Paper Group ANR 1341
An Empirical Study on the Practical Impact of Prior Beliefs over Policy Types. When can we improve on sample average approximation for stochastic optimization?. Understanding Distributional Ambiguity via Non-robust Chance Constraint. Imbalanced Learning-based Automatic SAR Images Change Detection by Morphologically Supervised PCA-Net. Pattern Recog …
An Empirical Study on the Practical Impact of Prior Beliefs over Policy Types
| Title | An Empirical Study on the Practical Impact of Prior Beliefs over Policy Types |
| Authors | Stefano V. Albrecht, Jacob W. Crandall, Subramanian Ramamoorthy |
| Abstract | Many multiagent applications require an agent to learn quickly how to interact with previously unknown other agents. To address this problem, researchers have studied learning algorithms which compute posterior beliefs over a hypothesised set of policies, based on the observed actions of the other agents. The posterior belief is complemented by the prior belief, which specifies the subjective likelihood of policies before any actions are observed. In this paper, we present the first comprehensive empirical study on the practical impact of prior beliefs over policies in repeated interactions. We show that prior beliefs can have a significant impact on the long-term performance of such methods, and that the magnitude of the impact depends on the depth of the planning horizon. Moreover, our results demonstrate that automatic methods can be used to compute prior beliefs with consistent performance effects. This indicates that prior beliefs could be eliminated as a manual parameter and instead be computed automatically. |
| Tasks | |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.05247v1 |
| https://arxiv.org/pdf/1907.05247v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-empirical-study-on-the-practical-impact-of |
| Repo | |
| Framework | |
When can we improve on sample average approximation for stochastic optimization?
| Title | When can we improve on sample average approximation for stochastic optimization? |
| Authors | Eddie Anderson, Harrison Nguyen |
| Abstract | We explore the performance of sample average approximation in comparison with several other methods for stochastic optimization when there is information available on the underlying true probability distribution. The methods we evaluate are (a) bagging; (b) kernel smoothing; (c) maximum likelihood estimation (MLE); and (d) a Bayesian approach. We use two test sets, the first has a quadratic objective function allowing for very different types of interaction between the random component and the univariate decision variable. Here the sample average approximation is remarkably effective and only consistently outperformed by a Bayesian approach. The second test set is a portfolio optimization problem in which we use different covariance structures for a set of 5 stocks. Here bagging, MLE and a Bayesian approach all do well. |
| Tasks | Portfolio Optimization, Stochastic Optimization |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.08334v1 |
| https://arxiv.org/pdf/1907.08334v1.pdf | |
| PWC | https://paperswithcode.com/paper/when-can-we-improve-on-sample-average |
| Repo | |
| Framework | |
Understanding Distributional Ambiguity via Non-robust Chance Constraint
| Title | Understanding Distributional Ambiguity via Non-robust Chance Constraint |
| Authors | Qi Wu, Shumin Ma, Cheuk Hang Leung, Wei Liu |
| Abstract | We propose a non-robust interpretation of the distributionally robust optimization (DRO) problem by relating the impact of uncertainties around the distribution on the impact of constraining the objective through tail probabilities. Our interpretation allows utility maximizers to figure out the size of the ambiguity set through parameters that are directly linked to the chance parameters. We first show that for general $\phi$-divergences, a DRO problem is asymptotically equivalent to a class of mean-deviation problems, where the ambiguity radius controls investor’s risk preference. Based on this non-robust reformulation, we then show that when a boundedness constraint is added to the investment strategy. The DRO problem can be cast as a chance-constrained optimization (CCO) problem without distributional uncertainties. Without the boundedness constraint, the CCO problem is shown to perform uniformly better than the DRO problem, irrespective of the radius of the ambiguity set, the choice of the divergence measure, or the tail heaviness of the center distribution. Besides the widely-used Kullback-Leibler (KL) divergence which requires the distribution of the objective function to be exponentially bounded, our results apply to divergence measures that accommodate well heavy tail distribution such as the student $t$-distribution and the lognormal distribution. Comprehensive testings on synthetic data and real data are provided. |
| Tasks | Portfolio Optimization |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.01981v3 |
| https://arxiv.org/pdf/1906.01981v3.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-distributional-ambiguity-via |
| Repo | |
| Framework | |
Imbalanced Learning-based Automatic SAR Images Change Detection by Morphologically Supervised PCA-Net
| Title | Imbalanced Learning-based Automatic SAR Images Change Detection by Morphologically Supervised PCA-Net |
| Authors | Rongfang Wang, Jie Zhang, Jia-Wei Chen, Licheng Jiao, Mi Wang |
| Abstract | Change detection is a quite challenging task due to the imbalance between unchanged and changed class. In addition, the traditional difference map generated by log-ratio is subject to the speckle, which will reduce the accuracy. In this letter, an imbalanced learning-based change detection is proposed based on PCA network (PCA-Net), where a supervised PCA-Net is designed to obtain the robust features directly from given multitemporal SAR images instead of a difference map. Furthermore, to tackle with the imbalance between changed and unchanged classes, we propose a morphologically supervised learning method, where the knowledge in the pixels near the boundary between two classes are exploited to guide network training. Finally, our proposed PCA-Net can be trained by the datasets with available reference maps and applied to a new dataset, which is quite practical in change detection projects. Our proposed method is verified on five sets of multiple temporal SAR images. It is demonstrated from the experiment results that with the knowledge in training samples from the boundary, the learned features benefit for change detection and make the proposed method outperforms than supervised methods trained by randomly drawing samples. |
| Tasks | |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.07923v1 |
| https://arxiv.org/pdf/1906.07923v1.pdf | |
| PWC | https://paperswithcode.com/paper/imbalanced-learning-based-automatic-sar |
| Repo | |
| Framework | |
Pattern Recognition in SAR Images using Fractional Random Fields and its Possible Application to the Problem of the Detection of Oil Spills in Open Sea
| Title | Pattern Recognition in SAR Images using Fractional Random Fields and its Possible Application to the Problem of the Detection of Oil Spills in Open Sea |
| Authors | Agustín Mailing, Segundo A. Molina, José L. Hamkalo, Fernando R. Dobarro, Juan M. Medina, Bruno Cernuschi-Frías, Daniel A. Fernández, Érica Schlaps |
| Abstract | In this note we deal with the detection of oil spills in open sea via self similar, long range dependence random fields and wavelet filters. We show some preliminary experimental results of our technique with Sentinel 1 SAR images. |
| Tasks | |
| Published | 2019-03-07 |
| URL | http://arxiv.org/abs/1903.03221v1 |
| http://arxiv.org/pdf/1903.03221v1.pdf | |
| PWC | https://paperswithcode.com/paper/pattern-recognition-in-sar-images-using |
| Repo | |
| Framework | |
SEALion: a Framework for Neural Network Inference on Encrypted Data
| Title | SEALion: a Framework for Neural Network Inference on Encrypted Data |
| Authors | Tim van Elsloo, Giorgio Patrini, Hamish Ivey-Law |
| Abstract | We present SEALion: an extensible framework for privacy-preserving machine learning with homomorphic encryption. It allows one to learn deep neural networks that can be seamlessly utilized for prediction on encrypted data. The framework consists of two layers: the first is built upon TensorFlow and SEAL and exposes standard algebra and deep learning primitives; the second implements a Keras-like syntax for training and inference with neural networks. Given a required level of security, a user is abstracted from the details of the encoding and the encryption scheme, allowing quick prototyping. We present two applications that exemplifying the extensibility of our proposal, which are also of independent interest: i) improving efficiency of neural network inference by an activity sparsifier and ii) transfer learning by querying a server-side Variational AutoEncoder that can handle encrypted data. |
| Tasks | Transfer Learning |
| Published | 2019-04-29 |
| URL | http://arxiv.org/abs/1904.12840v1 |
| http://arxiv.org/pdf/1904.12840v1.pdf | |
| PWC | https://paperswithcode.com/paper/sealion-a-framework-for-neural-network |
| Repo | |
| Framework | |
Fully-Featured Attribute Transfer
| Title | Fully-Featured Attribute Transfer |
| Authors | De Xie, Muli Yang, Cheng Deng, Wei Liu, Dacheng Tao |
| Abstract | Image attribute transfer aims to change an input image to a target one with expected attributes, which has received significant attention in recent years. However, most of the existing methods lack the ability to de-correlate the target attributes and irrelevant information, i.e., the other attributes and background information, thus often suffering from blurs and artifacts. To address these issues, we propose a novel Attribute Manifold Encoding GAN (AME-GAN) for fully-featured attribute transfer, which can modify and adjust every detail in the images. Specifically, our method divides the input image into image attribute part and image background part on manifolds, which are controlled by attribute latent variables and background latent variables respectively. Through enforcing attribute latent variables to Gaussian distributions and background latent variables to uniform distributions respectively, the attribute transfer procedure becomes controllable and image generation is more photo-realistic. Furthermore, we adopt a conditional multi-scale discriminator to render accurate and high-quality target attribute images. Experimental results on three popular datasets demonstrate the superiority of our proposed method in both performances of the attribute transfer and image generation quality. |
| Tasks | Image Generation |
| Published | 2019-02-17 |
| URL | http://arxiv.org/abs/1902.06258v1 |
| http://arxiv.org/pdf/1902.06258v1.pdf | |
| PWC | https://paperswithcode.com/paper/fully-featured-attribute-transfer |
| Repo | |
| Framework | |
Semi-supervised classification on graphs using explicit diffusion dynamics
| Title | Semi-supervised classification on graphs using explicit diffusion dynamics |
| Authors | Robert L. Peach, Alexis Arnaudon, Mauricio Barahona |
| Abstract | Classification tasks based on feature vectors can be significantly improved by including within deep learning a graph that summarises pairwise relationships between the samples. Intuitively, the graph acts as a conduit to channel and bias the inference of class labels. Here, we study classification methods that consider the graph as the originator of an explicit graph diffusion. We show that appending graph diffusion to feature-based learning as an \textit{a posteriori} refinement achieves state-of-the-art classification accuracy. This method, which we call Graph Diffusion Reclassification (GDR), uses overshooting events of a diffusive graph dynamics to reclassify individual nodes. The method uses intrinsic measures of node influence, which are distinct for each node, and allows the evaluation of the relationship and importance of features and graph for classification. We also present diff-GCN, a simple extension of Graph Convolutional Neural Network (GCN) architectures that leverages explicit diffusion dynamics, and allows the natural use of directed graphs. To showcase our methods, we use benchmark datasets of documents with associated citation data. |
| Tasks | |
| Published | 2019-09-24 |
| URL | https://arxiv.org/abs/1909.11117v1 |
| https://arxiv.org/pdf/1909.11117v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-classification-on-graphs |
| Repo | |
| Framework | |
Attention Optimization for Abstractive Document Summarization
| Title | Attention Optimization for Abstractive Document Summarization |
| Authors | Min Gui, Junfeng Tian, Rui Wang, Zhenglu Yang |
| Abstract | Attention plays a key role in the improvement of sequence-to-sequence-based document summarization models. To obtain a powerful attention helping with reproducing the most salient information and avoiding repetitions, we augment the vanilla attention model from both local and global aspects. We propose an attention refinement unit paired with local variance loss to impose supervision on the attention model at each decoding step, and a global variance loss to optimize the attention distributions of all decoding steps from the global perspective. The performances on the CNN/Daily Mail dataset verify the effectiveness of our methods. |
| Tasks | Document Summarization |
| Published | 2019-10-25 |
| URL | https://arxiv.org/abs/1910.11491v1 |
| https://arxiv.org/pdf/1910.11491v1.pdf | |
| PWC | https://paperswithcode.com/paper/attention-optimization-for-abstractive |
| Repo | |
| Framework | |
Human Motion Anticipation with Symbolic Label
| Title | Human Motion Anticipation with Symbolic Label |
| Authors | Julian Tanke, Andreas Weber, Juergen Gall |
| Abstract | Anticipating human motion depends on two factors: the past motion and the person’s intention. While the first factor has been extensively utilized to forecast short sequences of human motion, the second one remains elusive. In this work we approximate a person’s intention via a symbolic representation, for example fine-grained action labels such as walking or sitting down. Forecasting a symbolic representation is much easier than forecasting the full body pose with its complex inter-dependencies. However, knowing the future actions makes forecasting human motion easier. We exploit this connection by first anticipating symbolic labels and then generate human motion, conditioned on the human motion input sequence as well as on the forecast labels. This allows the model to anticipate motion changes many steps ahead and adapt the poses accordingly. We achieve state-of-the-art results on short-term as well as on long-term human motion forecasting. |
| Tasks | Motion Forecasting |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.06079v2 |
| https://arxiv.org/pdf/1912.06079v2.pdf | |
| PWC | https://paperswithcode.com/paper/human-motion-anticipation-with-symbolic-label |
| Repo | |
| Framework | |
Privacy Preserving Group Membership Verification and Identification
| Title | Privacy Preserving Group Membership Verification and Identification |
| Authors | Marzieh Gheisari, Teddy Furon, Laurent Amsaleg |
| Abstract | When convoking privacy, group membership verification checks if a biometric trait corresponds to one member of a group without revealing the identity of that member. Similarly, group membership identification states which group the individual belongs to, without knowing his/her identity. A recent contribution provides privacy and security for group membership protocols through the joint use of two mechanisms: quantizing biometric templates into discrete embeddings and aggregating several templates into one group representation. This paper significantly improves that contribution because it jointly learns how to embed and aggregate instead of imposing fixed and hard coded rules. This is demonstrated by exposing the mathematical underpinnings of the learning stage before showing the improvements through an extensive series of experiments targeting face recognition. Overall, experiments show that learning yields an excellent trade-off between security /privacy and verification /identification performances. |
| Tasks | Face Recognition |
| Published | 2019-04-23 |
| URL | http://arxiv.org/abs/1904.10327v1 |
| http://arxiv.org/pdf/1904.10327v1.pdf | |
| PWC | https://paperswithcode.com/paper/privacy-preserving-group-membership |
| Repo | |
| Framework | |
Modelling pressure-Hessian from local velocity gradients information in an incompressible turbulent flow field using deep neural networks
| Title | Modelling pressure-Hessian from local velocity gradients information in an incompressible turbulent flow field using deep neural networks |
| Authors | Nishant Parashar, Sawan S. Sinha, Balaji Srinivasan |
| Abstract | The understanding of the dynamics of the velocity gradients in turbulent flows is critical to understanding various non-linear turbulent processes. The pressure-Hessian and the viscous-Laplacian govern the evolution of the velocity-gradients and are known to be non-local in nature. Over the years, several simplified dynamical models have been proposed that models the viscous-Laplacian and the pressure-Hessian primarily in terms of local velocity gradients information. These models can also serve as closure models for the Lagrangian PDF methods. The recent fluid deformation closure model (RFDM) has been shown to retrieve excellent one-time statistics of the viscous process. However, the pressure-Hessian modelled by the RFDM has various physical limitations. In this work, we first demonstrate the limitations of the RFDM in estimating the pressure-Hessian. Further, we employ a tensor basis neural network (TBNN) to model the pressure-Hessian from the velocity gradient tensor itself. The neural network is trained on high-resolution data obtained from direct numerical simulation (DNS) of isotropic turbulence at Reynolds number of 433 (JHU turbulence database, JHTD). The predictions made by the TBNN are tested against two different isotropic turbulence datasets at Reynolds number of 433 (JHTD) and 315 (UP Madrid turbulence database, UPMTD) and channel flow dataset at Reynolds number of 1000 (UT Texas and JHTD). The evaluation of the neural network output is made in terms of the alignment statistics of the predicted pressure-Hessian eigenvectors with the strain-rate eigenvectors for turbulent isotropic flow as well as channel flow. Our analysis of the predicted solution leads to the discovery of ten unique coefficients of the tensor basis of strain-rate and rotation-rate tensors, the linear combination over which accurately captures key alignment statistics of the pressure-Hessian tensor. |
| Tasks | |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08056v1 |
| https://arxiv.org/pdf/1911.08056v1.pdf | |
| PWC | https://paperswithcode.com/paper/modelling-pressure-hessian-from-local |
| Repo | |
| Framework | |
TBNet:Pulmonary Tuberculosis Diagnosing System using Deep Neural Networks
| Title | TBNet:Pulmonary Tuberculosis Diagnosing System using Deep Neural Networks |
| Authors | Ram Srivatsav Ghorakavi |
| Abstract | Tuberculosis is a deadly infectious disease prevalent around the world. Due to the lack of proper technology in place, the early detection of this disease is unattainable. Also, the available methods to detect Tuberculosis is not up-to a commendable standards due to their dependency on unnecessary features, this make such technology obsolete for a reliable health-care technology. In this paper, I propose a deep-learning based system which diagnoses tuberculosis based on the important features in Chest X-rays along with original chest X-rays. Employing our system will accelerate the process of tuberculosis diagnosis by overcoming the need to perform the time-consuming sputum-based testing method (Diagnostic Microbiology). In contrast to the previous methods \cite{kant2018towards, melendez2016automated}, our work utilizes the state-of-the-art ResNet \cite{he2016deep} with proper data augmentation using traditional robust features like Haar \cite{viola2005detecting,viola2001rapid} and LBP \cite{ojala1994performance,ojala1996comparative}. I observed that such a procedure enhances the rate of tuberculosis detection to a highly satisfactory level. Our work uses the publicly available pulmonary chest X-ray dataset to train our network \cite{jaeger2014two}. Nevertheless, the publicly available dataset is very small and is inadequate to achieve the best accuracy. To overcome this issue I have devised an intuitive feature based data augmentation pipeline. Our approach shall help the deep neural network \cite{lecun2015deep,he2016deep,krizhevsky2012imagenet} to focus its training on tuberculosis affected regions making it more robust and accurate, when compared to other conventional methods that use procedures like mirroring and rotation. By using our simple yet powerful techniques, I observed a 10% boost in performance accuracy. |
| Tasks | Data Augmentation |
| Published | 2019-02-24 |
| URL | http://arxiv.org/abs/1902.08897v1 |
| http://arxiv.org/pdf/1902.08897v1.pdf | |
| PWC | https://paperswithcode.com/paper/tbnetpulmonary-tuberculosis-diagnosing-system |
| Repo | |
| Framework | |
A Locating Model for Pulmonary Tuberculosis Diagnosis in Radiographs
| Title | A Locating Model for Pulmonary Tuberculosis Diagnosis in Radiographs |
| Authors | Jiwei Liu, Junyu Liu, Yang Liu, Rui Yang, Dongjun Lv, Zhengting Cai, Jingjing Cui |
| Abstract | Objective: We propose an end-to-end CNN-based locating model for pulmonary tuberculosis (TB) diagnosis in radiographs. This model makes full use of chest radiograph (X-ray) for its improved accessibility, reduced cost and high accuracy for TB disease. Methods: Several specialized improvements are proposed for detection task in medical field. A false positive (FP) restrictor head is introduced for FP reduction. Anchor-oriented network heads is proposed in the position regression section. An optimization of loss function is designed for hard example mining. Results: The experimental results show that when the threshold of intersection over union (IoU) is set to 0.3, the average precision (AP) of two test data sets provided by different hospitals reaches 0.9023 and 0.9332. Ablation experiments shows that hard example mining and change of regressor heads contribute most in this work, but FP restriction is necessary in a CAD diagnose system. Conclusion: The results prove the high precision and good generalization ability of our proposed model comparing to previous works. Significance: We first make full use of the feature extraction ability of CNNs in TB diagnostic field and make exploration in localization of TB, when the previous works focus on the weaker task of healthy-sick subject classification. |
| Tasks | |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.09900v1 |
| https://arxiv.org/pdf/1910.09900v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-locating-model-for-pulmonary-tuberculosis |
| Repo | |
| Framework | |
GLAD: Learning Sparse Graph Recovery
| Title | GLAD: Learning Sparse Graph Recovery |
| Authors | Harsh Shrivastava, Xinshi Chen, Binghong Chen, Guanghui Lan, Srinvas Aluru, Han Liu, Le Song |
| Abstract | Recovering sparse conditional independence graphs from data is a fundamental problem in machine learning with wide applications. A popular formulation of the problem is an $\ell_1$ regularized maximum likelihood estimation. Many convex optimization algorithms have been designed to solve this formulation to recover the graph structure. Recently, there is a surge of interest to learn algorithms directly based on data, and in this case, learn to map empirical covariance to the sparse precision matrix. However, it is a challenging task in this case, since the symmetric positive definiteness (SPD) and sparsity of the matrix are not easy to enforce in learned algorithms, and a direct mapping from data to precision matrix may contain many parameters. We propose a deep learning architecture, GLAD, which uses an Alternating Minimization (AM) algorithm as our model inductive bias, and learns the model parameters via supervised learning. We show that GLAD learns a very compact and effective model for recovering sparse graphs from data. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://arxiv.org/abs/1906.00271v3 |
| https://arxiv.org/pdf/1906.00271v3.pdf | |
| PWC | https://paperswithcode.com/paper/190600271 |
| Repo | |
| Framework | |
