Paper Group ANR 404
High-dimensional Black-box Optimization via Divide and Approximate Conquer. Weighted bandits or: How bandits learn distorted values that are not expected. Local- and Holistic- Structure Preserving Image Super Resolution via Deep Joint Component Learning. Shape and Centroid Independent Clustring Algorithm for Crowd Management Applications. Topic Mod …
High-dimensional Black-box Optimization via Divide and Approximate Conquer
| Title | High-dimensional Black-box Optimization via Divide and Approximate Conquer |
| Authors | Peng Yang, Ke Tang, Xin Yao |
| Abstract | Divide and Conquer (DC) is conceptually well suited to high-dimensional optimization by decomposing a problem into multiple small-scale sub-problems. However, appealing performance can be seldom observed when the sub-problems are interdependent. This paper suggests that the major difficulty of tackling interdependent sub-problems lies in the precise evaluation of a partial solution (to a sub-problem), which can be overwhelmingly costly and thus makes sub-problems non-trivial to conquer. Thus, we propose an approximation approach, named Divide and Approximate Conquer (DAC), which reduces the cost of partial solution evaluation from exponential time to polynomial time. Meanwhile, the convergence to the global optimum (of the original problem) is still guaranteed. The effectiveness of DAC is demonstrated empirically on two sets of non-separable high-dimensional problems. |
| Tasks | |
| Published | 2016-03-11 |
| URL | http://arxiv.org/abs/1603.03518v2 |
| http://arxiv.org/pdf/1603.03518v2.pdf | |
| PWC | https://paperswithcode.com/paper/high-dimensional-black-box-optimization-via |
| Repo | |
| Framework | |
Weighted bandits or: How bandits learn distorted values that are not expected
| Title | Weighted bandits or: How bandits learn distorted values that are not expected |
| Authors | Aditya Gopalan, L. A. Prashanth, Michael Fu, Steve Marcus |
| Abstract | Motivated by models of human decision making proposed to explain commonly observed deviations from conventional expected value preferences, we formulate two stochastic multi-armed bandit problems with distorted probabilities on the cost distributions: the classic $K$-armed bandit and the linearly parameterized bandit. In both settings, we propose algorithms that are inspired by Upper Confidence Bound (UCB), incorporate cost distortions, and exhibit sublinear regret assuming \holder continuous weight distortion functions. For the $K$-armed setting, we show that the algorithm, called W-UCB, achieves problem-dependent regret $O(L^2 M^2 \log n/ \Delta^{\frac{2}{\alpha}-1})$, where $n$ is the number of plays, $\Delta$ is the gap in distorted expected value between the best and next best arm, $L$ and $\alpha$ are the H"{o}lder constants for the distortion function, and $M$ is an upper bound on costs, and a problem-independent regret bound of $O((KL^2M^2)^{\alpha/2}n^{(2-\alpha)/2})$. We also present a matching lower bound on the regret, showing that the regret of W-UCB is essentially unimprovable over the class of H"{o}lder-continuous weight distortions. For the linearly parameterized setting, we develop a new algorithm, a variant of the Optimism in the Face of Uncertainty Linear bandit (OFUL) algorithm called WOFUL (Weight-distorted OFUL), and show that it has regret $O(d\sqrt{n} ; \mbox{polylog}(n))$ with high probability, for sub-Gaussian cost distributions. Finally, numerical examples demonstrate the advantages resulting from using distortion-aware learning algorithms. |
| Tasks | Decision Making |
| Published | 2016-11-30 |
| URL | http://arxiv.org/abs/1611.10283v1 |
| http://arxiv.org/pdf/1611.10283v1.pdf | |
| PWC | https://paperswithcode.com/paper/weighted-bandits-or-how-bandits-learn |
| Repo | |
| Framework | |
Local- and Holistic- Structure Preserving Image Super Resolution via Deep Joint Component Learning
| Title | Local- and Holistic- Structure Preserving Image Super Resolution via Deep Joint Component Learning |
| Authors | Yukai Shi, Keze Wang, Li Xu, Liang Lin |
| Abstract | Recently, machine learning based single image super resolution (SR) approaches focus on jointly learning representations for high-resolution (HR) and low-resolution (LR) image patch pairs to improve the quality of the super-resolved images. However, due to treat all image pixels equally without considering the salient structures, these approaches usually fail to produce visual pleasant images with sharp edges and fine details. To address this issue, in this work we present a new novel SR approach, which replaces the main building blocks of the classical interpolation pipeline by a flexible, content-adaptive deep neural networks. In particular, two well-designed structure-aware components, respectively capturing local- and holistic- image contents, are naturally incorporated into the fully-convolutional representation learning to enhance the image sharpness and naturalness. Extensively evaluations on several standard benchmarks (e.g., Set5, Set14 and BSD200) demonstrate that our approach can achieve superior results, especially on the image with salient structures, over many existing state-of-the-art SR methods under both quantitative and qualitative measures. |
| Tasks | Image Super-Resolution, Representation Learning, Super-Resolution |
| Published | 2016-07-25 |
| URL | http://arxiv.org/abs/1607.07220v1 |
| http://arxiv.org/pdf/1607.07220v1.pdf | |
| PWC | https://paperswithcode.com/paper/local-and-holistic-structure-preserving-image |
| Repo | |
| Framework | |
Shape and Centroid Independent Clustring Algorithm for Crowd Management Applications
| Title | Shape and Centroid Independent Clustring Algorithm for Crowd Management Applications |
| Authors | Yasser Mohammad Seddiq, A. A. Alharbiy, Moayyad Hamza Ghunaim |
| Abstract | Clustering techniques play an important role in data mining and its related applications. Among the challenging applications that require robust and real-time processing are crowd management and group trajectory applications. In this paper, a robust and low-complexity clustering algorithm is proposed. It is capable of processing data in a manner that is shape and centroid independent. The algorithm is of low complexity due to the novel technique to compute the matrix power. The algorithm was tested on real and synthetic data and test results are reported. |
| Tasks | |
| Published | 2016-08-02 |
| URL | http://arxiv.org/abs/1608.00785v1 |
| http://arxiv.org/pdf/1608.00785v1.pdf | |
| PWC | https://paperswithcode.com/paper/shape-and-centroid-independent-clustring |
| Repo | |
| Framework | |
Topic Model Based Multi-Label Classification from the Crowd
| Title | Topic Model Based Multi-Label Classification from the Crowd |
| Authors | Divya Padmanabhan, Satyanath Bhat, Shirish Shevade, Y. Narahari |
| Abstract | Multi-label classification is a common supervised machine learning problem where each instance is associated with multiple classes. The key challenge in this problem is learning the correlations between the classes. An additional challenge arises when the labels of the training instances are provided by noisy, heterogeneous crowdworkers with unknown qualities. We first assume labels from a perfect source and propose a novel topic model where the present as well as the absent classes generate the latent topics and hence the words. We non-trivially extend our topic model to the scenario where the labels are provided by noisy crowdworkers. Extensive experimentation on real world datasets reveals the superior performance of the proposed model. The proposed model learns the qualities of the annotators as well, even with minimal training data. |
| Tasks | Multi-Label Classification |
| Published | 2016-04-04 |
| URL | http://arxiv.org/abs/1604.00783v1 |
| http://arxiv.org/pdf/1604.00783v1.pdf | |
| PWC | https://paperswithcode.com/paper/topic-model-based-multi-label-classification |
| Repo | |
| Framework | |
On a Well-behaved Relational Generalisation of Rough Set Approximations
| Title | On a Well-behaved Relational Generalisation of Rough Set Approximations |
| Authors | Alexa Gopaulsingh |
| Abstract | We examine non-dual relational extensions of rough set approximations and find an extension which satisfies surprisingly many of the usual rough set properties. We then use this definition to give an explanation for an observation made by Samanta and Chakraborty in their recent paper [P. Samanta and M.K. Chakraborty. Interface of rough set systems and modal logics: A survey. Transactions on Rough Sets XIX, pages 114-137, 2015]. |
| Tasks | |
| Published | 2016-12-05 |
| URL | http://arxiv.org/abs/1612.01857v2 |
| http://arxiv.org/pdf/1612.01857v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-a-well-behaved-relational-generalisation |
| Repo | |
| Framework | |
Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner
| Title | Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner |
| Authors | Emmanuel Dupoux |
| Abstract | During their first years of life, infants learn the language(s) of their environment at an amazing speed despite large cross cultural variations in amount and complexity of the available language input. Understanding this simple fact still escapes current cognitive and linguistic theories. Recently, spectacular progress in the engineering science, notably, machine learning and wearable technology, offer the promise of revolutionizing the study of cognitive development. Machine learning offers powerful learning algorithms that can achieve human-like performance on many linguistic tasks. Wearable sensors can capture vast amounts of data, which enable the reconstruction of the sensory experience of infants in their natural environment. The project of ‘reverse engineering’ language development, i.e., of building an effective system that mimics infant’s achievements appears therefore to be within reach. Here, we analyze the conditions under which such a project can contribute to our scientific understanding of early language development. We argue that instead of defining a sub-problem or simplifying the data, computational models should address the full complexity of the learning situation, and take as input the raw sensory signals available to infants. This implies that (1) accessible but privacy-preserving repositories of home data be setup and widely shared, and (2) models be evaluated at different linguistic levels through a benchmark of psycholinguist tests that can be passed by machines and humans alike, (3) linguistically and psychologically plausible learning architectures be scaled up to real data using probabilistic/optimization principles from machine learning. We discuss the feasibility of this approach and present preliminary results. |
| Tasks | |
| Published | 2016-07-29 |
| URL | http://arxiv.org/abs/1607.08723v4 |
| http://arxiv.org/pdf/1607.08723v4.pdf | |
| PWC | https://paperswithcode.com/paper/cognitive-science-in-the-era-of-artificial |
| Repo | |
| Framework | |
Keyphrase Annotation with Graph Co-Ranking
| Title | Keyphrase Annotation with Graph Co-Ranking |
| Authors | Adrien Bougouin, Florian Boudin, Béatrice Daille |
| Abstract | Keyphrase annotation is the task of identifying textual units that represent the main content of a document. Keyphrase annotation is either carried out by extracting the most important phrases from a document, keyphrase extraction, or by assigning entries from a controlled domain-specific vocabulary, keyphrase assignment. Assignment methods are generally more reliable. They provide better-formed keyphrases, as well as keyphrases that do not occur in the document. But they are often silent on the contrary of extraction methods that do not depend on manually built resources. This paper proposes a new method to perform both keyphrase extraction and keyphrase assignment in an integrated and mutual reinforcing manner. Experiments have been carried out on datasets covering different domains of humanities and social sciences. They show statistically significant improvements compared to both keyphrase extraction and keyphrase assignment state-of-the art methods. |
| Tasks | |
| Published | 2016-11-07 |
| URL | http://arxiv.org/abs/1611.02007v1 |
| http://arxiv.org/pdf/1611.02007v1.pdf | |
| PWC | https://paperswithcode.com/paper/keyphrase-annotation-with-graph-co-ranking |
| Repo | |
| Framework | |
Differentiable Pooling for Unsupervised Acoustic Model Adaptation
| Title | Differentiable Pooling for Unsupervised Acoustic Model Adaptation |
| Authors | Pawel Swietojanski, Steve Renals |
| Abstract | We present a deep neural network (DNN) acoustic model that includes parametrised and differentiable pooling operators. Unsupervised acoustic model adaptation is cast as the problem of updating the decision boundaries implemented by each pooling operator. In particular, we experiment with two types of pooling parametrisations: learned $L_p$-norm pooling and weighted Gaussian pooling, in which the weights of both operators are treated as speaker-dependent. We perform investigations using three different large vocabulary speech recognition corpora: AMI meetings, TED talks and Switchboard conversational telephone speech. We demonstrate that differentiable pooling operators provide a robust and relatively low-dimensional way to adapt acoustic models, with relative word error rates reductions ranging from 5–20% with respect to unadapted systems, which themselves are better than the baseline fully-connected DNN-based acoustic models. We also investigate how the proposed techniques work under various adaptation conditions including the quality of adaptation data and complementarity to other feature- and model-space adaptation methods, as well as providing an analysis of the characteristics of each of the proposed approaches. |
| Tasks | Large Vocabulary Continuous Speech Recognition, Speech Recognition |
| Published | 2016-03-31 |
| URL | http://arxiv.org/abs/1603.09630v2 |
| http://arxiv.org/pdf/1603.09630v2.pdf | |
| PWC | https://paperswithcode.com/paper/differentiable-pooling-for-unsupervised |
| Repo | |
| Framework | |
Recurrent Deep Stacking Networks for Speech Recognition
| Title | Recurrent Deep Stacking Networks for Speech Recognition |
| Authors | Peidong Wang, Zhongqiu Wang, Deliang Wang |
| Abstract | This paper presented our work on applying Recurrent Deep Stacking Networks (RDSNs) to Robust Automatic Speech Recognition (ASR) tasks. In the paper, we also proposed a more efficient yet comparable substitute to RDSN, Bi- Pass Stacking Network (BPSN). The main idea of these two models is to add phoneme-level information into acoustic models, transforming an acoustic model to the combination of an acoustic model and a phoneme-level N-gram model. Experiments showed that RDSN and BPsn can substantially improve the performances over conventional DNNs. |
| Tasks | Speech Recognition |
| Published | 2016-12-14 |
| URL | http://arxiv.org/abs/1612.04675v1 |
| http://arxiv.org/pdf/1612.04675v1.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-deep-stacking-networks-for-speech |
| Repo | |
| Framework | |
Parallel Strategies Selection
| Title | Parallel Strategies Selection |
| Authors | Anthony Palmieri, Jean-Charles Régin, Pierre Schaus |
| Abstract | We consider the problem of selecting the best variable-value strategy for solving a given problem in constraint programming. We show that the recent Embarrassingly Parallel Search method (EPS) can be used for this purpose. EPS proposes to solve a problem by decomposing it in a lot of subproblems and to give them on-demand to workers which run in parallel. Our method uses a part of these subproblems as a simple sample as defined in statistics for comparing some strategies in order to select the most promising one that will be used for solving the remaining subproblems. For each subproblem of the sample, the parallelism helps us to control the running time of the strategies because it gives us the possibility to introduce timeouts by stopping a strategy when it requires more than twice the time of the best one. Thus, we can deal with the great disparity in solving times for the strategies. The selections we made are based on the Wilcoxon signed rank tests because no assumption has to be made on the distribution of the solving times and because these tests can deal with the censored data that we obtain after introducing timeouts. The experiments we performed on a set of classical benchmarks for satisfaction and optimization problems show that our method obtain good performance by selecting almost all the time the best variable-value strategy and by almost never choosing a variable-value strategy which is dramatically slower than the best one. Our method also outperforms the portfolio approach consisting in running some strategies in parallel and is competitive with the multi armed bandit framework. |
| Tasks | |
| Published | 2016-04-21 |
| URL | http://arxiv.org/abs/1604.06484v1 |
| http://arxiv.org/pdf/1604.06484v1.pdf | |
| PWC | https://paperswithcode.com/paper/parallel-strategies-selection |
| Repo | |
| Framework | |
How Transferable are Neural Networks in NLP Applications?
| Title | How Transferable are Neural Networks in NLP Applications? |
| Authors | Lili Mou, Zhao Meng, Rui Yan, Ge Li, Yan Xu, Lu Zhang, Zhi Jin |
| Abstract | Transfer learning is aimed to make use of valuable knowledge in a source domain to help model performance in a target domain. It is particularly important to neural networks, which are very likely to be overfitting. In some fields like image processing, many studies have shown the effectiveness of neural network-based transfer learning. For neural NLP, however, existing studies have only casually applied transfer learning, and conclusions are inconsistent. In this paper, we conduct systematic case studies and provide an illuminating picture on the transferability of neural networks in NLP. |
| Tasks | Transfer Learning |
| Published | 2016-03-19 |
| URL | http://arxiv.org/abs/1603.06111v2 |
| http://arxiv.org/pdf/1603.06111v2.pdf | |
| PWC | https://paperswithcode.com/paper/how-transferable-are-neural-networks-in-nlp |
| Repo | |
| Framework | |
Translating Bayesian Networks into Entity Relationship Models, Extended Version
| Title | Translating Bayesian Networks into Entity Relationship Models, Extended Version |
| Authors | Frank Rosner, Alexander Hinneburg |
| Abstract | Big data analytics applications drive the convergence of data management and machine learning. But there is no conceptual language available that is spoken in both worlds. The main contribution of the paper is a method to translate Bayesian networks, a main conceptual language for probabilistic graphical models, into usable entity relationship models. The transformed representation of a Bayesian network leaves out mathematical details about probabilistic relationships but unfolds all information relevant for data management tasks. As a real world example, we present the TopicExplorer system that uses Bayesian topic models as a core component in an interactive, database-supported web application. Last, we sketch a conceptual framework that eases machine learning specific development tasks while building big data analytics applications. |
| Tasks | Topic Models |
| Published | 2016-07-08 |
| URL | http://arxiv.org/abs/1607.02399v1 |
| http://arxiv.org/pdf/1607.02399v1.pdf | |
| PWC | https://paperswithcode.com/paper/translating-bayesian-networks-into-entity |
| Repo | |
| Framework | |
Image segmentation based on histogram of depth and an application in driver distraction detection
| Title | Image segmentation based on histogram of depth and an application in driver distraction detection |
| Authors | Tran Hiep Dinh, Minh Trien Pham, Manh Duong Phung, Duc Manh Nguyen, Van Manh Hoang, Quang Vinh Tran |
| Abstract | This study proposes an approach to segment human object from a depth image based on histogram of depth values. The region of interest is first extracted based on a predefined threshold for histogram regions. A region growing process is then employed to separate multiple human bodies with the same depth interval. Our contribution is the identification of an adaptive growth threshold based on the detected histogram region. To demonstrate the effectiveness of the proposed method, an application in driver distraction detection was introduced. After successfully extracting the driver’s position inside the car, we came up with a simple solution to track the driver motion. With the analysis of the difference between initial and current frame, a change of cluster position or depth value in the interested region, which cross the preset threshold, is considered as a distracted activity. The experiment results demonstrated the success of the algorithm in detecting typical distracted driving activities such as using phone for calling or texting, adjusting internal devices and drinking in real time. |
| Tasks | Semantic Segmentation |
| Published | 2016-09-01 |
| URL | http://arxiv.org/abs/1609.00096v1 |
| http://arxiv.org/pdf/1609.00096v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-segmentation-based-on-histogram-of |
| Repo | |
| Framework | |
VolumeDeform: Real-time Volumetric Non-rigid Reconstruction
| Title | VolumeDeform: Real-time Volumetric Non-rigid Reconstruction |
| Authors | Matthias Innmann, Michael Zollhöfer, Matthias Nießner, Christian Theobalt, Marc Stamminger |
| Abstract | We present a novel approach for the reconstruction of dynamic geometric shapes using a single hand-held consumer-grade RGB-D sensor at real-time rates. Our method does not require a pre-defined shape template to start with and builds up the scene model from scratch during the scanning process. Geometry and motion are parameterized in a unified manner by a volumetric representation that encodes a distance field of the surface geometry as well as the non-rigid space deformation. Motion tracking is based on a set of extracted sparse color features in combination with a dense depth-based constraint formulation. This enables accurate tracking and drastically reduces drift inherent to standard model-to-depth alignment. We cast finding the optimal deformation of space as a non-linear regularized variational optimization problem by enforcing local smoothness and proximity to the input constraints. The problem is tackled in real-time at the camera’s capture rate using a data-parallel flip-flop optimization strategy. Our results demonstrate robust tracking even for fast motion and scenes that lack geometric features. |
| Tasks | |
| Published | 2016-03-27 |
| URL | http://arxiv.org/abs/1603.08161v2 |
| http://arxiv.org/pdf/1603.08161v2.pdf | |
| PWC | https://paperswithcode.com/paper/volumedeform-real-time-volumetric-non-rigid |
| Repo | |
| Framework | |
