Paper Group ANR 1098
Multi-Player Bandits: A Trekking Approach. A Multi-layer Gaussian Process for Motor Symptom Estimation in People with Parkinson’s Disease. Policy Optimization as Wasserstein Gradient Flows. Spectrally approximating large graphs with smaller graphs. Learning to recognize Abnormalities in Chest X-Rays with Location-Aware Dense Networks. A CNN for hom …
Multi-Player Bandits: A Trekking Approach
| Title | Multi-Player Bandits: A Trekking Approach |
| Authors | Manjesh K. Hanawal, Sumit J. Darak |
| Abstract | We study stochastic multi-armed bandits with many players. The players do not know the number of players, cannot communicate with each other and if multiple players select a common arm they collide and none of them receive any reward. We consider the static scenario, where the number of players remains fixed, and the dynamic scenario, where the players enter and leave at any time. We provide algorithms based on a novel `trekking approach’ that guarantees constant regret for the static case and sub-linear regret for the dynamic case with high probability. The trekking approach eliminates the need to estimate the number of players resulting in fewer collisions and improved regret performance compared to the state-of-the-art algorithms. We also develop an epoch-less algorithm that eliminates any requirement of time synchronization across the players provided each player can detect the presence of other players on an arm. We validate our theoretical guarantees using simulation based and real test-bed based experiments. | |
| Tasks | Multi-Armed Bandits |
| Published | 2018-09-17 |
| URL | http://arxiv.org/abs/1809.06040v1 |
| http://arxiv.org/pdf/1809.06040v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-player-bandits-a-trekking-approach |
| Repo | |
| Framework | |
A Multi-layer Gaussian Process for Motor Symptom Estimation in People with Parkinson’s Disease
| Title | A Multi-layer Gaussian Process for Motor Symptom Estimation in People with Parkinson’s Disease |
| Authors | Muriel Lang, Franz M. J. Pfister, Jakob Fröhner, Kian Abedinpour, Daniel Pichler, Urban Fietzek, Terry T. Um, Dana Kulić, Satoshi Endo, Sandra Hirche |
| Abstract | The assessment of Parkinson’s disease (PD) poses a significant challenge as it is influenced by various factors which lead to a complex and fluctuating symptom manifestation. Thus, a frequent and objective PD assessment is highly valuable for effective health management of people with Parkinson’s disease (PwP). Here, we propose a method for monitoring PwP by stochastically modeling the relationships between their wrist movements during unscripted daily activities and corresponding annotations about clinical displays of movement abnormalities. We approach the estimation of PD motor signs by independently modeling and hierarchically stacking Gaussian process models for three classes of commonly observed movement abnormalities in PwP including tremor, (non-tremulous) bradykinesia, and (non-tremulous) dyskinesia. We use clinically adopted severity measures as annotations for training the models, thus allowing our multi-layer Gaussian process prediction models to estimate not only their presence but also their severities. The experimental validation of our approach demonstrates strong agreement of the model predictions with these PD annotations. Our results show the proposed method produces promising results in objective monitoring of movement abnormalities of PD in the presence of arbitrary and unknown voluntary motions, and makes an important step towards continuous monitoring of PD in the home environment. |
| Tasks | |
| Published | 2018-08-31 |
| URL | http://arxiv.org/abs/1808.10663v2 |
| http://arxiv.org/pdf/1808.10663v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-multi-layer-gaussian-process-for-motor |
| Repo | |
| Framework | |
Policy Optimization as Wasserstein Gradient Flows
| Title | Policy Optimization as Wasserstein Gradient Flows |
| Authors | Ruiyi Zhang, Changyou Chen, Chunyuan Li, Lawrence Carin |
| Abstract | Policy optimization is a core component of reinforcement learning (RL), and most existing RL methods directly optimize parameters of a policy based on maximizing the expected total reward, or its surrogate. Though often achieving encouraging empirical success, its underlying mathematical principle on {\em policy-distribution} optimization is unclear. We place policy optimization into the space of probability measures, and interpret it as Wasserstein gradient flows. On the probability-measure space, under specified circumstances, policy optimization becomes a convex problem in terms of distribution optimization. To make optimization feasible, we develop efficient algorithms by numerically solving the corresponding discrete gradient flows. Our technique is applicable to several RL settings, and is related to many state-of-the-art policy-optimization algorithms. Empirical results verify the effectiveness of our framework, often obtaining better performance compared to related algorithms. |
| Tasks | |
| Published | 2018-08-09 |
| URL | http://arxiv.org/abs/1808.03030v1 |
| http://arxiv.org/pdf/1808.03030v1.pdf | |
| PWC | https://paperswithcode.com/paper/policy-optimization-as-wasserstein-gradient |
| Repo | |
| Framework | |
Spectrally approximating large graphs with smaller graphs
| Title | Spectrally approximating large graphs with smaller graphs |
| Authors | Andreas Loukas, Pierre Vandergheynst |
| Abstract | How does coarsening affect the spectrum of a general graph? We provide conditions such that the principal eigenvalues and eigenspaces of a coarsened and original graph Laplacian matrices are close. The achieved approximation is shown to depend on standard graph-theoretic properties, such as the degree and eigenvalue distributions, as well as on the ratio between the coarsened and actual graph sizes. Our results carry implications for learning methods that utilize coarsening. For the particular case of spectral clustering, they imply that coarse eigenvectors can be used to derive good quality assignments even without refinement—this phenomenon was previously observed, but lacked formal justification. |
| Tasks | |
| Published | 2018-02-21 |
| URL | http://arxiv.org/abs/1802.07510v1 |
| http://arxiv.org/pdf/1802.07510v1.pdf | |
| PWC | https://paperswithcode.com/paper/spectrally-approximating-large-graphs-with |
| Repo | |
| Framework | |
Learning to recognize Abnormalities in Chest X-Rays with Location-Aware Dense Networks
| Title | Learning to recognize Abnormalities in Chest X-Rays with Location-Aware Dense Networks |
| Authors | Sebastian Guendel, Sasa Grbic, Bogdan Georgescu, Kevin Zhou, Ludwig Ritschl, Andreas Meier, Dorin Comaniciu |
| Abstract | Chest X-ray is the most common medical imaging exam used to assess multiple pathologies. Automated algorithms and tools have the potential to support the reading workflow, improve efficiency, and reduce reading errors. With the availability of large scale data sets, several methods have been proposed to classify pathologies on chest X-ray images. However, most methods report performance based on random image based splitting, ignoring the high probability of the same patient appearing in both training and test set. In addition, most methods fail to explicitly incorporate the spatial information of abnormalities or utilize the high resolution images. We propose a novel approach based on location aware Dense Networks (DNetLoc), whereby we incorporate both high-resolution image data and spatial information for abnormality classification. We evaluate our method on the largest data set reported in the community, containing a total of 86,876 patients and 297,541 chest X-ray images. We achieve (i) the best average AUC score for published training and test splits on the single benchmarking data set (ChestX-Ray14), and (ii) improved AUC scores when the pathology location information is explicitly used. To foster future research we demonstrate the limitations of the current benchmarking setup and provide new reference patient-wise splits for the used data sets. This could support consistent and meaningful benchmarking of future methods on the largest publicly available data sets. |
| Tasks | |
| Published | 2018-03-12 |
| URL | http://arxiv.org/abs/1803.04565v1 |
| http://arxiv.org/pdf/1803.04565v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-recognize-abnormalities-in-chest |
| Repo | |
| Framework | |
A CNN for homogneous Riemannian manifolds with applications to Neuroimaging
| Title | A CNN for homogneous Riemannian manifolds with applications to Neuroimaging |
| Authors | Rudrasis Chakraborty, Monami Banerjee, Baba C. Vemuri |
| Abstract | Convolutional neural networks are ubiquitous in Machine Learning applications for solving a variety of problems. They however can not be used in their native form when the domain of the data is commonly encountered manifolds such as the sphere, the special orthogonal group, the Grassmanian, the manifold of symmetric positive definite matrices and others. Most recently, generalization of CNNs to data domains such as the 2-sphere has been reported by some research groups, which is referred to as the spherical CNNs (SCNNs). The key property of SCNNs distinct from CNNs is that they exhibit the rotational equivariance property that allows for sharing learned weights within a layer. In this paper, we theoretically generalize the CNNs to Riemannian homogeneous manifolds, that include but are not limited to the aforementioned example manifolds. Our key contributions in this work are: (i) A theorem stating that linear group equivariance systems are fully characterized by correlation of functions on the domain manifold and vice-versa. This is fundamental to the characterization of all linear group equivariant systems and parallels the widely used result in linear system theory for vector spaces. (ii) As a corrolary, we prove the equivariance of the correlation operation to group actions admitted by the input domains which are Riemannian homogeneous manifolds. (iii) We present the first end-to-end deep network architecture for classification of diffusion magnetic resonance image (dMRI) scans acquired from a cohort of 44 Parkinson Disease patients and 50 control/normal subjects. (iv) A proof of concept experiment involving synthetic data generated on the manifold of symmetric positive definite matrices is presented to demonstrate the applicability of our network to other types of domains. |
| Tasks | |
| Published | 2018-05-14 |
| URL | http://arxiv.org/abs/1805.05487v3 |
| http://arxiv.org/pdf/1805.05487v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-cnn-for-homogneous-riemannian-manifolds |
| Repo | |
| Framework | |
Conditional Sparse $\ell_p$-norm Regression With Optimal Probability
| Title | Conditional Sparse $\ell_p$-norm Regression With Optimal Probability |
| Authors | John Hainline, Brendan Juba, Hai S. Le, David Woodruff |
| Abstract | We consider the following conditional linear regression problem: the task is to identify both (i) a $k$-DNF condition $c$ and (ii) a linear rule $f$ such that the probability of $c$ is (approximately) at least some given bound $\mu$, and $f$ minimizes the $\ell_p$ loss of predicting the target $z$ in the distribution of examples conditioned on $c$. Thus, the task is to identify a portion of the distribution on which a linear rule can provide a good fit. Algorithms for this task are useful in cases where simple, learnable rules only accurately model portions of the distribution. The prior state-of-the-art for such algorithms could only guarantee finding a condition of probability $\Omega(\mu/n^k)$ when a condition of probability $\mu$ exists, and achieved an $O(n^k)$-approximation to the target loss, where $n$ is the number of Boolean attributes. Here, we give efficient algorithms for solving this task with a condition $c$ that nearly matches the probability of the ideal condition, while also improving the approximation to the target loss. We also give an algorithm for finding a $k$-DNF reference class for prediction at a given query point, that obtains a sparse regression fit that has loss within $O(n^k)$ of optimal among all sparse regression parameters and sufficiently large $k$-DNF reference classes containing the query point. |
| Tasks | |
| Published | 2018-06-26 |
| URL | http://arxiv.org/abs/1806.10222v1 |
| http://arxiv.org/pdf/1806.10222v1.pdf | |
| PWC | https://paperswithcode.com/paper/conditional-sparse-ell_p-norm-regression-with |
| Repo | |
| Framework | |
3D Depthwise Convolution: Reducing Model Parameters in 3D Vision Tasks
| Title | 3D Depthwise Convolution: Reducing Model Parameters in 3D Vision Tasks |
| Authors | Rongtian Ye, Fangyu Liu, Liqiang Zhang |
| Abstract | Standard 3D convolution operations require much larger amounts of memory and computation cost than 2D convolution operations. The fact has hindered the development of deep neural nets in many 3D vision tasks. In this paper, we investigate the possibility of applying depthwise separable convolutions in 3D scenario and introduce the use of 3D depthwise convolution. A 3D depthwise convolution splits a single standard 3D convolution into two separate steps, which would drastically reduce the number of parameters in 3D convolutions with more than one order of magnitude. We experiment with 3D depthwise convolution on popular CNN architectures and also compare it with a similar structure called pseudo-3D convolution. The results demonstrate that, with 3D depthwise convolutions, 3D vision tasks like classification and reconstruction can be carried out with more light-weighted neural networks while still delivering comparable performances. |
| Tasks | |
| Published | 2018-08-05 |
| URL | http://arxiv.org/abs/1808.01556v1 |
| http://arxiv.org/pdf/1808.01556v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-depthwise-convolution-reducing-model |
| Repo | |
| Framework | |
Learning to Synthesize Motion Blur
| Title | Learning to Synthesize Motion Blur |
| Authors | Tim Brooks, Jonathan T. Barron |
| Abstract | We present a technique for synthesizing a motion blurred image from a pair of unblurred images captured in succession. To build this system we motivate and design a differentiable “line prediction” layer to be used as part of a neural network architecture, with which we can learn a system to regress from image pairs to motion blurred images that span the capture time of the input image pair. Training this model requires an abundance of data, and so we design and execute a strategy for using frame interpolation techniques to generate a large-scale synthetic dataset of motion blurred images and their respective inputs. We additionally capture a high quality test set of real motion blurred images, synthesized from slow motion videos, with which we evaluate our model against several baseline techniques that can be used to synthesize motion blur. Our model produces higher accuracy output than our baselines, and is significantly faster than baselines with competitive accuracy. |
| Tasks | |
| Published | 2018-11-27 |
| URL | https://arxiv.org/abs/1811.11745v2 |
| https://arxiv.org/pdf/1811.11745v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-synthesize-motion-blur |
| Repo | |
| Framework | |
Emotion Detection in Text: a Review
| Title | Emotion Detection in Text: a Review |
| Authors | Armin Seyeditabari, Narges Tabari, Wlodek Zadrozny |
| Abstract | In recent years, emotion detection in text has become more popular due to its vast potential applications in marketing, political science, psychology, human-computer interaction, artificial intelligence, etc. Access to a huge amount of textual data, especially opinionated and self-expression text also played a special role to bring attention to this field. In this paper, we review the work that has been done in identifying emotion expressions in text and argue that although many techniques, methodologies, and models have been created to detect emotion in text, there are various reasons that make these methods insufficient. Although, there is an essential need to improve the design and architecture of current systems, factors such as the complexity of human emotions, and the use of implicit and metaphorical language in expressing it, lead us to think that just re-purposing standard methodologies will not be enough to capture these complexities, and it is important to pay attention to the linguistic intricacies of emotion expression. |
| Tasks | |
| Published | 2018-06-02 |
| URL | http://arxiv.org/abs/1806.00674v1 |
| http://arxiv.org/pdf/1806.00674v1.pdf | |
| PWC | https://paperswithcode.com/paper/emotion-detection-in-text-a-review |
| Repo | |
| Framework | |
Central Bank Communication and the Yield Curve: A Semi-Automatic Approach using Non-Negative Matrix Factorization
| Title | Central Bank Communication and the Yield Curve: A Semi-Automatic Approach using Non-Negative Matrix Factorization |
| Authors | Ancil Crayton |
| Abstract | Communication is now a standard tool in the central bank’s monetary policy toolkit. Theoretically, communication provides the central bank an opportunity to guide public expectations, and it has been shown empirically that central bank communication can lead to financial market fluctuations. However, there has been little research into which dimensions or topics of information are most important in causing these fluctuations. We develop a semi-automatic methodology that summarizes the FOMC statements into its main themes, automatically selects the best model based on coherency, and assesses whether there is a significant impact of these themes on the shape of the U.S Treasury yield curve using topic modeling methods from the machine learning literature. Our findings suggest that the FOMC statements can be decomposed into three topics: (i) information related to the economic conditions and the mandates, (ii) information related to monetary policy tools and intermediate targets, and (iii) information related to financial markets and the financial crisis. We find that statements are most influential during the financial crisis and the effects are mostly present in the curvature of the yield curve through information related to the financial theme. |
| Tasks | |
| Published | 2018-09-24 |
| URL | http://arxiv.org/abs/1809.08718v1 |
| http://arxiv.org/pdf/1809.08718v1.pdf | |
| PWC | https://paperswithcode.com/paper/central-bank-communication-and-the-yield |
| Repo | |
| Framework | |
A Variational U-Net for Conditional Appearance and Shape Generation
| Title | A Variational U-Net for Conditional Appearance and Shape Generation |
| Authors | Patrick Esser, Ekaterina Sutter, Björn Ommer |
| Abstract | Deep generative models have demonstrated great performance in image synthesis. However, results deteriorate in case of spatial deformations, since they generate images of objects directly, rather than modeling the intricate interplay of their inherent shape and appearance. We present a conditional U-Net for shape-guided image generation, conditioned on the output of a variational autoencoder for appearance. The approach is trained end-to-end on images, without requiring samples of the same object with varying pose or appearance. Experiments show that the model enables conditional image generation and transfer. Therefore, either shape or appearance can be retained from a query image, while freely altering the other. Moreover, appearance can be sampled due to its stochastic latent representation, while preserving shape. In quantitative and qualitative experiments on COCO, DeepFashion, shoes, Market-1501 and handbags, the approach demonstrates significant improvements over the state-of-the-art. |
| Tasks | Conditional Image Generation, Image Generation |
| Published | 2018-04-12 |
| URL | http://arxiv.org/abs/1804.04694v1 |
| http://arxiv.org/pdf/1804.04694v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-variational-u-net-for-conditional |
| Repo | |
| Framework | |
Attentive Relational Networks for Mapping Images to Scene Graphs
| Title | Attentive Relational Networks for Mapping Images to Scene Graphs |
| Authors | Mengshi Qi, Weijian Li, Zhengyuan Yang, Yunhong Wang, Jiebo Luo |
| Abstract | Scene graph generation refers to the task of automatically mapping an image into a semantic structural graph, which requires correctly labeling each extracted object and their interaction relationships. Despite the recent success in object detection using deep learning techniques, inferring complex contextual relationships and structured graph representations from visual data remains a challenging topic. In this study, we propose a novel Attentive Relational Network that consists of two key modules with an object detection backbone to approach this problem. The first module is a semantic transformation module utilized to capture semantic embedded relation features, by translating visual features and linguistic features into a common semantic space. The other module is a graph self-attention module introduced to embed a joint graph representation through assigning various importance weights to neighboring nodes. Finally, accurate scene graphs are produced by the relation inference module to recognize all entities and the corresponding relations. We evaluate our proposed method on the widely-adopted Visual Genome Dataset, and the results demonstrate the effectiveness and superiority of our model. |
| Tasks | Graph Generation, Object Detection, Scene Graph Generation |
| Published | 2018-11-26 |
| URL | http://arxiv.org/abs/1811.10696v2 |
| http://arxiv.org/pdf/1811.10696v2.pdf | |
| PWC | https://paperswithcode.com/paper/attentive-relational-networks-for-mapping |
| Repo | |
| Framework | |
Deep Multi-view Learning to Rank
| Title | Deep Multi-view Learning to Rank |
| Authors | Guanqun Cao, Alexandros Iosifidis, Moncef Gabbouj, Vijay Raghavan, Raju Gottumukkala |
| Abstract | We study the problem of learning to rank from multiple information sources. Though multi-view learning and learning to rank have been studied extensively leading to a wide range of applications, multi-view learning to rank as a synergy of both topics has received little attention. The aim of the paper is to propose a composite ranking method while keeping a close correlation with the individual rankings simultaneously. We present a generic framework for multi-view subspace learning to rank (MvSL2R), and two novel solutions are introduced under the framework. The first solution captures information of feature mappings from within each view as well as across views using autoencoder-like networks. Novel feature embedding methods are formulated in the optimization of multi-view unsupervised and discriminant autoencoders. Moreover, we introduce an end-to-end solution to learning towards both the joint ranking objective and the individual rankings. The proposed solution enhances the joint ranking with minimum view-specific ranking loss, so that it can achieve the maximum global view agreements in a single optimization process. The proposed method is evaluated on three different ranking problems, i.e. university ranking, multi-view lingual text ranking and image data ranking, providing superior results compared to related methods. |
| Tasks | Learning-To-Rank, MULTI-VIEW LEARNING |
| Published | 2018-01-31 |
| URL | https://arxiv.org/abs/1801.10402v2 |
| https://arxiv.org/pdf/1801.10402v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-multi-view-learning-to-rank |
| Repo | |
| Framework | |
Effects of Loss Functions And Target Representations on Adversarial Robustness
| Title | Effects of Loss Functions And Target Representations on Adversarial Robustness |
| Authors | Sean Saito, Sujoy Roy |
| Abstract | Understanding and evaluating the robustness of neural networks under adversarial settings is a subject of growing interest. Attacks proposed in the literature usually work with models trained to minimize cross-entropy loss and output softmax probabilities. In this work, we present interesting experimental results that suggest the importance of considering other loss functions and target representations, specifically, (1) training on mean-squared error and (2) representing targets as codewords generated from a random codebook. We evaluate the robustness of neural networks that implement these proposed modifications using existing attacks, showing an increase in accuracy against untargeted attacks of up to 98.7% and a decrease of targeted attack success rates of up to 99.8%. Our model demonstrates more robustness compared to its conventional counterpart even against attacks that are tailored to our modifications. Furthermore, we find that the parameters of our modified model have significantly smaller Lipschitz bounds, an important measure correlated with a model’s sensitivity to adversarial perturbations. |
| Tasks | |
| Published | 2018-12-01 |
| URL | https://arxiv.org/abs/1812.00181v3 |
| https://arxiv.org/pdf/1812.00181v3.pdf | |
| PWC | https://paperswithcode.com/paper/effects-of-loss-functions-and-target |
| Repo | |
| Framework | |
