Paper Group ANR 53
Fast Algorithms for Segmented Regression. Eye-CU: Sleep Pose Classification for Healthcare using Multimodal Multiview Data. Determining the Characteristic Vocabulary for a Specialized Dictionary using Word2vec and a Directed Crawler. Deep Coevolutionary Network: Embedding User and Item Features for Recommendation. Solving Visual Madlibs with Multip …
Fast Algorithms for Segmented Regression
| Title | Fast Algorithms for Segmented Regression |
| Authors | Jayadev Acharya, Ilias Diakonikolas, Jerry Li, Ludwig Schmidt |
| Abstract | We study the fixed design segmented regression problem: Given noisy samples from a piecewise linear function $f$, we want to recover $f$ up to a desired accuracy in mean-squared error. Previous rigorous approaches for this problem rely on dynamic programming (DP) and, while sample efficient, have running time quadratic in the sample size. As our main contribution, we provide new sample near-linear time algorithms for the problem that – while not being minimax optimal – achieve a significantly better sample-time tradeoff on large datasets compared to the DP approach. Our experimental evaluation shows that, compared with the DP approach, our algorithms provide a convergence rate that is only off by a factor of $2$ to $4$, while achieving speedups of three orders of magnitude. |
| Tasks | |
| Published | 2016-07-14 |
| URL | http://arxiv.org/abs/1607.03990v1 |
| http://arxiv.org/pdf/1607.03990v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-algorithms-for-segmented-regression |
| Repo | |
| Framework | |
Eye-CU: Sleep Pose Classification for Healthcare using Multimodal Multiview Data
| Title | Eye-CU: Sleep Pose Classification for Healthcare using Multimodal Multiview Data |
| Authors | Carlos Torres, Victor Fragoso, Scott D. Hammond, Jeffrey C. Fried, B. S. Manjunath |
| Abstract | Manual analysis of body poses of bed-ridden patients requires staff to continuously track and record patient poses. Two limitations in the dissemination of pose-related therapies are scarce human resources and unreliable automated systems. This work addresses these issues by introducing a new method and a new system for robust automated classification of sleep poses in an Intensive Care Unit (ICU) environment. The new method, coupled-constrained Least-Squares (cc-LS), uses multimodal and multiview (MM) data and finds the set of modality trust values that minimizes the difference between expected and estimated labels. The new system, Eye-CU, is an affordable multi-sensor modular system for unobtrusive data collection and analysis in healthcare. Experimental results indicate that the performance of cc-LS matches the performance of existing methods in ideal scenarios. This method outperforms the latest techniques in challenging scenarios by 13% for those with poor illumination and by 70% for those with both poor illumination and occlusions. Results also show that a reduced Eye-CU configuration can classify poses without pressure information with only a slight drop in its performance. |
| Tasks | |
| Published | 2016-02-07 |
| URL | http://arxiv.org/abs/1602.02343v2 |
| http://arxiv.org/pdf/1602.02343v2.pdf | |
| PWC | https://paperswithcode.com/paper/eye-cu-sleep-pose-classification-for |
| Repo | |
| Framework | |
Determining the Characteristic Vocabulary for a Specialized Dictionary using Word2vec and a Directed Crawler
| Title | Determining the Characteristic Vocabulary for a Specialized Dictionary using Word2vec and a Directed Crawler |
| Authors | Gregory Grefenstette, Lawrence Muchemi |
| Abstract | Specialized dictionaries are used to understand concepts in specific domains, especially where those concepts are not part of the general vocabulary, or having meanings that differ from ordinary languages. The first step in creating a specialized dictionary involves detecting the characteristic vocabulary of the domain in question. Classical methods for detecting this vocabulary involve gathering a domain corpus, calculating statistics on the terms found there, and then comparing these statistics to a background or general language corpus. Terms which are found significantly more often in the specialized corpus than in the background corpus are candidates for the characteristic vocabulary of the domain. Here we present two tools, a directed crawler, and a distributional semantics package, that can be used together, circumventing the need of a background corpus. Both tools are available on the web. |
| Tasks | |
| Published | 2016-05-31 |
| URL | http://arxiv.org/abs/1605.09564v1 |
| http://arxiv.org/pdf/1605.09564v1.pdf | |
| PWC | https://paperswithcode.com/paper/determining-the-characteristic-vocabulary-for |
| Repo | |
| Framework | |
Deep Coevolutionary Network: Embedding User and Item Features for Recommendation
| Title | Deep Coevolutionary Network: Embedding User and Item Features for Recommendation |
| Authors | Hanjun Dai, Yichen Wang, Rakshit Trivedi, Le Song |
| Abstract | Recommender systems often use latent features to explain the behaviors of users and capture the properties of items. As users interact with different items over time, user and item features can influence each other, evolve and co-evolve over time. The compatibility of user and item’s feature further influence the future interaction between users and items. Recently, point process based models have been proposed in the literature aiming to capture the temporally evolving nature of these latent features. However, these models often make strong parametric assumptions about the evolution process of the user and item latent features, which may not reflect the reality, and has limited power in expressing the complex and nonlinear dynamics underlying these processes. To address these limitations, we propose a novel deep coevolutionary network model (DeepCoevolve), for learning user and item features based on their interaction graph. DeepCoevolve use recurrent neural network (RNN) over evolving networks to define the intensity function in point processes, which allows the model to capture complex mutual influence between users and items, and the feature evolution over time. We also develop an efficient procedure for training the model parameters, and show that the learned models lead to significant improvements in recommendation and activity prediction compared to previous state-of-the-arts parametric models. |
| Tasks | Activity Prediction, Network Embedding, Point Processes, Recommendation Systems |
| Published | 2016-09-13 |
| URL | http://arxiv.org/abs/1609.03675v4 |
| http://arxiv.org/pdf/1609.03675v4.pdf | |
| PWC | https://paperswithcode.com/paper/deep-coevolutionary-network-embedding-user |
| Repo | |
| Framework | |
Solving Visual Madlibs with Multiple Cues
| Title | Solving Visual Madlibs with Multiple Cues |
| Authors | Tatiana Tommasi, Arun Mallya, Bryan Plummer, Svetlana Lazebnik, Alexander C. Berg, Tamara L. Berg |
| Abstract | This paper focuses on answering fill-in-the-blank style multiple choice questions from the Visual Madlibs dataset. Previous approaches to Visual Question Answering (VQA) have mainly used generic image features from networks trained on the ImageNet dataset, despite the wide scope of questions. In contrast, our approach employs features derived from networks trained for specialized tasks of scene classification, person activity prediction, and person and object attribute prediction. We also present a method for selecting sub-regions of an image that are relevant for evaluating the appropriateness of a putative answer. Visual features are computed both from the whole image and from local regions, while sentences are mapped to a common space using a simple normalized canonical correlation analysis (CCA) model. Our results show a significant improvement over the previous state of the art, and indicate that answering different question types benefits from examining a variety of image cues and carefully choosing informative image sub-regions. |
| Tasks | Activity Prediction, Question Answering, Scene Classification, Visual Question Answering |
| Published | 2016-08-11 |
| URL | http://arxiv.org/abs/1608.03410v1 |
| http://arxiv.org/pdf/1608.03410v1.pdf | |
| PWC | https://paperswithcode.com/paper/solving-visual-madlibs-with-multiple-cues |
| Repo | |
| Framework | |
Validation of Information Fusion
| Title | Validation of Information Fusion |
| Authors | Alexander Kott, Wes Milks |
| Abstract | We motivate and offer a formal definition of validation as it applies to information fusion systems. Common definitions of validation compare the actual state of the world with that derived by the fusion process. This definition conflates properties of the fusion system with properties of systems that intervene between the world and the fusion system. We propose an alternative definition where validation of an information fusion system references a standard fusion device, such as recognized human experts. We illustrate the approach by describing the validation process implemented in RAID, a program conducted by DARPA and focused on information fusion in adversarial, deceptive environments. |
| Tasks | |
| Published | 2016-07-22 |
| URL | http://arxiv.org/abs/1607.07288v1 |
| http://arxiv.org/pdf/1607.07288v1.pdf | |
| PWC | https://paperswithcode.com/paper/validation-of-information-fusion |
| Repo | |
| Framework | |
False-Friend Detection and Entity Matching via Unsupervised Transliteration
| Title | False-Friend Detection and Entity Matching via Unsupervised Transliteration |
| Authors | Yanqing Chen, Steven Skiena |
| Abstract | Transliterations play an important role in multilingual entity reference resolution, because proper names increasingly travel between languages in news and social media. Previous work associated with machine translation targets transliteration only single between language pairs, focuses on specific classes of entities (such as cities and celebrities) and relies on manual curation, which limits the expression power of transliteration in multilingual environment. By contrast, we present an unsupervised transliteration model covering 69 major languages that can generate good transliterations for arbitrary strings between any language pair. Our model yields top-(1, 20, 100) averages of (32.85%, 60.44%, 83.20%) in matching gold standard transliteration compared to results from a recently-published system of (26.71%, 50.27%, 72.79%). We also show the quality of our model in detecting true and false friends from Wikipedia high frequency lexicons. Our method indicates a strong signal of pronunciation similarity and boosts the probability of finding true friends in 68 out of 69 languages. |
| Tasks | Machine Translation, Transliteration |
| Published | 2016-11-21 |
| URL | http://arxiv.org/abs/1611.06722v1 |
| http://arxiv.org/pdf/1611.06722v1.pdf | |
| PWC | https://paperswithcode.com/paper/false-friend-detection-and-entity-matching |
| Repo | |
| Framework | |
Bandit-Based Random Mutation Hill-Climbing
| Title | Bandit-Based Random Mutation Hill-Climbing |
| Authors | Jialin Liu, Diego Peŕez-Liebana, Simon M. Lucas |
| Abstract | The Random Mutation Hill-Climbing algorithm is a direct search technique mostly used in discrete domains. It repeats the process of randomly selecting a neighbour of a best-so-far solution and accepts the neighbour if it is better than or equal to it. In this work, we propose to use a novel method to select the neighbour solution using a set of independent multi- armed bandit-style selection units which results in a bandit-based Random Mutation Hill-Climbing algorithm. The new algorithm significantly outperforms Random Mutation Hill-Climbing in both OneMax (in noise-free and noisy cases) and Royal Road problems (in the noise-free case). The algorithm shows particular promise for discrete optimisation problems where each fitness evaluation is expensive. |
| Tasks | |
| Published | 2016-06-20 |
| URL | http://arxiv.org/abs/1606.06041v1 |
| http://arxiv.org/pdf/1606.06041v1.pdf | |
| PWC | https://paperswithcode.com/paper/bandit-based-random-mutation-hill-climbing |
| Repo | |
| Framework | |
Knowledge Representation in Graphs using Convolutional Neural Networks
| Title | Knowledge Representation in Graphs using Convolutional Neural Networks |
| Authors | Armando Vieira |
| Abstract | Knowledge Graphs (KG) constitute a flexible representation of complex relationships between entities particularly useful for biomedical data. These KG, however, are very sparse with many missing edges (facts) and the visualisation of the mesh of interactions nontrivial. Here we apply a compositional model to embed nodes and relationships into a vectorised semantic space to perform graph completion. A visualisation tool based on Convolutional Neural Networks and Self-Organised Maps (SOM) is proposed to extract high-level insights from the KG. We apply this technique to a subset of CTD, containing interactions of compounds with human genes / proteins and show that the performance is comparable to the one obtained by structural models. |
| Tasks | Knowledge Graphs |
| Published | 2016-12-07 |
| URL | http://arxiv.org/abs/1612.02255v1 |
| http://arxiv.org/pdf/1612.02255v1.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-representation-in-graphs-using |
| Repo | |
| Framework | |
Typical Stability
| Title | Typical Stability |
| Authors | Raef Bassily, Yoav Freund |
| Abstract | In this paper, we introduce a notion of algorithmic stability called typical stability. When our goal is to release real-valued queries (statistics) computed over a dataset, this notion does not require the queries to be of bounded sensitivity – a condition that is generally assumed under differential privacy [DMNS06, Dwork06] when used as a notion of algorithmic stability [DFHPRR15a, DFHPRR15b, BNSSSU16] – nor does it require the samples in the dataset to be independent – a condition that is usually assumed when generalization-error guarantees are sought. Instead, typical stability requires the output of the query, when computed on a dataset drawn from the underlying distribution, to be concentrated around its expected value with respect to that distribution. We discuss the implications of typical stability on the generalization error (i.e., the difference between the value of the query computed on the dataset and the expected value of the query with respect to the true data distribution). We show that typical stability can control generalization error in adaptive data analysis even when the samples in the dataset are not necessarily independent and when queries to be computed are not necessarily of bounded-sensitivity as long as the results of the queries over the dataset (i.e., the computed statistics) follow a distribution with a “light” tail. Examples of such queries include, but not limited to, subgaussian and subexponential queries. We also discuss the composition guarantees of typical stability and prove composition theorems that characterize the degradation of the parameters of typical stability under $k$-fold adaptive composition. We also give simple noise-addition algorithms that achieve this notion. These algorithms are similar to their differentially private counterparts, however, the added noise is calibrated differently. |
| Tasks | |
| Published | 2016-04-12 |
| URL | http://arxiv.org/abs/1604.03336v2 |
| http://arxiv.org/pdf/1604.03336v2.pdf | |
| PWC | https://paperswithcode.com/paper/typical-stability |
| Repo | |
| Framework | |
Nonparametric Bayesian label prediction on a graph
| Title | Nonparametric Bayesian label prediction on a graph |
| Authors | Jarno Hartog, Harry van Zanten |
| Abstract | An implementation of a nonparametric Bayesian approach to solving binary classification problems on graphs is described. A hierarchical Bayesian approach with a randomly scaled Gaussian prior is considered. The prior uses the graph Laplacian to take into account the underlying geometry of the graph. A method based on a theoretically optimal prior and a more flexible variant using partial conjugacy are proposed. Two simulated data examples and two examples using real data are used in order to illustrate the proposed methods. |
| Tasks | |
| Published | 2016-12-06 |
| URL | http://arxiv.org/abs/1612.01930v2 |
| http://arxiv.org/pdf/1612.01930v2.pdf | |
| PWC | https://paperswithcode.com/paper/nonparametric-bayesian-label-prediction-on-a-1 |
| Repo | |
| Framework | |
Efficient and Robust Pedestrian Detection using Deep Learning for Human-Aware Navigation
| Title | Efficient and Robust Pedestrian Detection using Deep Learning for Human-Aware Navigation |
| Authors | Andre Mateus, David Ribeiro, Pedro Miraldo, Jacinto C. Nascimento |
| Abstract | This paper addresses the problem of Human-Aware Navigation (HAN), using multi camera sensors to implement a vision-based person tracking system. The main contributions of this paper are as follows: a novel and efficient Deep Learning person detection and a standardization of human-aware constraints. In the first stage of the approach, we propose to cascade the Aggregate Channel Features (ACF) detector with a deep Convolutional Neural Network (CNN) to achieve fast and accurate Pedestrian Detection (PD). Regarding the human awareness (that can be defined as constraints associated with the robot’s motion), we use a mixture of asymmetric Gaussian functions, to define the cost functions associated to each constraint. Both methods proposed herein are evaluated individually to measure the impact of each of the components. The final solution (including both the proposed pedestrian detection and the human-aware constraints) is tested in a typical domestic indoor scenario, in four distinct experiments. The results show that the robot is able to cope with human-aware constraints, defined after common proxemics and social rules. |
| Tasks | Human Detection, Pedestrian Detection |
| Published | 2016-07-15 |
| URL | http://arxiv.org/abs/1607.04441v3 |
| http://arxiv.org/pdf/1607.04441v3.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-and-robust-pedestrian-detection |
| Repo | |
| Framework | |
Low-dimensional Data Embedding via Robust Ranking
| Title | Low-dimensional Data Embedding via Robust Ranking |
| Authors | Ehsan Amid, Nikos Vlassis, Manfred K. Warmuth |
| Abstract | We describe a new method called t-ETE for finding a low-dimensional embedding of a set of objects in Euclidean space. We formulate the embedding problem as a joint ranking problem over a set of triplets, where each triplet captures the relative similarities between three objects in the set. By exploiting recent advances in robust ranking, t-ETE produces high-quality embeddings even in the presence of a significant amount of noise and better preserves local scale than known methods, such as t-STE and t-SNE. In particular, our method produces significantly better results than t-SNE on signature datasets while also being faster to compute. |
| Tasks | |
| Published | 2016-11-30 |
| URL | http://arxiv.org/abs/1611.09957v2 |
| http://arxiv.org/pdf/1611.09957v2.pdf | |
| PWC | https://paperswithcode.com/paper/low-dimensional-data-embedding-via-robust |
| Repo | |
| Framework | |
Iterative proportional scaling revisited: a modern optimization perspective
| Title | Iterative proportional scaling revisited: a modern optimization perspective |
| Authors | Yiyuan She, Shao Tang |
| Abstract | This paper revisits the classic iterative proportional scaling (IPS) from a modern optimization perspective. In contrast to the criticisms made in the literature, we show that based on a coordinate descent characterization, IPS can be slightly modified to deliver coefficient estimates, and from a majorization-minimization standpoint, IPS can be extended to handle log-affine models with features not necessarily binary-valued or nonnegative. Furthermore, some state-of-the-art optimization techniques such as block-wise computation, randomization and momentum-based acceleration can be employed to provide more scalable IPS algorithms, as well as some regularized variants of IPS for concurrent feature selection. |
| Tasks | Feature Selection |
| Published | 2016-10-08 |
| URL | http://arxiv.org/abs/1610.02588v4 |
| http://arxiv.org/pdf/1610.02588v4.pdf | |
| PWC | https://paperswithcode.com/paper/iterative-proportional-scaling-revisited-a |
| Repo | |
| Framework | |
Nystrom Method for Approximating the GMM Kernel
| Title | Nystrom Method for Approximating the GMM Kernel |
| Authors | Ping Li |
| Abstract | The GMM (generalized min-max) kernel was recently proposed (Li, 2016) as a measure of data similarity and was demonstrated effective in machine learning tasks. In order to use the GMM kernel for large-scale datasets, the prior work resorted to the (generalized) consistent weighted sampling (GCWS) to convert the GMM kernel to linear kernel. We call this approach as GMM-GCWS''. In the machine learning literature, there is a popular algorithm which we call RBF-RFF’'. That is, one can use the random Fourier features'' (RFF) to convert the radial basis function’’ (RBF) kernel to linear kernel. It was empirically shown in (Li, 2016) that RBF-RFF typically requires substantially more samples than GMM-GCWS in order to achieve comparable accuracies. The Nystrom method is a general tool for computing nonlinear kernels, which again converts nonlinear kernels into linear kernels. We apply the Nystrom method for approximating the GMM kernel, a strategy which we name as ``GMM-NYS’'. In this study, our extensive experiments on a set of fairly large datasets confirm that GMM-NYS is also a strong competitor of RBF-RFF. | |
| Tasks | |
| Published | 2016-07-12 |
| URL | http://arxiv.org/abs/1607.03475v1 |
| http://arxiv.org/pdf/1607.03475v1.pdf | |
| PWC | https://paperswithcode.com/paper/nystrom-method-for-approximating-the-gmm |
| Repo | |
| Framework | |
