWC	https://paperswithcode.com/paper/learning-preferences-for-manipulation-tasks
Repo
Framework

Causal Discovery from Subsampled Time Series Data by Constraint Optimization


Title	Causal Discovery from Subsampled Time Series Data by Constraint Optimization
Authors	Antti Hyttinen, Sergey Plis, Matti Järvisalo, Frederick Eberhardt, David Danks
Abstract	This paper focuses on causal structure estimation from time series data in which measurements are obtained at a coarser timescale than the causal timescale of the underlying system. Previous work has shown that such subsampling can lead to significant errors about the system’s causal structure if not properly taken into account. In this paper, we first consider the search for the system timescale causal structures that correspond to a given measurement timescale structure. We provide a constraint satisfaction procedure whose computational performance is several orders of magnitude better than previous approaches. We then consider finite-sample data as input, and propose the first constraint optimization approach for recovering the system timescale causal structure. This algorithm optimally recovers from possible conflicts due to statistical errors. More generally, these advances allow for a robust and non-parametric estimation of system timescale causal structures from subsampled time series data.
Tasks	Causal Discovery, Time Series
Published	2016-02-25
URL	http://arxiv.org/abs/1602.07970v2
PDF	http://arxiv.org/pdf/1602.07970v2.pdf
PWC	https://paperswithcode.com/paper/causal-discovery-from-subsampled-time-series
Repo
Framework

Learning in Implicit Generative Models


Title	Learning in Implicit Generative Models
Authors	Shakir Mohamed, Balaji Lakshminarayanan
Abstract	Generative adversarial networks (GANs) provide an algorithmic framework for constructing generative models with several appealing properties: they do not require a likelihood function to be specified, only a generating procedure; they provide samples that are sharp and compelling; and they allow us to harness our knowledge of building highly accurate neural network classifiers. Here, we develop our understanding of GANs with the aim of forming a rich view of this growing area of machine learning—to build connections to the diverse set of statistical thinking on this topic, of which much can be gained by a mutual exchange of ideas. We frame GANs within the wider landscape of algorithms for learning in implicit generative models–models that only specify a stochastic procedure with which to generate data–and relate these ideas to modelling problems in related fields, such as econometrics and approximate Bayesian computation. We develop likelihood-free inference methods and highlight hypothesis testing as a principle for learning in implicit generative models, using which we are able to derive the objective function used by GANs, and many other related objectives. The testing viewpoint directs our focus to the general problem of density ratio estimation. There are four approaches for density ratio estimation, one of which is a solution using classifiers to distinguish real from generated data. Other approaches such as divergence minimisation and moment matching have also been explored in the GAN literature, and we synthesise these views to form an understanding in terms of the relationships between them and the wider literature, highlighting avenues for future exploration and cross-pollination.
Tasks
Published	2016-10-11
URL	http://arxiv.org/abs/1610.03483v4
PDF	http://arxiv.org/pdf/1610.03483v4.pdf
PWC	https://paperswithcode.com/paper/learning-in-implicit-generative-models
Repo
Framework

Reordering rules for English-Hindi SMT


Title	Reordering rules for English-Hindi SMT
Authors	Raj Nath Patel, Rohit Gupta, Prakash B. Pimpale, Sasikumar M
Abstract	Reordering is a preprocessing stage for Statistical Machine Translation (SMT) system where the words of the source sentence are reordered as per the syntax of the target language. We are proposing a rich set of rules for better reordering. The idea is to facilitate the training process by better alignments and parallel phrase extraction for a phrase-based SMT system. Reordering also helps the decoding process and hence improving the machine translation quality. We have observed significant improvements in the translation quality by using our approach over the baseline SMT. We have used BLEU, NIST, multi-reference word error rate, multi-reference position independent error rate for judging the improvements. We have exploited open source SMT toolkit MOSES to develop the system.
Tasks	Machine Translation
Published	2016-10-24
URL	http://arxiv.org/abs/1610.07420v1
PDF	http://arxiv.org/pdf/1610.07420v1.pdf
PWC	https://paperswithcode.com/paper/reordering-rules-for-english-hindi-smt
Repo
Framework

Correspondence Insertion for As-Projective-As-Possible Image Stitching


Title	Correspondence Insertion for As-Projective-As-Possible Image Stitching
Authors	William X. Liu, Tat-Jun Chin
Abstract	Spatially varying warps are increasingly popular for image alignment. In particular, as-projective-as-possible (APAP) warps have been proven effective for accurate panoramic stitching, especially in cases with significant depth parallax that defeat standard homographic warps. However, estimating spatially varying warps requires a sufficient number of feature matches. In image regions where feature detection or matching fail, the warp loses guidance and is unable to accurately model the true underlying warp, thus resulting in poor registration. In this paper, we propose a correspondence insertion method for APAP warps, with a focus on panoramic stitching. Our method automatically identifies misaligned regions, and inserts appropriate point correspondences to increase the flexibility of the warp and improve alignment. Unlike other warp varieties, the underlying projective regularization of APAP warps reduces overfitting and geometric distortion, despite increases to the warp complexity. Comparisons with recent techniques for parallax-tolerant image stitching demonstrate the effectiveness and simplicity of our approach.
Tasks	Image Stitching
Published	2016-08-29
URL	http://arxiv.org/abs/1608.07997v1
PDF	http://arxiv.org/pdf/1608.07997v1.pdf
PWC	https://paperswithcode.com/paper/correspondence-insertion-for-as-projective-as
Repo
Framework

Hankel Matrix Nuclear Norm Regularized Tensor Completion for $N$-dimensional Exponential Signals


Title	Hankel Matrix Nuclear Norm Regularized Tensor Completion for $N$-dimensional Exponential Signals
Authors	Jiaxi Ying, Hengfa Lu, Qingtao Wei, Jian-Feng Cai, Di Guo, Jihui Wu, Zhong Chen, Xiaobo Qu
Abstract	Signals are generally modeled as a superposition of exponential functions in spectroscopy of chemistry, biology and medical imaging. For fast data acquisition or other inevitable reasons, however, only a small amount of samples may be acquired and thus how to recover the full signal becomes an active research topic. But existing approaches can not efficiently recover $N$-dimensional exponential signals with $N\geq 3$. In this paper, we study the problem of recovering N-dimensional (particularly $N\geq 3$) exponential signals from partial observations, and formulate this problem as a low-rank tensor completion problem with exponential factor vectors. The full signal is reconstructed by simultaneously exploiting the CANDECOMP/PARAFAC structure and the exponential structure of the associated factor vectors. The latter is promoted by minimizing an objective function involving the nuclear norm of Hankel matrices. Experimental results on simulated and real magnetic resonance spectroscopy data show that the proposed approach can successfully recover full signals from very limited samples and is robust to the estimated tensor rank.
Tasks
Published	2016-04-06
URL	http://arxiv.org/abs/1604.02100v2
PDF	http://arxiv.org/pdf/1604.02100v2.pdf
PWC	https://paperswithcode.com/paper/hankel-matrix-nuclear-norm-regularized-tensor
Repo
Framework

Using Neural Networks to Compute Approximate and Guaranteed Feasible Hamilton-Jacobi-Bellman PDE Solutions


Title	Using Neural Networks to Compute Approximate and Guaranteed Feasible Hamilton-Jacobi-Bellman PDE Solutions
Authors	Frank Jiang, Glen Chou, Mo Chen, Claire J. Tomlin
Abstract	To sidestep the curse of dimensionality when computing solutions to Hamilton-Jacobi-Bellman partial differential equations (HJB PDE), we propose an algorithm that leverages a neural network to approximate the value function. We show that our final approximation of the value function generates near optimal controls which are guaranteed to successfully drive the system to a target state. Our framework is not dependent on state space discretization, leading to a significant reduction in computation time and space complexity in comparison with dynamic programming-based approaches. Using this grid-free approach also enables us to plan over longer time horizons with relatively little additional computation overhead. Unlike many previous neural network HJB PDE approximating formulations, our approximation is strictly conservative and hence any trajectories we generate will be strictly feasible. For demonstration, we specialize our new general framework to the Dubins car model and discuss how the framework can be applied to other models with higher-dimensional state spaces.
Tasks
Published	2016-11-10
URL	http://arxiv.org/abs/1611.03158v2
PDF	http://arxiv.org/pdf/1611.03158v2.pdf
PWC	https://paperswithcode.com/paper/using-neural-networks-to-compute-approximate
Repo
Framework

Complex Networks of Words in Fables


Title	Complex Networks of Words in Fables
Authors	Yurij Holovatch, Vasyl Palchykov
Abstract	In this chapter we give an overview of the application of complex network theory to quantify some properties of language. Our study is based on two fables in Ukrainian, Mykyta the Fox and Abu-Kasym’s slippers. It consists of two parts: the analysis of frequency-rank distributions of words and the application of complex-network theory. The first part shows that the text sizes are sufficiently large to observe statistical properties. This supports their selection for the analysis of typical properties of the language networks in the second part of the chapter. In describing language as a complex network, while words are usually associated with nodes, there is more variability in the choice of links and different representations result in different networks. Here, we examine a number of such representations of the language network and perform a comparative analysis of their characteristics. Our results suggest that, irrespective of link representation, the Ukrainian language network used in the selected fables is a strongly correlated, scale-free, small world. We discuss how such empirical approaches may help form a useful basis for a theoretical description of language evolution and how they may be used in analyses of other textual narratives.
Tasks
Published	2016-02-04
URL	http://arxiv.org/abs/1602.04853v1
PDF	http://arxiv.org/pdf/1602.04853v1.pdf
PWC	https://paperswithcode.com/paper/complex-networks-of-words-in-fables
Repo
Framework

Combining Maps and Street Level Images for Building Height and Facade Estimation


Title	Combining Maps and Street Level Images for Building Height and Facade Estimation
Authors	Jiangye Yuan, Anil M. Cheriyadat
Abstract	We propose a method that integrates two widely available data sources, building footprints from 2D maps and street level images, to derive valuable information that is generally difficult to acquire – building heights and building facade masks in images. Building footprints are elevated in world coordinates and projected onto images. Building heights are estimated by scoring projected footprints based on their alignment with building features in images. Building footprints with estimated heights can be converted to simple 3D building models, which are projected back to images to identify buildings. In this procedure, accurate camera projections are critical. However, camera position errors inherited from external sensors commonly exist, which adversely affect results. We derive a solution to precisely locate cameras on maps using correspondence between image features and building footprints. Experiments on real-world datasets show the promise of our method.
Tasks
Published	2016-01-28
URL	http://arxiv.org/abs/1601.07630v2
PDF	http://arxiv.org/pdf/1601.07630v2.pdf
PWC	https://paperswithcode.com/paper/combining-maps-and-street-level-images-for
Repo
Framework

Exploring Prediction Uncertainty in Machine Translation Quality Estimation


Title	Exploring Prediction Uncertainty in Machine Translation Quality Estimation
Authors	Daniel Beck, Lucia Specia, Trevor Cohn
Abstract	Machine Translation Quality Estimation is a notoriously difficult task, which lessens its usefulness in real-world translation environments. Such scenarios can be improved if quality predictions are accompanied by a measure of uncertainty. However, models in this task are traditionally evaluated only in terms of point estimate metrics, which do not take prediction uncertainty into account. We investigate probabilistic methods for Quality Estimation that can provide well-calibrated uncertainty estimates and evaluate them in terms of their full posterior predictive distributions. We also show how this posterior information can be useful in an asymmetric risk scenario, which aims to capture typical situations in translation workflows.
Tasks	Machine Translation
Published	2016-06-30
URL	http://arxiv.org/abs/1606.09600v1
PDF	http://arxiv.org/pdf/1606.09600v1.pdf
PWC	https://paperswithcode.com/paper/exploring-prediction-uncertainty-in-machine
Repo
Framework

Multiview Cauchy Estimator Feature Embedding for Depth and Inertial Sensor-Based Human Action Recognition


Title	Multiview Cauchy Estimator Feature Embedding for Depth and Inertial Sensor-Based Human Action Recognition
Authors	Yanan Guo, Lei Li, Weifeng Liu, Jun Cheng, Dapeng Tao
Abstract	The ever-growing popularity of Kinect and inertial sensors has prompted intensive research efforts on human action recognition. Since human actions can be characterized by multiple feature representations extracted from Kinect and inertial sensors, multiview features must be encoded into a unified space optimal for human action recognition. In this paper, we propose a new unsupervised feature fusion method termed Multiview Cauchy Estimator Feature Embedding (MCEFE) for human action recognition. By minimizing empirical risk, MCEFE integrates the encoded complementary information in multiple views to find the unified data representation and the projection matrices. To enhance robustness to outliers, the Cauchy estimator is imposed on the reconstruction error. Furthermore, ensemble manifold regularization is enforced on the projection matrices to encode the correlations between different views and avoid overfitting. Experiments are conducted on the new Chinese Academy of Sciences - Yunnan University - Multimodal Human Action Database (CAS-YNU-MHAD) to demonstrate the effectiveness and robustness of MCEFE for human action recognition.
Tasks	Temporal Action Localization
Published	2016-08-07
URL	http://arxiv.org/abs/1608.02183v2
PDF	http://arxiv.org/pdf/1608.02183v2.pdf
PWC	https://paperswithcode.com/paper/multiview-cauchy-estimator-feature-embedding
Repo
Framework

Provably Good Early Detection of Diseases using Non-Sparse Covariance-Regularized Linear Discriminant Analysis


Title	Provably Good Early Detection of Diseases using Non-Sparse Covariance-Regularized Linear Discriminant Analysis
Authors	Haoyi Xiong, Yanjie Fu, Wenqing Hu, Guanling Chen, Laura E. Barnes
Abstract	To improve the performance of Linear Discriminant Analysis (LDA) for early detection of diseases using Electronic Health Records (EHR) data, we propose \TheName{} – a novel framework for \emph{\underline{E}HR based \underline{E}arly \underline{D}etection of \underline{D}iseases} on top of \emph{Covariance-Regularized} LDA models. Specifically, \TheName\ employs a \emph{non-sparse} inverse covariance matrix (or namely precision matrix) estimator derived from graphical lasso and incorporates the estimator into LDA classifiers to improve classification accuracy. Theoretical analysis on \TheName\ shows that it can bound the expected error rate of LDA classification, under certain assumptions. Finally, we conducted extensive experiments using a large-scale real-world EHR dataset – CHSN. We compared our solution with other regularized LDA and downstream classifiers. The result shows \TheName\ outperforms all baselines and backups our theoretical analysis.
Tasks
Published	2016-10-18
URL	http://arxiv.org/abs/1610.05446v2
PDF	http://arxiv.org/pdf/1610.05446v2.pdf
PWC	https://paperswithcode.com/paper/provably-good-early-detection-of-diseases
Repo
Framework

Partition Functions from Rao-Blackwellized Tempered Sampling


Title	Partition Functions from Rao-Blackwellized Tempered Sampling
Authors	David Carlson, Patrick Stinson, Ari Pakman, Liam Paninski
Abstract	Partition functions of probability distributions are important quantities for model evaluation and comparisons. We present a new method to compute partition functions of complex and multimodal distributions. Such distributions are often sampled using simulated tempering, which augments the target space with an auxiliary inverse temperature variable. Our method exploits the multinomial probability law of the inverse temperatures, and provides estimates of the partition function in terms of a simple quotient of Rao-Blackwellized marginal inverse temperature probability estimates, which are updated while sampling. We show that the method has interesting connections with several alternative popular methods, and offers some significant advantages. In particular, we empirically find that the new method provides more accurate estimates than Annealed Importance Sampling when calculating partition functions of large Restricted Boltzmann Machines (RBM); moreover, the method is sufficiently accurate to track training and validation log-likelihoods during learning of RBMs, at minimal computational cost.
Tasks
Published	2016-03-07
URL	http://arxiv.org/abs/1603.01912v3
PDF	http://arxiv.org/pdf/1603.01912v3.pdf
PWC	https://paperswithcode.com/paper/partition-functions-from-rao-blackwellized
Repo
Framework

Exploiting Deep Semantics and Compositionality of Natural Language for Human-Robot-Interaction


Title	Exploiting Deep Semantics and Compositionality of Natural Language for Human-Robot-Interaction
Authors	Manfred Eppe, Sean Trott, Jerome Feldman
Abstract	We develop a natural language interface for human robot interaction that implements reasoning about deep semantics in natural language. To realize the required deep analysis, we employ methods from cognitive linguistics, namely the modular and compositional framework of Embodied Construction Grammar (ECG) [Feldman, 2009]. Using ECG, robots are able to solve fine-grained reference resolution problems and other issues related to deep semantics and compositionality of natural language. This also includes verbal interaction with humans to clarify commands and queries that are too ambiguous to be executed safely. We implement our NLU framework as a ROS package and present proof-of-concept scenarios with different robots, as well as a survey on the state of the art.
Tasks
Published	2016-04-22
URL	http://arxiv.org/abs/1604.06721v1
PDF	http://arxiv.org/pdf/1604.06721v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-deep-semantics-and
Repo
Framework

Reconstructing Articulated Rigged Models from RGB-D Videos


Title	Reconstructing Articulated Rigged Models from RGB-D Videos
Authors	Dimitrios Tzionas, Juergen Gall
Abstract	Although commercial and open-source software exist to reconstruct a static object from a sequence recorded with an RGB-D sensor, there is a lack of tools that build rigged models of articulated objects that deform realistically and can be used for tracking or animation. In this work, we fill this gap and propose a method that creates a fully rigged model of an articulated object from depth data of a single sensor. To this end, we combine deformable mesh tracking, motion segmentation based on spectral clustering and skeletonization based on mean curvature flow. The fully rigged model then consists of a watertight mesh, embedded skeleton, and skinning weights.
Tasks	Motion Segmentation
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01371v2
PDF	http://arxiv.org/pdf/1609.01371v2.pdf
PWC	https://paperswithcode.com/paper/reconstructing-articulated-rigged-models-from
Repo
Framework