July 27, 2019

2948 words 14 mins read

Paper Group ANR 745

Regret Analysis for Continuous Dueling Bandit. Bandits with Movement Costs and Adaptive Pricing. Improving Content-Invariance in Gated Autoencoders for 2D and 3D Object Rotation. Diversification-Based Learning in Computing and Optimization. Deep Reinforcement Learning for High Precision Assembly Tasks. Discriminant Projection Representation-based C …

Regret Analysis for Continuous Dueling Bandit


Title	Regret Analysis for Continuous Dueling Bandit
Authors	Wataru Kumagai
Abstract	The dueling bandit is a learning framework wherein the feedback information in the learning process is restricted to a noisy comparison between a pair of actions. In this research, we address a dueling bandit problem based on a cost function over a continuous space. We propose a stochastic mirror descent algorithm and show that the algorithm achieves an $O(\sqrt{T\log T})$-regret bound under strong convexity and smoothness assumptions for the cost function. Subsequently, we clarify the equivalence between regret minimization in dueling bandit and convex optimization for the cost function. Moreover, when considering a lower bound in convex optimization, our algorithm is shown to achieve the optimal convergence rate in convex optimization and the optimal regret in dueling bandit except for a logarithmic factor.
Tasks
Published	2017-11-21
URL	http://arxiv.org/abs/1711.07693v2
PDF	http://arxiv.org/pdf/1711.07693v2.pdf
PWC	https://paperswithcode.com/paper/regret-analysis-for-continuous-dueling-bandit
Repo
Framework

Bandits with Movement Costs and Adaptive Pricing


Title	Bandits with Movement Costs and Adaptive Pricing
Authors	Tomer Koren, Roi Livni, Yishay Mansour
Abstract	We extend the model of Multi-armed Bandit with unit switching cost to incorporate a metric between the actions. We consider the case where the metric over the actions can be modeled by a complete binary tree, and the distance between two leaves is the size of the subtree of their least common ancestor, which abstracts the case that the actions are points on the continuous interval $[0,1]$ and the switching cost is their distance. In this setting, we give a new algorithm that establishes a regret of $\widetilde{O}(\sqrt{kT} + T/k)$, where $k$ is the number of actions and $T$ is the time horizon. When the set of actions corresponds to whole $[0,1]$ interval we can exploit our method for the task of bandit learning with Lipschitz loss functions, where our algorithm achieves an optimal regret rate of $\widetilde{\Theta}(T^{2/3})$, which is the same rate one obtains when there is no penalty for movements. As our main application, we use our new algorithm to solve an adaptive pricing problem. Specifically, we consider the case of a single seller faced with a stream of patient buyers. Each buyer has a private value and a window of time in which they are interested in buying, and they buy at the lowest price in the window, if it is below their value. We show that with an appropriate discretization of the prices, the seller can achieve a regret of $\widetilde{O}(T^{2/3})$ compared to the best fixed price in hindsight, which outperform the previous regret bound of $\widetilde{O}(T^{3/4})$ for the problem.
Tasks
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07444v1
PDF	http://arxiv.org/pdf/1702.07444v1.pdf
PWC	https://paperswithcode.com/paper/bandits-with-movement-costs-and-adaptive
Repo
Framework

Improving Content-Invariance in Gated Autoencoders for 2D and 3D Object Rotation


Title	Improving Content-Invariance in Gated Autoencoders for 2D and 3D Object Rotation
Authors	Stefan Lattner, Maarten Grachten
Abstract	Content-invariance in mapping codes learned by GAEs is a useful feature for various relation learning tasks. In this paper we show that the content-invariance of mapping codes for images of 2D and 3D rotated objects can be substantially improved by extending the standard GAE loss (symmetric reconstruction error) with a regularization term that penalizes the symmetric cross-reconstruction error. This error term involves reconstruction of pairs with mapping codes obtained from other pairs exhibiting similar transformations. Although this would principally require knowledge of the transformations exhibited by training pairs, our experiments show that a bootstrapping approach can sidestep this issue, and that the regularization term can effectively be used in an unsupervised setting.
Tasks
Published	2017-07-05
URL	http://arxiv.org/abs/1707.01357v1
PDF	http://arxiv.org/pdf/1707.01357v1.pdf
PWC	https://paperswithcode.com/paper/improving-content-invariance-in-gated
Repo
Framework

Diversification-Based Learning in Computing and Optimization


Title	Diversification-Based Learning in Computing and Optimization
Authors	Fred Glover, Jin-Kao Hao
Abstract	Diversification-Based Learning (DBL) derives from a collection of principles and methods introduced in the field of metaheuristics that have broad applications in computing and optimization. We show that the DBL framework goes significantly beyond that of the more recent Opposition-based learning (OBL) framework introduced in Tizhoosh (2005), which has become the focus of numerous research initiatives in machine learning and metaheuristic optimization. We unify and extend earlier proposals in metaheuristic search (Glover, 1997, Glover and Laguna, 1997) to give a collection of approaches that are more flexible and comprehensive than OBL for creating intensification and diversification strategies in metaheuristic search. We also describe potential applications of DBL to various subfields of machine learning and optimization.
Tasks
Published	2017-03-23
URL	http://arxiv.org/abs/1703.07929v1
PDF	http://arxiv.org/pdf/1703.07929v1.pdf
PWC	https://paperswithcode.com/paper/diversification-based-learning-in-computing
Repo
Framework

Deep Reinforcement Learning for High Precision Assembly Tasks


Title	Deep Reinforcement Learning for High Precision Assembly Tasks
Authors	Tadanobu Inoue, Giovanni De Magistris, Asim Munawar, Tsuyoshi Yokoya, Ryuki Tachibana
Abstract	High precision assembly of mechanical parts requires accuracy exceeding the robot precision. Conventional part mating methods used in the current manufacturing requires tedious tuning of numerous parameters before deployment. We show how the robot can successfully perform a tight clearance peg-in-hole task through training a recurrent neural network with reinforcement learning. In addition to saving the manual effort, the proposed technique also shows robustness against position and angle errors for the peg-in-hole task. The neural network learns to take the optimal action by observing the robot sensors to estimate the system state. The advantages of our proposed method is validated experimentally on a 7-axis articulated robot arm.
Tasks
Published	2017-08-14
URL	http://arxiv.org/abs/1708.04033v2
PDF	http://arxiv.org/pdf/1708.04033v2.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-for-high
Repo
Framework

Discriminant Projection Representation-based Classification for Vision Recognition


Title	Discriminant Projection Representation-based Classification for Vision Recognition
Authors	Qingxiang Feng, Yicong Zhou
Abstract	Representation-based classification methods such as sparse representation-based classification (SRC) and linear regression classification (LRC) have attracted a lot of attentions. In order to obtain the better representation, a novel method called projection representation-based classification (PRC) is proposed for image recognition in this paper. PRC is based on a new mathematical model. This model denotes that the ‘ideal projection’ of a sample point $x$ on the hyper-space $H$ may be gained by iteratively computing the projection of $x$ on a line of hyper-space $H$ with the proper strategy. Therefore, PRC is able to iteratively approximate the ‘ideal representation’ of each subject for classification. Moreover, the discriminant PRC (DPRC) is further proposed, which obtains the discriminant information by maximizing the ratio of the between-class reconstruction error over the within-class reconstruction error. Experimental results on five typical databases show that the proposed PRC and DPRC are effective and outperform other state-of-the-art methods on several vision recognition tasks.
Tasks	Sparse Representation-based Classification
Published	2017-11-19
URL	http://arxiv.org/abs/1712.01643v1
PDF	http://arxiv.org/pdf/1712.01643v1.pdf
PWC	https://paperswithcode.com/paper/discriminant-projection-representation-based
Repo
Framework

Automatic Spatially-aware Fashion Concept Discovery


Title	Automatic Spatially-aware Fashion Concept Discovery
Authors	Xintong Han, Zuxuan Wu, Phoenix X. Huang, Xiao Zhang, Menglong Zhu, Yuan Li, Yang Zhao, Larry S. Davis
Abstract	This paper proposes an automatic spatially-aware concept discovery approach using weakly labeled image-text data from shopping websites. We first fine-tune GoogleNet by jointly modeling clothing images and their corresponding descriptions in a visual-semantic embedding space. Then, for each attribute (word), we generate its spatially-aware representation by combining its semantic word vector representation with its spatial representation derived from the convolutional maps of the fine-tuned network. The resulting spatially-aware representations are further used to cluster attributes into multiple groups to form spatially-aware concepts (e.g., the neckline concept might consist of attributes like v-neck, round-neck, etc). Finally, we decompose the visual-semantic embedding space into multiple concept-specific subspaces, which facilitates structured browsing and attribute-feedback product retrieval by exploiting multimodal linguistic regularities. We conducted extensive experiments on our newly collected Fashion200K dataset, and results on clustering quality evaluation and attribute-feedback product retrieval task demonstrate the effectiveness of our automatically discovered spatially-aware concepts.
Tasks
Published	2017-08-03
URL	http://arxiv.org/abs/1708.01311v1
PDF	http://arxiv.org/pdf/1708.01311v1.pdf
PWC	https://paperswithcode.com/paper/automatic-spatially-aware-fashion-concept
Repo
Framework

A Machine Learning Approach For Identifying Patients with Mild Traumatic Brain Injury Using Diffusion MRI Modeling


Title	A Machine Learning Approach For Identifying Patients with Mild Traumatic Brain Injury Using Diffusion MRI Modeling
Authors	Shervin Minaee, Yao Wang, Sohae Chung, Xiuyuan Wang, Els Fieremans, Steven Flanagan, Joseph Rath, Yvonne W. Lui
Abstract	While diffusion MRI has been extremely promising in the study of MTBI, identifying patients with recent MTBI remains a challenge. The literature is mixed with regard to localizing injury in these patients, however, gray matter such as the thalamus and white matter including the corpus callosum and frontal deep white matter have been repeatedly implicated as areas at high risk for injury. The purpose of this study is to develop a machine learning framework to classify MTBI patients and controls using features derived from multi-shell diffusion MRI in the thalamus, frontal white matter and corpus callosum.
Tasks
Published	2017-08-27
URL	http://arxiv.org/abs/1708.09000v1
PDF	http://arxiv.org/pdf/1708.09000v1.pdf
PWC	https://paperswithcode.com/paper/a-machine-learning-approach-for-identifying
Repo
Framework

Learning Discrete Weights Using the Local Reparameterization Trick


Title	Learning Discrete Weights Using the Local Reparameterization Trick
Authors	Oran Shayer, Dan Levi, Ethan Fetaya
Abstract	Recent breakthroughs in computer vision make use of large deep neural networks, utilizing the substantial speedup offered by GPUs. For applications running on limited hardware, however, high precision real-time processing can still be a challenge. One approach to solving this problem is training networks with binary or ternary weights, thus removing the need to calculate multiplications and significantly reducing memory size. In this work, we introduce LR-nets (Local reparameterization networks), a new method for training neural networks with discrete weights using stochastic parameters. We show how a simple modification to the local reparameterization trick, previously used to train Gaussian distributed weights, enables the training of discrete weights. Using the proposed training we test both binary and ternary models on MNIST, CIFAR-10 and ImageNet benchmarks and reach state-of-the-art results on most experiments.
Tasks
Published	2017-10-21
URL	http://arxiv.org/abs/1710.07739v3
PDF	http://arxiv.org/pdf/1710.07739v3.pdf
PWC	https://paperswithcode.com/paper/learning-discrete-weights-using-the-local
Repo
Framework

A semi-automated segmentation method for detection of pulmonary embolism in True-FISP MRI sequences


Title	A semi-automated segmentation method for detection of pulmonary embolism in True-FISP MRI sequences
Authors	Luis R Soenksen, Luis Jiménez-Angeles, Gabriela Melendez, Aloha Meave
Abstract	Pulmonary embolism (PE) is a highly mortal disease, currently assessed by pulmonary CT angiography. True-FISP MRI has emerged as an innocuous alternative that does not hold many of the limitations of x-ray imaging. However, True-FISP MRI is very sensitive to turbulent blood flow, generating artifacts that may resemble fake clots in the pulmonary vasculature. These misinterpretations reduce its overall diagnostic accuracy to 94%, limiting a wider use in clinical environments. A new segmentation algorithm is proposed to confirm the presence of real pulmonary clots in True-FISP MR images by quantitative means, measuring the shape, intensity, and solidity of the formation. The algorithm was evaluated in 37 patients. The developed method increased the diagnostic accuracy of expert observers assessing Pulmonary True-FISP MRI sequences by 6% without the use of ionizing radiation, achieving a diagnostic accuracy comparable to standard CT angiography.
Tasks
Published	2017-09-23
URL	http://arxiv.org/abs/1709.07993v1
PDF	http://arxiv.org/pdf/1709.07993v1.pdf
PWC	https://paperswithcode.com/paper/a-semi-automated-segmentation-method-for
Repo
Framework

Sparse-View X-Ray CT Reconstruction Using $\ell_1$ Prior with Learned Transform


Title	Sparse-View X-Ray CT Reconstruction Using $\ell_1$ Prior with Learned Transform
Authors	Xuehang Zheng, Il Yong Chun, Zhipeng Li, Yong Long, Jeffrey A. Fessler
Abstract	A major challenge in X-ray computed tomography (CT) is reducing radiation dose while maintaining high quality of reconstructed images. To reduce the radiation dose, one can reduce the number of projection views (sparse-view CT); however, it becomes difficult to achieve high-quality image reconstruction as the number of projection views decreases. Researchers have applied the concept of learning sparse representations from (high-quality) CT image dataset to the sparse-view CT reconstruction. We propose a new statistical CT reconstruction model that combines penalized weighted-least squares (PWLS) and $\ell_1$ prior with learned sparsifying transform (PWLS-ST-$\ell_1$), and a corresponding efficient algorithm based on Alternating Direction Method of Multipliers (ADMM). To moderate the difficulty of tuning ADMM parameters, we propose a new ADMM parameter selection scheme based on approximated condition numbers. We interpret the proposed model by analyzing the minimum mean square error of its ($\ell_2$-norm relaxed) image update estimator. Our results with the extended cardiac-torso (XCAT) phantom data and clinical chest data show that, for sparse-view 2D fan-beam CT and 3D axial cone-beam CT, PWLS-ST-$\ell_1$ improves the quality of reconstructed images compared to the CT reconstruction methods using edge-preserving regularizer and $\ell_2$ prior with learned ST. These results also show that, for sparse-view 2D fan-beam CT, PWLS-ST-$\ell_1$ achieves comparable or better image quality and requires much shorter runtime than PWLS-DL using a learned overcomplete dictionary. Our results with clinical chest data show that, methods using the unsupervised learned prior generalize better than a state-of-the-art deep “denoising” neural network that does not use a physical imaging model.
Tasks	Computed Tomography (CT), Denoising, Image Reconstruction
Published	2017-11-02
URL	https://arxiv.org/abs/1711.00905v3
PDF	https://arxiv.org/pdf/1711.00905v3.pdf
PWC	https://paperswithcode.com/paper/sparse-view-x-ray-ct-reconstruction-using
Repo
Framework

Learning User Intent from Action Sequences on Interactive Systems


Title	Learning User Intent from Action Sequences on Interactive Systems
Authors	Rakshit Agrawal, Anwar Habeeb, Chih-Hsin Hsueh
Abstract	Interactive systems have taken over the web and mobile space with increasing participation from users. Applications across every marketing domain can now be accessed through mobile or web where users can directly perform certain actions and reach a desired outcome. Actions of user on a system, though, can be representative of a certain intent. Ability to learn this intent through user’s actions can help draw certain insight into the behavior of users on a system. In this paper, we present models to optimize interactive systems by learning and analyzing user intent through their actions on the system. We present a four phased model that uses time-series of interaction actions sequentially using a Long Short-Term Memory (LSTM) based sequence learning system that helps build a model for intent recognition. Our system then provides an objective specific maximization followed by analysis and contrasting methods in order to identify spaces of improvement in the interaction system. We discuss deployment scenarios for such a system and present results from evaluation on an online marketplace using user clickstream data.
Tasks	Time Series
Published	2017-12-04
URL	http://arxiv.org/abs/1712.01328v1
PDF	http://arxiv.org/pdf/1712.01328v1.pdf
PWC	https://paperswithcode.com/paper/learning-user-intent-from-action-sequences-on
Repo
Framework

A Sentence Simplification System for Improving Relation Extraction


Title	A Sentence Simplification System for Improving Relation Extraction
Authors	Christina Niklaus, Bernhard Bermeitinger, Siegfried Handschuh, André Freitas
Abstract	In this demo paper, we present a text simplification approach that is directed at improving the performance of state-of-the-art Open Relation Extraction (RE) systems. As syntactically complex sentences often pose a challenge for current Open RE approaches, we have developed a simplification framework that performs a pre-processing step by taking a single sentence as input and using a set of syntactic-based transformation rules to create a textual input that is easier to process for subsequently applied Open RE systems.
Tasks	Relation Extraction, Text Simplification
Published	2017-03-27
URL	http://arxiv.org/abs/1703.09013v1
PDF	http://arxiv.org/pdf/1703.09013v1.pdf
PWC	https://paperswithcode.com/paper/a-sentence-simplification-system-for
Repo
Framework

An efficient deep learning hashing neural network for mobile visual search


Title	An efficient deep learning hashing neural network for mobile visual search
Authors	Heng Qi, Wu Liu, Liang Liu
Abstract	Mobile visual search applications are emerging that enable users to sense their surroundings with smart phones. However, because of the particular challenges of mobile visual search, achieving a high recognition bitrate has becomes a consistent target of previous related works. In this paper, we propose a few-parameter, low-latency, and high-accuracy deep hashing approach for constructing binary hash codes for mobile visual search. First, we exploit the architecture of the MobileNet model, which significantly decreases the latency of deep feature extraction by reducing the number of model parameters while maintaining accuracy. Second, we add a hash-like layer into MobileNet to train the model on labeled mobile visual data. Evaluations show that the proposed system can exceed state-of-the-art accuracy performance in terms of the MAP. More importantly, the memory consumption is much less than that of other deep learning models. The proposed method requires only $13$ MB of memory for the neural network and achieves a MAP of $97.80%$ on the mobile location recognition dataset used for testing.
Tasks
Published	2017-10-21
URL	http://arxiv.org/abs/1710.07750v1
PDF	http://arxiv.org/pdf/1710.07750v1.pdf
PWC	https://paperswithcode.com/paper/an-efficient-deep-learning-hashing-neural
Repo
Framework

Keyword-based Query Comprehending via Multiple Optimized-Demand Augmentation


Title	Keyword-based Query Comprehending via Multiple Optimized-Demand Augmentation
Authors	Boyuan Pan, Hao Li, Zhou Zhao, Deng Cai, Xiaofei He
Abstract	In this paper, we consider the problem of machine reading task when the questions are in the form of keywords, rather than natural language. In recent years, researchers have achieved significant success on machine reading comprehension tasks, such as SQuAD and TriviaQA. These datasets provide a natural language question sentence and a pre-selected passage, and the goal is to answer the question according to the passage. However, in the situation of interacting with machines by means of text, people are more likely to raise a query in form of several keywords rather than a complete sentence. The keyword-based query comprehension is a new challenge, because small variations to a question may completely change its semantical information, thus yield different answers. In this paper, we propose a novel neural network system that consists a Demand Optimization Model based on a passage-attention neural machine translation and a Reader Model that can find the answer given the optimized question. The Demand Optimization Model optimizes the original query and output multiple reconstructed questions, then the Reader Model takes the new questions as input and locate the answers from the passage. To make predictions robust, an evaluation mechanism will score the reconstructed questions so the final answer strike a good balance between the quality of both the Demand Optimization Model and the Reader Model. Experimental results on several datasets show that our framework significantly improves multiple strong baselines on this challenging task.
Tasks	Machine Reading Comprehension, Machine Translation, Reading Comprehension
Published	2017-11-01
URL	http://arxiv.org/abs/1711.00179v1
PDF	http://arxiv.org/pdf/1711.00179v1.pdf
PWC	https://paperswithcode.com/paper/keyword-based-query-comprehending-via
Repo
Framework