Paper Group ANR 608
Structured and Unstructured Outlier Identification for Robust PCA: A Non iterative, Parameter free Algorithm. Simple Distances for Trajectories via Landmarks. Efficient and Scalable Batch Bayesian Optimization Using K-Means. Introducer Concepts in n-Dimensional Contexts. The Mafiascum Dataset: A Large Text Corpus for Deception Detection. Geometric …
Structured and Unstructured Outlier Identification for Robust PCA: A Non iterative, Parameter free Algorithm
| Title | Structured and Unstructured Outlier Identification for Robust PCA: A Non iterative, Parameter free Algorithm |
| Authors | Vishnu Menon, Sheetal Kalyani |
| Abstract | Robust PCA, the problem of PCA in the presence of outliers has been extensively investigated in the last few years. Here we focus on Robust PCA in the outlier model where each column of the data matrix is either an inlier or an outlier. Most of the existing methods for this model assumes either the knowledge of the dimension of the lower dimensional subspace or the fraction of outliers in the system. However in many applications knowledge of these parameters is not available. Motivated by this we propose a parameter free outlier identification method for robust PCA which a) does not require the knowledge of outlier fraction, b) does not require the knowledge of the dimension of the underlying subspace, c) is computationally simple and fast d) can handle structured and unstructured outliers. Further, analytical guarantees are derived for outlier identification and the performance of the algorithm is compared with the existing state of the art methods in both real and synthetic data for various outlier structures. |
| Tasks | |
| Published | 2018-09-11 |
| URL | http://arxiv.org/abs/1809.04445v1 |
| http://arxiv.org/pdf/1809.04445v1.pdf | |
| PWC | https://paperswithcode.com/paper/structured-and-unstructured-outlier |
| Repo | |
| Framework | |
Simple Distances for Trajectories via Landmarks
| Title | Simple Distances for Trajectories via Landmarks |
| Authors | Jeff M. Phillips, Pingfan Tang |
| Abstract | We develop a new class of distances for objects including lines, hyperplanes, and trajectories, based on the distance to a set of landmarks. These distances easily and interpretably map objects to a Euclidean space, are simple to compute, and perform well in data analysis tasks. For trajectories, they match and in some cases significantly out-perform all state-of-the-art other metrics, can effortlessly be used in k-means clustering, and directly plugged into approximate nearest neighbor approaches which immediately out-perform the best recent advances in trajectory similarity search by several orders of magnitude. These distances do not require a geometry distorting dual (common in the line or halfspace case) or complicated alignment (common in trajectory case). We show reasonable and often simple conditions under which these distances are metrics. |
| Tasks | |
| Published | 2018-04-30 |
| URL | https://arxiv.org/abs/1804.11284v3 |
| https://arxiv.org/pdf/1804.11284v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-data-dependent-distance-for-regression |
| Repo | |
| Framework | |
Efficient and Scalable Batch Bayesian Optimization Using K-Means
| Title | Efficient and Scalable Batch Bayesian Optimization Using K-Means |
| Authors | Matthew Groves, Edward O. Pyzer-Knapp |
| Abstract | We present K-Means Batch Bayesian Optimization (KMBBO), a novel batch sampling algorithm for Bayesian Optimization (BO). KMBBO uses unsupervised learning to efficiently estimate peaks of the model acquisition function. We show in empirical experiments that our method outperforms the current state-of-the-art batch allocation algorithms on a variety of test problems including tuning of algorithm hyper-parameters and a challenging drug discovery problem. In order to accommodate the real-world problem of high dimensional data, we propose a modification to KMBBO by combining it with compressed sensing to project the optimization into a lower dimensional subspace. We demonstrate empirically that this 2-step method outperforms algorithms where no dimensionality reduction has taken place. |
| Tasks | Dimensionality Reduction, Drug Discovery |
| Published | 2018-06-04 |
| URL | http://arxiv.org/abs/1806.01159v2 |
| http://arxiv.org/pdf/1806.01159v2.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-and-scalable-batch-bayesian |
| Repo | |
| Framework | |
Introducer Concepts in n-Dimensional Contexts
| Title | Introducer Concepts in n-Dimensional Contexts |
| Authors | Giacomo Kahn, Alexandre Bazin |
| Abstract | Concept lattices are well-known conceptual structures that organise interesting patterns-the concepts-extracted from data. In some applications, such as software engineering or data mining, the size of the lattice can be a problem, as it is often too large to be efficiently computed, and too complex to be browsed. For this reason, the Galois Sub-Hierarchy, a restriction of the concept lattice to introducer concepts, has been introduced as a smaller alternative. In this paper, we generalise the Galois Sub-Hierarchy to n-lattices, conceptual structures obtained from multidimensional data in the same way that concept lattices are obtained from binary relations. |
| Tasks | |
| Published | 2018-02-12 |
| URL | http://arxiv.org/abs/1802.04030v1 |
| http://arxiv.org/pdf/1802.04030v1.pdf | |
| PWC | https://paperswithcode.com/paper/introducer-concepts-in-n-dimensional-contexts |
| Repo | |
| Framework | |
The Mafiascum Dataset: A Large Text Corpus for Deception Detection
| Title | The Mafiascum Dataset: A Large Text Corpus for Deception Detection |
| Authors | Bob de Ruiter, George Kachergis |
| Abstract | Detecting deception in natural language has a wide variety of applications, but because of its hidden nature there are currently no public, large-scale sources of labeled deceptive text. This work introduces the Mafiascum dataset [1], a collection of over 700 games of Mafia, in which players are randomly assigned either deceptive or non-deceptive roles and then interact via forum postings. Over 9000 documents were compiled from the dataset, which each contained all messages written by a single player in a single game. This corpus was used to construct a set of hand-picked linguistic features based on prior deception research, as well as a set of average word vectors enriched with subword information. A logistic regression classifier fit on a combination of these feature sets achieved an average precision of 0.39 (chance = 0.26) and an AUROC of 0.68 on 5000+ word documents. On 50+ word documents, an average precision of 0.29 (chance = 0.23) and an AUROC of 0.59 was achieved. [1] https://bitbucket.org/bopjesvla/thesis/src |
| Tasks | Deception Detection |
| Published | 2018-11-19 |
| URL | https://arxiv.org/abs/1811.07851v3 |
| https://arxiv.org/pdf/1811.07851v3.pdf | |
| PWC | https://paperswithcode.com/paper/the-mafiascum-dataset-a-large-text-corpus-for |
| Repo | |
| Framework | |
Geometric Generalization Based Zero-Shot Learning Dataset Infinite World: Simple Yet Powerful
| Title | Geometric Generalization Based Zero-Shot Learning Dataset Infinite World: Simple Yet Powerful |
| Authors | Rajesh Chidambaram, Michael Kampffmeyer, Willie Neiswanger, Xiaodan Liang, Thomas Lachmann, Eric Xing |
| Abstract | Raven’s Progressive Matrices are one of the widely used tests in evaluating the human test taker’s fluid intelligence. Analogously, this paper introduces geometric generalization based zero-shot learning tests to measure the rapid learning ability and the internal consistency of deep generative models. Our empirical research analysis on state-of-the-art generative models discern their ability to generalize concepts across classes. In the process, we introduce Infinite World, an evaluable, scalable, multi-modal, light-weight dataset and Zero-Shot Intelligence Metric ZSI. The proposed tests condenses human-level spatial and numerical reasoning tasks to its simplistic geometric forms. The dataset is scalable to a theoretical limit of infinity, in numerical features of the generated geometric figures, image size and in quantity. We systematically analyze state-of-the-art model’s internal consistency, identify their bottlenecks and propose a pro-active optimization method for few-shot and zero-shot learning. |
| Tasks | Zero-Shot Learning |
| Published | 2018-07-10 |
| URL | http://arxiv.org/abs/1807.03711v2 |
| http://arxiv.org/pdf/1807.03711v2.pdf | |
| PWC | https://paperswithcode.com/paper/geometric-generalization-based-zero-shot |
| Repo | |
| Framework | |
Competitive Learning Enriches Learning Representation and Accelerates the Fine-tuning of CNNs
| Title | Competitive Learning Enriches Learning Representation and Accelerates the Fine-tuning of CNNs |
| Authors | Takashi Shinozaki |
| Abstract | In this study, we propose the integration of competitive learning into convolutional neural networks (CNNs) to improve the representation learning and efficiency of fine-tuning. Conventional CNNs use back propagation learning, and it enables powerful representation learning by a discrimination task. However, it requires huge amount of labeled data, and acquisition of labeled data is much harder than that of unlabeled data. Thus, efficient use of unlabeled data is getting crucial for DNNs. To address the problem, we introduce unsupervised competitive learning into the convolutional layer, and utilize unlabeled data for effective representation learning. The results of validation experiments using a toy model demonstrated that strong representation learning effectively extracted bases of images into convolutional filters using unlabeled data, and accelerated the speed of the fine-tuning of subsequent supervised back propagation learning. The leverage was more apparent when the number of filters was sufficiently large, and, in such a case, the error rate steeply decreased in the initial phase of fine-tuning. Thus, the proposed method enlarged the number of filters in CNNs, and enabled a more detailed and generalized representation. It could provide a possibility of not only deep but broad neural networks. |
| Tasks | Representation Learning |
| Published | 2018-04-26 |
| URL | http://arxiv.org/abs/1804.09859v1 |
| http://arxiv.org/pdf/1804.09859v1.pdf | |
| PWC | https://paperswithcode.com/paper/competitive-learning-enriches-learning |
| Repo | |
| Framework | |
Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting
| Title | Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting |
| Authors | Xiang Cheng, Niladri S. Chatterji, Yasin Abbasi-Yadkori, Peter L. Bartlett, Michael I. Jordan |
| Abstract | We study the problem of sampling from a distribution where the negative logarithm of the target density is $L$-smooth everywhere and $m$-strongly convex outside a ball of radius $R$, but potentially non-convex inside this ball. We study both overdamped and underdamped Langevin MCMC and prove upper bounds on the time required to obtain a sample from a distribution that is within $\epsilon$ of the target distribution in $1$-Wasserstein distance. For the first-order method (overdamped Langevin MCMC), the time complexity is $\tilde{\mathcal{O}}\left(e^{cLR^2}\frac{d}{\epsilon^2}\right)$, where $d$ is the dimension of the underlying space. For the second-order method (underdamped Langevin MCMC), the time complexity is $\tilde{\mathcal{O}}\left(e^{cLR^2}\frac{\sqrt{d}}{\epsilon}\right)$ for some explicit positive constant $c$. Surprisingly, the convergence rate is only polynomial in the dimension $d$ and the target accuracy $\epsilon$. It is however exponential in the problem parameter $LR^2$, which is a measure of non-logconcavity of the target distribution. |
| Tasks | |
| Published | 2018-05-04 |
| URL | http://arxiv.org/abs/1805.01648v3 |
| http://arxiv.org/pdf/1805.01648v3.pdf | |
| PWC | https://paperswithcode.com/paper/sharp-convergence-rates-for-langevin-dynamics |
| Repo | |
| Framework | |
Characterization and extraction of condensed representation of correlated patterns based on formal concept analysis
| Title | Characterization and extraction of condensed representation of correlated patterns based on formal concept analysis |
| Authors | Souad Bouasker |
| Abstract | Correlated pattern mining has increasingly become an important task in data mining since these patterns allow conveying knowledge about meaningful and surprising relations among data. Frequent correlated patterns were thoroughly studied in the literature. In this thesis, we propose to benefit from both frequent correlated as well as rare correlated patterns according to the bond correlation measure. We propose to extract a subset without information loss of the sets of frequent correlated and of rare correlated patterns, this subset is called Condensed Representation. In this regard, we are based on the notions derived from the Formal Concept Analysis FCA, specifically the equivalence classes associated to a closure operator fbond dedicated to the bond measure, to introduce new concise representations of both frequent correlated and rare correlated patterns. |
| Tasks | |
| Published | 2018-10-12 |
| URL | http://arxiv.org/abs/1810.05570v1 |
| http://arxiv.org/pdf/1810.05570v1.pdf | |
| PWC | https://paperswithcode.com/paper/characterization-and-extraction-of-condensed |
| Repo | |
| Framework | |
Generative Adversarial Imitation from Observation
| Title | Generative Adversarial Imitation from Observation |
| Authors | Faraz Torabi, Garrett Warnell, Peter Stone |
| Abstract | Imitation from observation (IfO) is the problem of learning directly from state-only demonstrations without having access to the demonstrator’s actions. The lack of action information both distinguishes IfO from most of the literature in imitation learning, and also sets it apart as a method that may enable agents to learn from a large set of previously inapplicable resources such as internet videos. In this paper, we propose both a general framework for IfO approaches and also a new IfO approach based on generative adversarial networks called generative adversarial imitation from observation (GAIfO). We conduct experiments in two different settings: (1) when demonstrations consist of low-dimensional, manually-defined state features, and (2) when demonstrations consist of high-dimensional, raw visual data. We demonstrate that our approach performs comparably to classical imitation learning approaches (which have access to the demonstrator’s actions) and significantly outperforms existing imitation from observation methods in high-dimensional simulation environments. |
| Tasks | Imitation Learning |
| Published | 2018-07-17 |
| URL | https://arxiv.org/abs/1807.06158v4 |
| https://arxiv.org/pdf/1807.06158v4.pdf | |
| PWC | https://paperswithcode.com/paper/generative-adversarial-imitation-from |
| Repo | |
| Framework | |
Image2GIF: Generating Cinemagraphs using Recurrent Deep Q-Networks
| Title | Image2GIF: Generating Cinemagraphs using Recurrent Deep Q-Networks |
| Authors | Yipin Zhou, Yale Song, Tamara L. Berg |
| Abstract | Given a still photograph, one can imagine how dynamic objects might move against a static background. This idea has been actualized in the form of cinemagraphs, where the motion of particular objects within a still image is repeated, giving the viewer a sense of animation. In this paper, we learn computational models that can generate cinemagraph sequences automatically given a single image. To generate cinemagraphs, we explore combining generative models with a recurrent neural network and deep Q-networks to enhance the power of sequence generation. To enable and evaluate these models we make use of two datasets, one synthetically generated and the other containing real video generated cinemagraphs. Both qualitative and quantitative evaluations demonstrate the effectiveness of our models on the synthetic and real datasets. |
| Tasks | |
| Published | 2018-01-27 |
| URL | http://arxiv.org/abs/1801.09042v1 |
| http://arxiv.org/pdf/1801.09042v1.pdf | |
| PWC | https://paperswithcode.com/paper/image2gif-generating-cinemagraphs-using |
| Repo | |
| Framework | |
Tree-to-tree Neural Networks for Program Translation
| Title | Tree-to-tree Neural Networks for Program Translation |
| Authors | Xinyun Chen, Chang Liu, Dawn Song |
| Abstract | Program translation is an important tool to migrate legacy code in one language into an ecosystem built in a different language. In this work, we are the first to employ deep neural networks toward tackling this problem. We observe that program translation is a modular procedure, in which a sub-tree of the source tree is translated into the corresponding target sub-tree at each step. To capture this intuition, we design a tree-to-tree neural network to translate a source tree into a target one. Meanwhile, we develop an attention mechanism for the tree-to-tree model, so that when the decoder expands one non-terminal in the target tree, the attention mechanism locates the corresponding sub-tree in the source tree to guide the expansion of the decoder. We evaluate the program translation capability of our tree-to-tree model against several state-of-the-art approaches. Compared against other neural translation models, we observe that our approach is consistently better than the baselines with a margin of up to 15 points. Further, our approach can improve the previous state-of-the-art program translation approaches by a margin of 20 points on the translation of real-world projects. |
| Tasks | |
| Published | 2018-02-11 |
| URL | http://arxiv.org/abs/1802.03691v3 |
| http://arxiv.org/pdf/1802.03691v3.pdf | |
| PWC | https://paperswithcode.com/paper/tree-to-tree-neural-networks-for-program |
| Repo | |
| Framework | |
Learning Shape Priors for Single-View 3D Completion and Reconstruction
| Title | Learning Shape Priors for Single-View 3D Completion and Reconstruction |
| Authors | Jiajun Wu, Chengkai Zhang, Xiuming Zhang, Zhoutong Zhang, William T. Freeman, Joshua B. Tenenbaum |
| Abstract | The problem of single-view 3D shape completion or reconstruction is challenging, because among the many possible shapes that explain an observation, most are implausible and do not correspond to natural objects. Recent research in the field has tackled this problem by exploiting the expressiveness of deep convolutional networks. In fact, there is another level of ambiguity that is often overlooked: among plausible shapes, there are still multiple shapes that fit the 2D image equally well; i.e., the ground truth shape is non-deterministic given a single-view input. Existing fully supervised approaches fail to address this issue, and often produce blurry mean shapes with smooth surfaces but no fine details. In this paper, we propose ShapeHD, pushing the limit of single-view shape completion and reconstruction by integrating deep generative models with adversarially learned shape priors. The learned priors serve as a regularizer, penalizing the model only if its output is unrealistic, not if it deviates from the ground truth. Our design thus overcomes both levels of ambiguity aforementioned. Experiments demonstrate that ShapeHD outperforms state of the art by a large margin in both shape completion and shape reconstruction on multiple real datasets. |
| Tasks | |
| Published | 2018-09-13 |
| URL | http://arxiv.org/abs/1809.05068v1 |
| http://arxiv.org/pdf/1809.05068v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-shape-priors-for-single-view-3d |
| Repo | |
| Framework | |
Data-Driven Interaction Review of an Ed-Tech Application
| Title | Data-Driven Interaction Review of an Ed-Tech Application |
| Authors | Alejandro Baldominos, David Quintana |
| Abstract | Smile and Learn is an Ed-Tech company that runs a smart library with more that 100 applications, games and interactive stories, aimed at children aged two to 10 and their families. The platform gathers thousands of data points from the interaction with the system to subsequently offer reports and recommendations. Given the complexity of navigating all the content, the library implements a recommender system. The purpose of this paper is to evaluate two aspects of such system focused on children: the influence of the order of recommendations on user exploratory behavior, and the impact of the choice of the recommendation algorithm on engagement. The assessment, based on data collected between 15 October 2018 and 1 December 2018, required the analysis of the number of clicks performed on the recommendations depending on their ordering, and an A/B/C testing where two standard recommendation algorithmswere comparedwith a randomrecommendation that served as baseline. The results suggest a direct connection between the order of the recommendation and the interest raised, and the superiority of recommendations based on popularity against other alternatives. |
| Tasks | Recommendation Systems |
| Published | 2018-12-13 |
| URL | http://arxiv.org/abs/1812.05465v3 |
| http://arxiv.org/pdf/1812.05465v3.pdf | |
| PWC | https://paperswithcode.com/paper/data-driven-interaction-review-of-an-ed-tech |
| Repo | |
| Framework | |
Data Selection with Feature Decay Algorithms Using an Approximated Target Side
| Title | Data Selection with Feature Decay Algorithms Using an Approximated Target Side |
| Authors | Alberto Poncelas, Gideon Maillette de Buy Wenniger, Andy Way |
| Abstract | Data selection techniques applied to neural machine translation (NMT) aim to increase the performance of a model by retrieving a subset of sentences for use as training data. One of the possible data selection techniques are transductive learning methods, which select the data based on the test set, i.e. the document to be translated. A limitation of these methods to date is that using the source-side test set does not by itself guarantee that sentences are selected with correct translations, or translations that are suitable given the test-set domain. Some corpora, such as subtitle corpora, may contain parallel sentences with inaccurate translations caused by localization or length restrictions. In order to try to fix this problem, in this paper we propose to use an approximated target-side in addition to the source-side when selecting suitable sentence-pairs for training a model. This approximated target-side is built by pre-translating the source-side. In this work, we explore the performance of this general idea for one specific data selection approach called Feature Decay Algorithms (FDA). We train German-English NMT models on data selected by using the test set (source), the approximated target side, and a mixture of both. Our findings reveal that models built using a combination of outputs of FDA (using the test set and an approximated target side) perform better than those solely using the test set. We obtain a statistically significant improvement of more than 1.5 BLEU points over a model trained with all data, and more than 0.5 BLEU points over a strong FDA baseline that uses source-side information only. |
| Tasks | Machine Translation |
| Published | 2018-11-07 |
| URL | http://arxiv.org/abs/1811.03039v1 |
| http://arxiv.org/pdf/1811.03039v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-selection-with-feature-decay-algorithms |
| Repo | |
| Framework | |
