Paper Group ANR 264
Local Minimax Complexity of Stochastic Convex Optimization. Distributed Processing of Biosignal-Database for Emotion Recognition with Mahout. Automatic Extraction of Causal Relations from Natural Language Texts: A Comprehensive Survey. Hybrid CPU-GPU Framework for Network Motifs. Optimal Binary Autoencoding with Pairwise Correlations. Multi-task an …
Local Minimax Complexity of Stochastic Convex Optimization
| Title | Local Minimax Complexity of Stochastic Convex Optimization |
| Authors | Yuancheng Zhu, Sabyasachi Chatterjee, John Duchi, John Lafferty |
| Abstract | We extend the traditional worst-case, minimax analysis of stochastic convex optimization by introducing a localized form of minimax complexity for individual functions. Our main result gives function-specific lower and upper bounds on the number of stochastic subgradient evaluations needed to optimize either the function or its “hardest local alternative” to a given numerical precision. The bounds are expressed in terms of a localized and computational analogue of the modulus of continuity that is central to statistical minimax analysis. We show how the computational modulus of continuity can be explicitly calculated in concrete cases, and relates to the curvature of the function at the optimum. We also prove a superefficiency result that demonstrates it is a meaningful benchmark, acting as a computational analogue of the Fisher information in statistical estimation. The nature and practical implications of the results are demonstrated in simulations. |
| Tasks | |
| Published | 2016-05-24 |
| URL | http://arxiv.org/abs/1605.07596v3 |
| http://arxiv.org/pdf/1605.07596v3.pdf | |
| PWC | https://paperswithcode.com/paper/local-minimax-complexity-of-stochastic-convex |
| Repo | |
| Framework | |
Distributed Processing of Biosignal-Database for Emotion Recognition with Mahout
| Title | Distributed Processing of Biosignal-Database for Emotion Recognition with Mahout |
| Authors | Varvara Kollia, Oguz H. Elibol |
| Abstract | This paper investigates the use of distributed processing on the problem of emotion recognition from physiological sensors using a popular machine learning library on distributed mode. Specifically, we run a random forests classifier on the biosignal-data, which have been pre-processed to form exclusive groups in an unsupervised fashion, on a Cloudera cluster using Mahout. The use of distributed processing significantly reduces the time required for the offline training of the classifier, enabling processing of large physiological datasets through many iterations. |
| Tasks | Emotion Recognition |
| Published | 2016-09-09 |
| URL | http://arxiv.org/abs/1609.02631v1 |
| http://arxiv.org/pdf/1609.02631v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-processing-of-biosignal-database |
| Repo | |
| Framework | |
Automatic Extraction of Causal Relations from Natural Language Texts: A Comprehensive Survey
| Title | Automatic Extraction of Causal Relations from Natural Language Texts: A Comprehensive Survey |
| Authors | Nabiha Asghar |
| Abstract | Automatic extraction of cause-effect relationships from natural language texts is a challenging open problem in Artificial Intelligence. Most of the early attempts at its solution used manually constructed linguistic and syntactic rules on small and domain-specific data sets. However, with the advent of big data, the availability of affordable computing power and the recent popularization of machine learning, the paradigm to tackle this problem has slowly shifted. Machines are now expected to learn generic causal extraction rules from labelled data with minimal supervision, in a domain independent-manner. In this paper, we provide a comprehensive survey of causal relation extraction techniques from both paradigms, and analyse their relative strengths and weaknesses, with recommendations for future work. |
| Tasks | Relation Extraction |
| Published | 2016-05-25 |
| URL | http://arxiv.org/abs/1605.07895v1 |
| http://arxiv.org/pdf/1605.07895v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-extraction-of-causal-relations-from-1 |
| Repo | |
| Framework | |
Hybrid CPU-GPU Framework for Network Motifs
| Title | Hybrid CPU-GPU Framework for Network Motifs |
| Authors | Ryan A. Rossi, Rong Zhou |
| Abstract | Massively parallel architectures such as the GPU are becoming increasingly important due to the recent proliferation of data. In this paper, we propose a key class of hybrid parallel graphlet algorithms that leverages multiple CPUs and GPUs simultaneously for computing k-vertex induced subgraph statistics (called graphlets). In addition to the hybrid multi-core CPU-GPU framework, we also investigate single GPU methods (using multiple cores) and multi-GPU methods that leverage all available GPUs simultaneously for computing induced subgraph statistics. Both methods leverage GPU devices only, whereas the hybrid multi-core CPU-GPU framework leverages all available multi-core CPUs and multiple GPUs for computing graphlets in large networks. Compared to recent approaches, our methods are orders of magnitude faster, while also more cost effective enjoying superior performance per capita and per watt. In particular, the methods are up to 300 times faster than the recent state-of-the-art method. To the best of our knowledge, this is the first work to leverage multiple CPUs and GPUs simultaneously for computing induced subgraph statistics. |
| Tasks | |
| Published | 2016-08-18 |
| URL | http://arxiv.org/abs/1608.05138v2 |
| http://arxiv.org/pdf/1608.05138v2.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-cpu-gpu-framework-for-network-motifs |
| Repo | |
| Framework | |
Optimal Binary Autoencoding with Pairwise Correlations
| Title | Optimal Binary Autoencoding with Pairwise Correlations |
| Authors | Akshay Balsubramani |
| Abstract | We formulate learning of a binary autoencoder as a biconvex optimization problem which learns from the pairwise correlations between encoded and decoded bits. Among all possible algorithms that use this information, ours finds the autoencoder that reconstructs its inputs with worst-case optimal loss. The optimal decoder is a single layer of artificial neurons, emerging entirely from the minimax loss minimization, and with weights learned by convex optimization. All this is reflected in competitive experimental results, demonstrating that binary autoencoding can be done efficiently by conveying information in pairwise correlations in an optimal fashion. |
| Tasks | |
| Published | 2016-11-07 |
| URL | http://arxiv.org/abs/1611.02268v1 |
| http://arxiv.org/pdf/1611.02268v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-binary-autoencoding-with-pairwise |
| Repo | |
| Framework | |
Multi-task and Lifelong Learning of Kernels
| Title | Multi-task and Lifelong Learning of Kernels |
| Authors | Anastasia Pentina, Shai Ben-David |
| Abstract | We consider a problem of learning kernels for use in SVM classification in the multi-task and lifelong scenarios and provide generalization bounds on the error of a large margin classifier. Our results show that, under mild conditions on the family of kernels used for learning, solving several related tasks simultaneously is beneficial over single task learning. In particular, as the number of observed tasks grows, assuming that in the considered family of kernels there exists one that yields low approximation error on all tasks, the overhead associated with learning such a kernel vanishes and the complexity converges to that of learning when this good kernel is given to the learner. |
| Tasks | |
| Published | 2016-02-21 |
| URL | http://arxiv.org/abs/1602.06531v2 |
| http://arxiv.org/pdf/1602.06531v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-task-and-lifelong-learning-of-kernels |
| Repo | |
| Framework | |
Extended Gauss-Newton and Gauss-Newton-ADMM Algorithms for Low-Rank Matrix Optimization
| Title | Extended Gauss-Newton and Gauss-Newton-ADMM Algorithms for Low-Rank Matrix Optimization |
| Authors | Quoc Tran-Dinh, Zheqi Zhang |
| Abstract | We develop a generic Gauss-Newton (GN) framework for solving a class of nonconvex optimization problems involving low-rank matrix variables. As opposed to standard Gauss-Newton method, our framework allows one to handle general smooth convex cost function via its surrogate. The main complexity-per-iteration consists of the inverse of two rank-size matrices and at most six small matrix multiplications to compute a closed form Gauss-Newton direction, and a backtracking linesearch. We show, under mild conditions, that the proposed algorithm globally and locally converges to a stationary point of the original nonconvex problem. We also show empirically that the Gauss-Newton algorithm achieves much higher accurate solutions compared to the well studied alternating direction method (ADM). Then, we specify our Gauss-Newton framework to handle the symmetric case and prove its convergence, where ADM is not applicable without lifting variables. Next, we incorporate our Gauss-Newton scheme into the alternating direction method of multipliers (ADMM) to design a GN-ADMM algorithm for solving the low-rank optimization problem. We prove that, under mild conditions and a proper choice of the penalty parameter, our GN-ADMM globally converges to a stationary point of the original problem. Finally, we apply our algorithms to solve several problems in practice such as low-rank approximation, matrix completion, robust low-rank matrix recovery, and matrix recovery in quantum tomography. The numerical experiments provide encouraging results to motivate the use of nonconvex optimization. |
| Tasks | Matrix Completion |
| Published | 2016-06-10 |
| URL | http://arxiv.org/abs/1606.03358v2 |
| http://arxiv.org/pdf/1606.03358v2.pdf | |
| PWC | https://paperswithcode.com/paper/extended-gauss-newton-and-gauss-newton-admm |
| Repo | |
| Framework | |
Should I use TensorFlow
| Title | Should I use TensorFlow |
| Authors | Martin Schrimpf |
| Abstract | Google’s Machine Learning framework TensorFlow was open-sourced in November 2015 [1] and has since built a growing community around it. TensorFlow is supposed to be flexible for research purposes while also allowing its models to be deployed productively. This work is aimed towards people with experience in Machine Learning considering whether they should use TensorFlow in their environment. Several aspects of the framework important for such a decision are examined, such as the heterogenity, extensibility and its computation graph. A pure Python implementation of linear classification is compared with an implementation utilizing TensorFlow. I also contrast TensorFlow to other popular frameworks with respect to modeling capability, deployment and performance and give a brief description of the current adaption of the framework. |
| Tasks | |
| Published | 2016-11-27 |
| URL | http://arxiv.org/abs/1611.08903v1 |
| http://arxiv.org/pdf/1611.08903v1.pdf | |
| PWC | https://paperswithcode.com/paper/should-i-use-tensorflow |
| Repo | |
| Framework | |
Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Tracking
| Title | Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Tracking |
| Authors | Guanghan Ning, Zhi Zhang, Chen Huang, Zhihai He, Xiaobo Ren, Haohong Wang |
| Abstract | In this paper, we develop a new approach of spatially supervised recurrent convolutional neural networks for visual object tracking. Our recurrent convolutional network exploits the history of locations as well as the distinctive visual features learned by the deep neural networks. Inspired by recent bounding box regression methods for object detection, we study the regression capability of Long Short-Term Memory (LSTM) in the temporal domain, and propose to concatenate high-level visual features produced by convolutional networks with region information. In contrast to existing deep learning based trackers that use binary classification for region candidates, we use regression for direct prediction of the tracking locations both at the convolutional layer and at the recurrent unit. Our extensive experimental results and performance comparison with state-of-the-art tracking methods on challenging benchmark video tracking datasets shows that our tracker is more accurate and robust while maintaining low computational cost. For most test video sequences, our method achieves the best tracking performance, often outperforms the second best by a large margin. |
| Tasks | Object Detection, Object Tracking, Visual Object Tracking |
| Published | 2016-07-19 |
| URL | http://arxiv.org/abs/1607.05781v1 |
| http://arxiv.org/pdf/1607.05781v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatially-supervised-recurrent-convolutional |
| Repo | |
| Framework | |
Marr Revisited: 2D-3D Alignment via Surface Normal Prediction
| Title | Marr Revisited: 2D-3D Alignment via Surface Normal Prediction |
| Authors | Aayush Bansal, Bryan Russell, Abhinav Gupta |
| Abstract | We introduce an approach that leverages surface normal predictions, along with appearance cues, to retrieve 3D models for objects depicted in 2D still images from a large CAD object library. Critical to the success of our approach is the ability to recover accurate surface normals for objects in the depicted scene. We introduce a skip-network model built on the pre-trained Oxford VGG convolutional neural network (CNN) for surface normal prediction. Our model achieves state-of-the-art accuracy on the NYUv2 RGB-D dataset for surface normal prediction, and recovers fine object detail compared to previous methods. Furthermore, we develop a two-stream network over the input image and predicted surface normals that jointly learns pose and style for CAD model retrieval. When using the predicted surface normals, our two-stream network matches prior work using surface normals computed from RGB-D images on the task of pose prediction, and achieves state of the art when using RGB-D input. Finally, our two-stream network allows us to retrieve CAD models that better match the style and pose of a depicted object compared with baseline approaches. |
| Tasks | Pose Prediction |
| Published | 2016-04-05 |
| URL | http://arxiv.org/abs/1604.01347v1 |
| http://arxiv.org/pdf/1604.01347v1.pdf | |
| PWC | https://paperswithcode.com/paper/marr-revisited-2d-3d-alignment-via-surface |
| Repo | |
| Framework | |
Learning feed-forward one-shot learners
| Title | Learning feed-forward one-shot learners |
| Authors | Luca Bertinetto, João F. Henriques, Jack Valmadre, Philip H. S. Torr, Andrea Vedaldi |
| Abstract | One-shot learning is usually tackled by using generative models or discriminative embeddings. Discriminative methods based on deep learning, which are very effective in other learning scenarios, are ill-suited for one-shot learning as they need large amounts of training data. In this paper, we propose a method to learn the parameters of a deep model in one shot. We construct the learner as a second deep network, called a learnet, which predicts the parameters of a pupil network from a single exemplar. In this manner we obtain an efficient feed-forward one-shot learner, trained end-to-end by minimizing a one-shot classification objective in a learning to learn formulation. In order to make the construction feasible, we propose a number of factorizations of the parameters of the pupil network. We demonstrate encouraging results by learning characters from single exemplars in Omniglot, and by tracking visual objects from a single initial exemplar in the Visual Object Tracking benchmark. |
| Tasks | Object Tracking, Omniglot, One-Shot Learning, Visual Object Tracking |
| Published | 2016-06-16 |
| URL | http://arxiv.org/abs/1606.05233v1 |
| http://arxiv.org/pdf/1606.05233v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-feed-forward-one-shot-learners |
| Repo | |
| Framework | |
Multi-modal Tracking for Object based SLAM
| Title | Multi-modal Tracking for Object based SLAM |
| Authors | Prateek Singhal, Ruffin White, Henrik Christensen |
| Abstract | We present an on-line 3D visual object tracking framework for monocular cameras by incorporating spatial knowledge and uncertainty from semantic mapping along with high frequency measurements from visual odometry. Using a combination of vision and odometry that are tightly integrated we can increase the overall performance of object based tracking for semantic mapping. We present a framework for integration of the two data-sources into a coherent framework through information based fusion/arbitration. We demonstrate the framework in the context of OmniMapper[1] and present results on 6 challenging sequences over multiple objects compared to data obtained from a motion capture systems. We are able to achieve a mean error of 0.23m for per frame tracking showing 9% relative error less than state of the art tracker. |
| Tasks | Motion Capture, Object Tracking, Visual Object Tracking, Visual Odometry |
| Published | 2016-03-14 |
| URL | http://arxiv.org/abs/1603.04117v1 |
| http://arxiv.org/pdf/1603.04117v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-modal-tracking-for-object-based-slam |
| Repo | |
| Framework | |
Bayesian Learning of Dynamic Multilayer Networks
| Title | Bayesian Learning of Dynamic Multilayer Networks |
| Authors | Daniele Durante, Nabanita Mukherjee, Rebecca C. Steorts |
| Abstract | A plethora of networks is being collected in a growing number of fields, including disease transmission, international relations, social interactions, and others. As data streams continue to grow, the complexity associated with these highly multidimensional connectivity data presents novel challenges. In this paper, we focus on the time-varying interconnections among a set of actors in multiple contexts, called layers. Current literature lacks flexible statistical models for dynamic multilayer networks, which can enhance quality in inference and prediction by efficiently borrowing information within each network, across time, and between layers. Motivated by this gap, we develop a Bayesian nonparametric model leveraging latent space representations. Our formulation characterizes the edge probabilities as a function of shared and layer-specific actors positions in a latent space, with these positions changing in time via Gaussian processes. This representation facilitates dimensionality reduction and incorporates different sources of information in the observed data. In addition, we obtain tractable procedures for posterior computation, inference, and prediction. We provide theoretical results on the flexibility of our model. Our methods are tested on simulations and infection studies monitoring dynamic face-to-face contacts among individuals in multiple days, where we perform better than current methods in inference and prediction. |
| Tasks | Dimensionality Reduction, Gaussian Processes |
| Published | 2016-08-07 |
| URL | http://arxiv.org/abs/1608.02209v2 |
| http://arxiv.org/pdf/1608.02209v2.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-learning-of-dynamic-multilayer |
| Repo | |
| Framework | |
Siamese Instance Search for Tracking
| Title | Siamese Instance Search for Tracking |
| Authors | Ran Tao, Efstratios Gavves, Arnold W. M. Smeulders |
| Abstract | In this paper we present a tracker, which is radically different from state-of-the-art trackers: we apply no model updating, no occlusion detection, no combination of trackers, no geometric matching, and still deliver state-of-the-art tracking performance, as demonstrated on the popular online tracking benchmark (OTB) and six very challenging YouTube videos. The presented tracker simply matches the initial patch of the target in the first frame with candidates in a new frame and returns the most similar patch by a learned matching function. The strength of the matching function comes from being extensively trained generically, i.e., without any data of the target, using a Siamese deep neural network, which we design for tracking. Once learned, the matching function is used as is, without any adapting, to track previously unseen targets. It turns out that the learned matching function is so powerful that a simple tracker built upon it, coined Siamese INstance search Tracker, SINT, which only uses the original observation of the target from the first frame, suffices to reach state-of-the-art performance. Further, we show the proposed tracker even allows for target re-identification after the target was absent for a complete video shot. |
| Tasks | Instance Search |
| Published | 2016-05-19 |
| URL | http://arxiv.org/abs/1605.05863v1 |
| http://arxiv.org/pdf/1605.05863v1.pdf | |
| PWC | https://paperswithcode.com/paper/siamese-instance-search-for-tracking |
| Repo | |
| Framework | |
LIME: A Method for Low-light IMage Enhancement
| Title | LIME: A Method for Low-light IMage Enhancement |
| Authors | Xiaojie Guo |
| Abstract | When one captures images in low-light conditions, the images often suffer from low visibility. This poor quality may significantly degrade the performance of many computer vision and multimedia algorithms that are primarily designed for high-quality inputs. In this paper, we propose a very simple and effective method, named as LIME, to enhance low-light images. More concretely, the illumination of each pixel is first estimated individually by finding the maximum value in R, G and B channels. Further, we refine the initial illumination map by imposing a structure prior on it, as the final illumination map. Having the well-constructed illumination map, the enhancement can be achieved accordingly. Experiments on a number of challenging real-world low-light images are present to reveal the efficacy of our LIME and show its superiority over several state-of-the-arts. |
| Tasks | Image Enhancement, Low-Light Image Enhancement |
| Published | 2016-05-17 |
| URL | http://arxiv.org/abs/1605.05034v3 |
| http://arxiv.org/pdf/1605.05034v3.pdf | |
| PWC | https://paperswithcode.com/paper/lime-a-method-for-low-light-image-enhancement |
| Repo | |
| Framework | |
