Paper Group ANR 119
Nonparametric independence testing via mutual information. Deep API Programmer: Learning to Program with APIs. Specious rules: an efficient and effective unifying method for removing misleading and uninformative patterns in association rule mining. A unified deep artificial neural network approach to partial differential equations in complex geomet …
Nonparametric independence testing via mutual information
| Title | Nonparametric independence testing via mutual information |
| Authors | Thomas B. Berrett, Richard J. Samworth |
| Abstract | We propose a test of independence of two multivariate random vectors, given a sample from the underlying population. Our approach, which we call MINT, is based on the estimation of mutual information, whose decomposition into joint and marginal entropies facilitates the use of recently-developed efficient entropy estimators derived from nearest neighbour distances. The proposed critical values, which may be obtained from simulation (in the case where one marginal is known) or resampling, guarantee that the test has nominal size, and we provide local power analyses, uniformly over classes of densities whose mutual information satisfies a lower bound. Our ideas may be extended to provide a new goodness-of-fit tests of normal linear models based on assessing the independence of our vector of covariates and an appropriately-defined notion of an error vector. The theory is supported by numerical studies on both simulated and real data. |
| Tasks | |
| Published | 2017-11-17 |
| URL | http://arxiv.org/abs/1711.06642v1 |
| http://arxiv.org/pdf/1711.06642v1.pdf | |
| PWC | https://paperswithcode.com/paper/nonparametric-independence-testing-via-mutual |
| Repo | |
| Framework | |
Deep API Programmer: Learning to Program with APIs
| Title | Deep API Programmer: Learning to Program with APIs |
| Authors | Surya Bhupatiraju, Rishabh Singh, Abdel-rahman Mohamed, Pushmeet Kohli |
| Abstract | We present DAPIP, a Programming-By-Example system that learns to program with APIs to perform data transformation tasks. We design a domain-specific language (DSL) that allows for arbitrary concatenations of API outputs and constant strings. The DSL consists of three family of APIs: regular expression-based APIs, lookup APIs, and transformation APIs. We then present a novel neural synthesis algorithm to search for programs in the DSL that are consistent with a given set of examples. The search algorithm uses recently introduced neural architectures to encode input-output examples and to model the program search in the DSL. We show that synthesis algorithm outperforms baseline methods for synthesizing programs on both synthetic and real-world benchmarks. |
| Tasks | |
| Published | 2017-04-14 |
| URL | http://arxiv.org/abs/1704.04327v1 |
| http://arxiv.org/pdf/1704.04327v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-api-programmer-learning-to-program-with |
| Repo | |
| Framework | |
Specious rules: an efficient and effective unifying method for removing misleading and uninformative patterns in association rule mining
| Title | Specious rules: an efficient and effective unifying method for removing misleading and uninformative patterns in association rule mining |
| Authors | Wilhelmiina Hämäläinen, Geoffrey I. Webb |
| Abstract | We present theoretical analysis and a suite of tests and procedures for addressing a broad class of redundant and misleading association rules we call \emph{specious rules}. Specious dependencies, also known as \emph{spurious}, \emph{apparent}, or \emph{illusory associations}, refer to a well-known phenomenon where marginal dependencies are merely products of interactions with other variables and disappear when conditioned on those variables. The most extreme example is Yule-Simpson’s paradox where two variables present positive dependence in the marginal contingency table but negative in all partial tables defined by different levels of a confounding factor. It is accepted wisdom that in data of any nontrivial dimensionality it is infeasible to control for all of the exponentially many possible confounds of this nature. In this paper, we consider the problem of specious dependencies in the context of statistical association rule mining. We define specious rules and show they offer a unifying framework which covers many types of previously proposed redundant or misleading association rules. After theoretical analysis, we introduce practical algorithms for detecting and pruning out specious association rules efficiently under many key goodness measures, including mutual information and exact hypergeometric probabilities. We demonstrate that the procedure greatly reduces the number of associations discovered, providing an elegant and effective solution to the problem of association mining discovering large numbers of misleading and redundant rules. |
| Tasks | |
| Published | 2017-09-12 |
| URL | http://arxiv.org/abs/1709.03915v1 |
| http://arxiv.org/pdf/1709.03915v1.pdf | |
| PWC | https://paperswithcode.com/paper/specious-rules-an-efficient-and-effective |
| Repo | |
| Framework | |
A unified deep artificial neural network approach to partial differential equations in complex geometries
| Title | A unified deep artificial neural network approach to partial differential equations in complex geometries |
| Authors | Jens Berg, Kaj Nyström |
| Abstract | In this paper we use deep feedforward artificial neural networks to approximate solutions to partial differential equations in complex geometries. We show how to modify the backpropagation algorithm to compute the partial derivatives of the network output with respect to the space variables which is needed to approximate the differential operator. The method is based on an ansatz for the solution which requires nothing but feedforward neural networks and an unconstrained gradient based optimization method such as gradient descent or a quasi-Newton method. We show an example where classical mesh based methods cannot be used and neural networks can be seen as an attractive alternative. Finally, we highlight the benefits of deep compared to shallow neural networks and device some other convergence enhancing techniques. |
| Tasks | |
| Published | 2017-11-17 |
| URL | http://arxiv.org/abs/1711.06464v2 |
| http://arxiv.org/pdf/1711.06464v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-deep-artificial-neural-network |
| Repo | |
| Framework | |
Name Disambiguation in Anonymized Graphs using Network Embedding
| Title | Name Disambiguation in Anonymized Graphs using Network Embedding |
| Authors | Baichuan Zhang, Mohammad Al Hasan |
| Abstract | In real-world, our DNA is unique but many people share names. This phenomenon often causes erroneous aggregation of documents of multiple persons who are namesake of one another. Such mistakes deteriorate the performance of document retrieval, web search, and more seriously, cause improper attribution of credit or blame in digital forensic. To resolve this issue, the name disambiguation task is designed which aims to partition the documents associated with a name reference such that each partition contains documents pertaining to a unique real-life person. Existing solutions to this task substantially rely on feature engineering, such as biographical feature extraction, or construction of auxiliary features from Wikipedia. However, for many scenarios, such features may be costly to obtain or unavailable due to the risk of privacy violation. In this work, we propose a novel name disambiguation method. Our proposed method is non-intrusive of privacy because instead of using attributes pertaining to a real-life person, our method leverages only relational data in the form of anonymized graphs. In the methodological aspect, the proposed method uses a novel representation learning model to embed each document in a low dimensional vector space where name disambiguation can be solved by a hierarchical agglomerative clustering algorithm. Our experimental results demonstrate that the proposed method is significantly better than the existing name disambiguation methods working in a similar setting. |
| Tasks | Feature Engineering, Network Embedding, Representation Learning |
| Published | 2017-02-08 |
| URL | http://arxiv.org/abs/1702.02287v4 |
| http://arxiv.org/pdf/1702.02287v4.pdf | |
| PWC | https://paperswithcode.com/paper/name-disambiguation-in-anonymized-graphs |
| Repo | |
| Framework | |
Extraction and Classification of Diving Clips from Continuous Video Footage
| Title | Extraction and Classification of Diving Clips from Continuous Video Footage |
| Authors | Aiden Nibali, Zhen He, Stuart Morgan, Daniel Greenwood |
| Abstract | Due to recent advances in technology, the recording and analysis of video data has become an increasingly common component of athlete training programmes. Today it is incredibly easy and affordable to set up a fixed camera and record athletes in a wide range of sports, such as diving, gymnastics, golf, tennis, etc. However, the manual analysis of the obtained footage is a time-consuming task which involves isolating actions of interest and categorizing them using domain-specific knowledge. In order to automate this kind of task, three challenging sub-problems are often encountered: 1) temporally cropping events/actions of interest from continuous video; 2) tracking the object of interest; and 3) classifying the events/actions of interest. Most previous work has focused on solving just one of the above sub-problems in isolation. In contrast, this paper provides a complete solution to the overall action monitoring task in the context of a challenging real-world exemplar. Specifically, we address the problem of diving classification. This is a challenging problem since the person (diver) of interest typically occupies fewer than 1% of the pixels in each frame. The model is required to learn the temporal boundaries of a dive, even though other divers and bystanders may be in view. Finally, the model must be sensitive to subtle changes in body pose over a large number of frames to determine the classification code. We provide effective solutions to each of the sub-problems which combine to provide a highly functional solution to the task as a whole. The techniques proposed can be easily generalized to video footage recorded from other sports. |
| Tasks | |
| Published | 2017-05-25 |
| URL | http://arxiv.org/abs/1705.09003v1 |
| http://arxiv.org/pdf/1705.09003v1.pdf | |
| PWC | https://paperswithcode.com/paper/extraction-and-classification-of-diving-clips |
| Repo | |
| Framework | |
A Brief Introduction to the Temporal Group LASSO and its Potential Applications in Healthcare
| Title | A Brief Introduction to the Temporal Group LASSO and its Potential Applications in Healthcare |
| Authors | Diego Saldana Miranda |
| Abstract | The Temporal Group LASSO is an example of a multi-task, regularized regression approach for the prediction of response variables that vary over time. The aim of this work is to introduce the reader to the concepts behind the Temporal Group LASSO and its related methods, as well as to the type of potential applications in a healthcare setting that the method has. We argue that the method is attractive because of its ability to reduce overfitting, select predictors, learn smooth effect patterns over time, and finally, its simplicity |
| Tasks | |
| Published | 2017-04-07 |
| URL | http://arxiv.org/abs/1704.02370v2 |
| http://arxiv.org/pdf/1704.02370v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-brief-introduction-to-the-temporal-group |
| Repo | |
| Framework | |
ACO for Continuous Function Optimization: A Performance Analysis
| Title | ACO for Continuous Function Optimization: A Performance Analysis |
| Authors | Varun Kumar Ojha, Ajith Abraham, Vaclav Snasel |
| Abstract | The performance of the meta-heuristic algorithms often depends on their parameter settings. Appropriate tuning of the underlying parameters can drastically improve the performance of a meta-heuristic. The Ant Colony Optimization (ACO), a population based meta-heuristic algorithm inspired by the foraging behavior of the ants, is no different. Fundamentally, the ACO depends on the construction of new solutions, variable by variable basis using Gaussian sampling of the selected variables from an archive of solutions. A comprehensive performance analysis of the underlying parameters such as: selection strategy, distance measure metric and pheromone evaporation rate of the ACO suggests that the Roulette Wheel Selection strategy enhances the performance of the ACO due to its ability to provide non-uniformity and adequate diversity in the selection of a solution. On the other hand, the Squared Euclidean distance-measure metric offers better performance than other distance-measure metrics. It is observed from the analysis that the ACO is sensitive towards the evaporation rate. Experimental analysis between classical ACO and other meta-heuristic suggested that the performance of the well-tuned ACO surpasses its counterparts. |
| Tasks | |
| Published | 2017-07-06 |
| URL | http://arxiv.org/abs/1707.01812v1 |
| http://arxiv.org/pdf/1707.01812v1.pdf | |
| PWC | https://paperswithcode.com/paper/aco-for-continuous-function-optimization-a |
| Repo | |
| Framework | |
Face Detection through Scale-Friendly Deep Convolutional Networks
| Title | Face Detection through Scale-Friendly Deep Convolutional Networks |
| Authors | Shuo Yang, Yuanjun Xiong, Chen Change Loy, Xiaoou Tang |
| Abstract | In this paper, we share our experience in designing a convolutional network-based face detector that could handle faces of an extremely wide range of scales. We show that faces with different scales can be modeled through a specialized set of deep convolutional networks with different structures. These detectors can be seamlessly integrated into a single unified network that can be trained end-to-end. In contrast to existing deep models that are designed for wide scale range, our network does not require an image pyramid input and the model is of modest complexity. Our network, dubbed ScaleFace, achieves promising performance on WIDER FACE and FDDB datasets with practical runtime speed. Specifically, our method achieves 76.4 average precision on the challenging WIDER FACE dataset and 96% recall rate on the FDDB dataset with 7 frames per second (fps) for 900 * 1300 input image. |
| Tasks | Face Detection |
| Published | 2017-06-09 |
| URL | http://arxiv.org/abs/1706.02863v1 |
| http://arxiv.org/pdf/1706.02863v1.pdf | |
| PWC | https://paperswithcode.com/paper/face-detection-through-scale-friendly-deep |
| Repo | |
| Framework | |
Classification without labels: Learning from mixed samples in high energy physics
| Title | Classification without labels: Learning from mixed samples in high energy physics |
| Authors | Eric M. Metodiev, Benjamin Nachman, Jesse Thaler |
| Abstract | Modern machine learning techniques can be used to construct powerful models for difficult collider physics problems. In many applications, however, these models are trained on imperfect simulations due to a lack of truth-level information in the data, which risks the model learning artifacts of the simulation. In this paper, we introduce the paradigm of classification without labels (CWoLa) in which a classifier is trained to distinguish statistical mixtures of classes, which are common in collider physics. Crucially, neither individual labels nor class proportions are required, yet we prove that the optimal classifier in the CWoLa paradigm is also the optimal classifier in the traditional fully-supervised case where all label information is available. After demonstrating the power of this method in an analytical toy example, we consider a realistic benchmark for collider physics: distinguishing quark- versus gluon-initiated jets using mixed quark/gluon training samples. More generally, CWoLa can be applied to any classification problem where labels or class proportions are unknown or simulations are unreliable, but statistical mixtures of the classes are available. |
| Tasks | |
| Published | 2017-08-09 |
| URL | http://arxiv.org/abs/1708.02949v3 |
| http://arxiv.org/pdf/1708.02949v3.pdf | |
| PWC | https://paperswithcode.com/paper/classification-without-labels-learning-from |
| Repo | |
| Framework | |
The Size of a Hyperball in a Conceptual Space
| Title | The Size of a Hyperball in a Conceptual Space |
| Authors | Lucas Bechberger |
| Abstract | The cognitive framework of conceptual spaces [3] provides geometric means for representing knowledge. A conceptual space is a high-dimensional space whose dimensions are partitioned into so-called domains. Within each domain, the Euclidean metric is used to compute distances. Distances in the overall space are computed by applying the Manhattan metric to the intra-domain distances. Instances are represented as points in this space and concepts are represented by regions. In this paper, we derive a formula for the size of a hyperball under the combined metric of a conceptual space. One can think of such a hyperball as the set of all points having a certain minimal similarity to the hyperball’s center. |
| Tasks | |
| Published | 2017-07-04 |
| URL | http://arxiv.org/abs/1708.05263v4 |
| http://arxiv.org/pdf/1708.05263v4.pdf | |
| PWC | https://paperswithcode.com/paper/the-size-of-a-hyperball-in-a-conceptual-space |
| Repo | |
| Framework | |
Image Matching: An Application-oriented Benchmark
| Title | Image Matching: An Application-oriented Benchmark |
| Authors | JiaWang Bian, Le Zhang, Yun Liu, Wen-Yan Lin, Ming-Ming Cheng, Ian D. Reid |
| Abstract | Image matching approaches have been widely used in computer vision applications in which the image-level matching performance of matchers is critical. However, it has not been well investigated by previous works which place more emphases on evaluating local features. To this end, we present a uniform benchmark with novel evaluation metrics and a large-scale dataset for evaluating the overall performance of image matching methods. The proposed metrics are application-oriented as they emphasize application requirements for matchers. The dataset contains two portions for benchmarking video frame matching and unordered image matching separately, where each portion consists of real-world image sequences and each sequence has a specific attribute. Subsequently, we carry out a comprehensive performance evaluation of different state-of-the-art methods and conduct in-depth analyses regarding various aspects such as application requirements, matching types, and data diversity. Moreover, we shed light on how to choose appropriate approaches for different applications based on empirical results and analyses. Conclusions in this benchmark can be used as general guidelines to design practical matching systems and also advocate potential future research directions in this field. |
| Tasks | |
| Published | 2017-09-12 |
| URL | http://arxiv.org/abs/1709.03917v4 |
| http://arxiv.org/pdf/1709.03917v4.pdf | |
| PWC | https://paperswithcode.com/paper/image-matching-an-application-oriented |
| Repo | |
| Framework | |
Word and Phrase Translation with word2vec
| Title | Word and Phrase Translation with word2vec |
| Authors | Stefan Jansen |
| Abstract | Word and phrase tables are key inputs to machine translations, but costly to produce. New unsupervised learning methods represent words and phrases in a high-dimensional vector space, and these monolingual embeddings have been shown to encode syntactic and semantic relationships between language elements. The information captured by these embeddings can be exploited for bilingual translation by learning a transformation matrix that allows matching relative positions across two monolingual vector spaces. This method aims to identify high-quality candidates for word and phrase translation more cost-effectively from unlabeled data. This paper expands the scope of previous attempts of bilingual translation to four languages (English, German, Spanish, and French). It shows how to process the source data, train a neural network to learn the high-dimensional embeddings for individual languages and expands the framework for testing their quality beyond the English language. Furthermore, it shows how to learn bilingual transformation matrices and obtain candidates for word and phrase translation, and assess their quality. |
| Tasks | |
| Published | 2017-05-09 |
| URL | http://arxiv.org/abs/1705.03127v4 |
| http://arxiv.org/pdf/1705.03127v4.pdf | |
| PWC | https://paperswithcode.com/paper/word-and-phrase-translation-with-word2vec |
| Repo | |
| Framework | |
O$^2$TD: (Near)-Optimal Off-Policy TD Learning
| Title | O$^2$TD: (Near)-Optimal Off-Policy TD Learning |
| Authors | Bo Liu, Daoming Lyu, Wen Dong, Saad Biaz |
| Abstract | Temporal difference learning and Residual Gradient methods are the most widely used temporal difference based learning algorithms; however, it has been shown that none of their objective functions is optimal w.r.t approximating the true value function $V$. Two novel algorithms are proposed to approximate the true value function $V$. This paper makes the following contributions: (1) A batch algorithm that can help find the approximate optimal off-policy prediction of the true value function $V$. (2) A linear computational cost (per step) near-optimal algorithm that can learn from a collection of off-policy samples. (3) A new perspective of the emphatic temporal difference learning which bridges the gap between off-policy optimality and off-policy stability. |
| Tasks | |
| Published | 2017-04-17 |
| URL | http://arxiv.org/abs/1704.05147v2 |
| http://arxiv.org/pdf/1704.05147v2.pdf | |
| PWC | https://paperswithcode.com/paper/o2td-near-optimal-off-policy-td-learning |
| Repo | |
| Framework | |
Information-theoretic analysis of generalization capability of learning algorithms
| Title | Information-theoretic analysis of generalization capability of learning algorithms |
| Authors | Aolin Xu, Maxim Raginsky |
| Abstract | We derive upper bounds on the generalization error of a learning algorithm in terms of the mutual information between its input and output. The bounds provide an information-theoretic understanding of generalization in learning problems, and give theoretical guidelines for striking the right balance between data fit and generalization by controlling the input-output mutual information. We propose a number of methods for this purpose, among which are algorithms that regularize the ERM algorithm with relative entropy or with random noise. Our work extends and leads to nontrivial improvements on the recent results of Russo and Zou. |
| Tasks | |
| Published | 2017-05-22 |
| URL | http://arxiv.org/abs/1705.07809v2 |
| http://arxiv.org/pdf/1705.07809v2.pdf | |
| PWC | https://paperswithcode.com/paper/information-theoretic-analysis-of |
| Repo | |
| Framework | |
