May 5, 2019

3117 words 15 mins read

Paper Group ANR 469

Bayesian Exploration: Incentivizing Exploration in Bayesian Games. A Basic Recurrent Neural Network Model. Automated detection of smuggled high-risk security threats using Deep Learning. Unsupervised Pretraining for Sequence to Sequence Learning. A deep representation for depth images from synthetic data. Undecidability of the Lambek calculus with …

Bayesian Exploration: Incentivizing Exploration in Bayesian Games


Title	Bayesian Exploration: Incentivizing Exploration in Bayesian Games
Authors	Yishay Mansour, Aleksandrs Slivkins, Vasilis Syrgkanis, Zhiwei Steven Wu
Abstract	We consider a ubiquitous scenario in the Internet economy when individual decision-makers (henceforth, agents) both produce and consume information as they make strategic choices in an uncertain environment. This creates a three-way tradeoff between exploration (trying out insufficiently explored alternatives to help others in the future), exploitation (making optimal decisions given the information discovered by other agents), and incentives of the agents (who are myopically interested in exploitation, while preferring the others to explore). We posit a principal who controls the flow of information from agents that came before, and strives to coordinate the agents towards a socially optimal balance between exploration and exploitation, not using any monetary transfers. The goal is to design a recommendation policy for the principal which respects agents’ incentives and minimizes a suitable notion of regret. We extend prior work in this direction to allow the agents to interact with one another in a shared environment: at each time step, multiple agents arrive to play a Bayesian game, receive recommendations, choose their actions, receive their payoffs, and then leave the game forever. The agents now face two sources of uncertainty: the actions of the other agents and the parameters of the uncertain game environment. Our main contribution is to show that the principal can achieve constant regret when the utilities are deterministic (where the constant depends on the prior distribution, but not on the time horizon), and logarithmic regret when the utilities are stochastic. As a key technical tool, we introduce the concept of explorable actions, the actions which some incentive-compatible policy can recommend with non-zero probability. We show how the principal can identify (and explore) all explorable actions, and use the revealed information to perform optimally.
Tasks
Published	2016-02-24
URL	http://arxiv.org/abs/1602.07570v3
PDF	http://arxiv.org/pdf/1602.07570v3.pdf
PWC	https://paperswithcode.com/paper/bayesian-exploration-incentivizing
Repo
Framework

A Basic Recurrent Neural Network Model


Title	A Basic Recurrent Neural Network Model
Authors	Fathi M. Salem
Abstract	We present a model of a basic recurrent neural network (or bRNN) that includes a separate linear term with a slightly “stable” fixed matrix to guarantee bounded solutions and fast dynamic response. We formulate a state space viewpoint and adapt the constrained optimization Lagrange Multiplier (CLM) technique and the vector Calculus of Variations (CoV) to derive the (stochastic) gradient descent. In this process, one avoids the commonly used re-application of the circular chain-rule and identifies the error back-propagation with the co-state backward dynamic equations. We assert that this bRNN can successfully perform regression tracking of time-series. Moreover, the “vanishing and exploding” gradients are explicitly quantified and explained through the co-state dynamics and the update laws. The adapted CoV framework, in addition, can correctly and principally integrate new loss functions in the network on any variable and for varied goals, e.g., for supervised learning on the outputs and unsupervised learning on the internal (hidden) states.
Tasks	Time Series
Published	2016-12-29
URL	http://arxiv.org/abs/1612.09022v1
PDF	http://arxiv.org/pdf/1612.09022v1.pdf
PWC	https://paperswithcode.com/paper/a-basic-recurrent-neural-network-model
Repo
Framework

Automated detection of smuggled high-risk security threats using Deep Learning


Title	Automated detection of smuggled high-risk security threats using Deep Learning
Authors	Nicolas Jaccard, Thomas W. Rogers, Edward J. Morton, Lewis D. Griffin
Abstract	The security infrastructure is ill-equipped to detect and deter the smuggling of non-explosive devices that enable terror attacks such as those recently perpetrated in western Europe. The detection of so-called “small metallic threats” (SMTs) in cargo containers currently relies on statistical risk analysis, intelligence reports, and visual inspection of X-ray images by security officers. The latter is very slow and unreliable due to the difficulty of the task: objects potentially spanning less than 50 pixels have to be detected in images containing more than 2 million pixels against very complex and cluttered backgrounds. In this contribution, we demonstrate for the first time the use of Convolutional Neural Networks (CNNs), a type of Deep Learning, to automate the detection of SMTs in fullsize X-ray images of cargo containers. Novel approaches for dataset augmentation allowed to train CNNs from-scratch despite the scarcity of data available. We report fewer than 6% false alarms when detecting 90% SMTs synthetically concealed in stream-of-commerce images, which corresponds to an improvement of over an order of magnitude over conventional approaches such as Bag-of-Words (BoWs). The proposed scheme offers potentially super-human performance for a fraction of the time it would take for a security officers to carry out visual inspection (processing time is approximately 3.5s per container image).
Tasks
Published	2016-09-09
URL	http://arxiv.org/abs/1609.02805v1
PDF	http://arxiv.org/pdf/1609.02805v1.pdf
PWC	https://paperswithcode.com/paper/automated-detection-of-smuggled-high-risk
Repo
Framework

Unsupervised Pretraining for Sequence to Sequence Learning


Title	Unsupervised Pretraining for Sequence to Sequence Learning
Authors	Prajit Ramachandran, Peter J. Liu, Quoc V. Le
Abstract	This work presents a general unsupervised learning method to improve the accuracy of sequence to sequence (seq2seq) models. In our method, the weights of the encoder and decoder of a seq2seq model are initialized with the pretrained weights of two language models and then fine-tuned with labeled data. We apply this method to challenging benchmarks in machine translation and abstractive summarization and find that it significantly improves the subsequent supervised models. Our main result is that pretraining improves the generalization of seq2seq models. We achieve state-of-the art results on the WMT English$\rightarrow$German task, surpassing a range of methods using both phrase-based machine translation and neural machine translation. Our method achieves a significant improvement of 1.3 BLEU from the previous best models on both WMT’14 and WMT’15 English$\rightarrow$German. We also conduct human evaluations on abstractive summarization and find that our method outperforms a purely supervised learning baseline in a statistically significant manner.
Tasks	Abstractive Text Summarization, Machine Translation
Published	2016-11-08
URL	http://arxiv.org/abs/1611.02683v2
PDF	http://arxiv.org/pdf/1611.02683v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-pretraining-for-sequence-to
Repo
Framework

A deep representation for depth images from synthetic data


Title	A deep representation for depth images from synthetic data
Authors	Fabio Maria Carlucci, Paolo Russo, Barbara Caputo
Abstract	Convolutional Neural Networks (CNNs) trained on large scale RGB databases have become the secret sauce in the majority of recent approaches for object categorization from RGB-D data. Thanks to colorization techniques, these methods exploit the filters learned from 2D images to extract meaningful representations in 2.5D. Still, the perceptual signature of these two kind of images is very different, with the first usually strongly characterized by textures, and the second mostly by silhouettes of objects. Ideally, one would like to have two CNNs, one for RGB and one for depth, each trained on a suitable data collection, able to capture the perceptual properties of each channel for the task at hand. This has not been possible so far, due to the lack of a suitable depth database. This paper addresses this issue, proposing to opt for synthetically generated images rather than collecting by hand a 2.5D large scale database. While being clearly a proxy for real data, synthetic images allow to trade quality for quantity, making it possible to generate a virtually infinite amount of data. We show that the filters learned from such data collection, using the very same architecture typically used on visual data, learns very different filters, resulting in depth features (a) able to better characterize the different facets of depth images, and (b) complementary with respect to those derived from CNNs pre-trained on 2D datasets. Experiments on two publicly available databases show the power of our approach.
Tasks	Colorization
Published	2016-09-30
URL	http://arxiv.org/abs/1609.09713v1
PDF	http://arxiv.org/pdf/1609.09713v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-representation-for-depth-images-from
Repo
Framework

Undecidability of the Lambek calculus with subexponential and bracket modalities


Title	Undecidability of the Lambek calculus with subexponential and bracket modalities
Authors	Max Kanovich, Stepan Kuznetsov, Andre Scedrov
Abstract	The Lambek calculus is a well-known logical formalism for modelling natural language syntax. The original calculus covered a substantial number of intricate natural language phenomena, but only those restricted to the context-free setting. In order to address more subtle linguistic issues, the Lambek calculus has been extended in various ways. In particular, Morrill and Valentin (2015) introduce an extension with so-called exponential and bracket modalities. Their extension is based on a non-standard contraction rule for the exponential that interacts with the bracket structure in an intricate way. The standard contraction rule is not admissible in this calculus. In this paper we prove undecidability of the derivability problem in their calculus. We also investigate restricted decidable fragments considered by Morrill and Valentin and we show that these fragments belong to the NP class.
Tasks
Published	2016-08-13
URL	http://arxiv.org/abs/1608.04020v2
PDF	http://arxiv.org/pdf/1608.04020v2.pdf
PWC	https://paperswithcode.com/paper/undecidability-of-the-lambek-calculus-with
Repo
Framework

Explaining Classification Models Built on High-Dimensional Sparse Data


Title	Explaining Classification Models Built on High-Dimensional Sparse Data
Authors	Julie Moeyersoms, Brian d’Alessandro, Foster Provost, David Martens
Abstract	Predictive modeling applications increasingly use data representing people’s behavior, opinions, and interactions. Fine-grained behavior data often has different structure from traditional data, being very high-dimensional and sparse. Models built from these data are quite difficult to interpret, since they contain many thousands or even many millions of features. Listing features with large model coefficients is not sufficient, because the model coefficients do not incorporate information on feature presence, which is key when analysing sparse data. In this paper we introduce two alternatives for explaining predictive models by listing important features. We evaluate these alternatives in terms of explanation “bang for the buck,", i.e., how many examples’ inferences are explained for a given number of features listed. The bottom line: (i) The proposed alternatives have double the bang-for-the-buck as compared to just listing the high-coefficient features, and (ii) interestingly, although they come from different sources and motivations, the two new alternatives provide strikingly similar rankings of important features.
Tasks
Published	2016-07-21
URL	http://arxiv.org/abs/1607.06280v2
PDF	http://arxiv.org/pdf/1607.06280v2.pdf
PWC	https://paperswithcode.com/paper/explaining-classification-models-built-on
Repo
Framework

Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings


Title	Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings
Authors	Rie Johnson, Tong Zhang
Abstract	One-hot CNN (convolutional neural network) has been shown to be effective for text categorization (Johnson & Zhang, 2015). We view it as a special case of a general framework which jointly trains a linear model with a non-linear feature generator consisting of `text region embedding + pooling’. Under this framework, we explore a more sophisticated region embedding method using Long Short-Term Memory (LSTM). LSTM can embed text regions of variable (and possibly large) sizes, whereas the region size needs to be fixed in a CNN. We seek effective and efficient use of LSTM for this purpose in the supervised and semi-supervised settings. The best results were obtained by combining region embeddings in the form of LSTM and convolution layers trained on unlabeled data. The results indicate that on this task, embeddings of text regions, which can convey complex concepts, are more useful than embeddings of single words in isolation. We report performances exceeding the previous best results on four benchmark datasets. \|
Tasks	Sentiment Analysis, Text Categorization, Text Classification
Published	2016-02-07
URL	http://arxiv.org/abs/1602.02373v2
PDF	http://arxiv.org/pdf/1602.02373v2.pdf
PWC	https://paperswithcode.com/paper/supervised-and-semi-supervised-text
Repo
Framework

DENSER Cities: A System for Dense Efficient Reconstructions of Cities


Title	DENSER Cities: A System for Dense Efficient Reconstructions of Cities
Authors	Michael Tanner, Pedro Pinies, Lina Maria Paz, Paul Newman
Abstract	This paper is about the efficient generation of dense, colored models of city-scale environments from range data and in particular, stereo cameras. Better maps make for better understanding; better understanding leads to better robots, but this comes at a cost. The computational and memory requirements of large dense models can be prohibitive. We provide the theory and the system needed to create city-scale dense reconstructions. To do so, we apply a regularizer over a compressed 3D data structure while dealing with the complex boundary conditions this induces during the data-fusion stage. We show that only with these considerations can we swiftly create neat, large, “well behaved” reconstructions. We evaluate our system using the KITTI dataset and provide statistics for the metric errors in all surfaces created compared to those measured with 3D laser. Our regularizer reduces the median error by 40% in 3.4 km of dense reconstructions with a median accuracy of 6 cm. For subjective analysis, we provide a qualitative review of 6.1 km of our dense reconstructions in an attached video. These are the largest dense reconstructions from a single passive camera we are aware of in the literature.
Tasks
Published	2016-04-13
URL	http://arxiv.org/abs/1604.03734v1
PDF	http://arxiv.org/pdf/1604.03734v1.pdf
PWC	https://paperswithcode.com/paper/denser-cities-a-system-for-dense-efficient
Repo
Framework

Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond


Title	Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond
Authors	Levent Sagun, Leon Bottou, Yann LeCun
Abstract	We look at the eigenvalues of the Hessian of a loss function before and after training. The eigenvalue distribution is seen to be composed of two parts, the bulk which is concentrated around zero, and the edges which are scattered away from zero. We present empirical evidence for the bulk indicating how over-parametrized the system is, and for the edges that depend on the input data.
Tasks
Published	2016-11-22
URL	http://arxiv.org/abs/1611.07476v2
PDF	http://arxiv.org/pdf/1611.07476v2.pdf
PWC	https://paperswithcode.com/paper/eigenvalues-of-the-hessian-in-deep-learning
Repo
Framework

Query Answering in Resource-Based Answer Set Semantics


Title	Query Answering in Resource-Based Answer Set Semantics
Authors	Stefania Costantini, Andrea Formisano
Abstract	In recent work we defined resource-based answer set semantics, which is an extension to answer set semantics stemming from the study of its relationship with linear logic. In fact, the name of the new semantics comes from the fact that in the linear-logic formulation every literal (including negative ones) were considered as a resource. In this paper, we propose a query-answering procedure reminiscent of Prolog for answer set programs under this extended semantics as an extension of XSB-resolution for logic programs with negation. We prove formal properties of the proposed procedure. Under consideration for acceptance in TPLP.
Tasks
Published	2016-08-04
URL	http://arxiv.org/abs/1608.01604v1
PDF	http://arxiv.org/pdf/1608.01604v1.pdf
PWC	https://paperswithcode.com/paper/query-answering-in-resource-based-answer-set
Repo
Framework

Intrinsically Motivated Multimodal Structure Learning


Title	Intrinsically Motivated Multimodal Structure Learning
Authors	Jay Ming Wong, Roderic A. Grupen
Abstract	We present a long-term intrinsically motivated structure learning method for modeling transition dynamics during controlled interactions between a robot and semi-permanent structures in the world. In particular, we discuss how partially-observable state is represented using distributions over a Markovian state and build models of objects that predict how state distributions change in response to interactions with such objects. These structures serve as the basis for a number of possible future tasks defined as Markov Decision Processes (MDPs). The approach is an example of a structure learning technique applied to a multimodal affordance representation that yields a population of forward models for use in planning. We evaluate the approach using experiments on a bimanual mobile manipulator (uBot-6) that show the performance of model acquisition as the number of transition actions increases.
Tasks
Published	2016-07-15
URL	http://arxiv.org/abs/1607.04376v1
PDF	http://arxiv.org/pdf/1607.04376v1.pdf
PWC	https://paperswithcode.com/paper/intrinsically-motivated-multimodal-structure
Repo
Framework

BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits


Title	BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits
Authors	Alexander Rakhlin, Karthik Sridharan
Abstract	We present efficient algorithms for the problem of contextual bandits with i.i.d. covariates, an arbitrary sequence of rewards, and an arbitrary class of policies. Our algorithm BISTRO requires d calls to the empirical risk minimization (ERM) oracle per round, where d is the number of actions. The method uses unlabeled data to make the problem computationally simple. When the ERM problem itself is computationally hard, we extend the approach by employing multiplicative approximation algorithms for the ERM. The integrality gap of the relaxation only enters in the regret bound rather than the benchmark. Finally, we show that the adversarial version of the contextual bandit problem is learnable (and efficient) whenever the full-information supervised online learning problem has a non-trivial regret guarantee (and efficient).
Tasks	Multi-Armed Bandits
Published	2016-02-06
URL	http://arxiv.org/abs/1602.02196v1
PDF	http://arxiv.org/pdf/1602.02196v1.pdf
PWC	https://paperswithcode.com/paper/bistro-an-efficient-relaxation-based-method
Repo
Framework

An automatic bad band preremoval algorithm for hyperspectral imagery


Title	An automatic bad band preremoval algorithm for hyperspectral imagery
Authors	Luyan Ji, Xiurui Geng, Yongchao Zhao, Fuxiang Wang
Abstract	For most hyperspectral remote sensing applications, removing bad bands, such as water absorption bands, is a required preprocessing step. Currently, the commonly applied method is by visual inspection, which is very time-consuming and it is easy to overlook some noisy bands. In this study, we find an inherent connection between target detection algorithms and the corrupted band removal. As an example, for the matched filter (MF), which is the most widely used target detection method for hyperspectral data, we present an automatic MF-based algorithm for bad band identification. The MF detector is a filter vector, and the resulting filter output is the sum of all bands weighted by the MF coefficients. Therefore, we can identify bad bands only by using the MF filter vector itself, the absolute value of whose entry accounts for the importance of each band for the target detection. For a specific target of interest, the bands with small MF weights correspond to the noisy or bad ones. Based on this fact, we develop an automatic bad band preremoval algorithm by utilizing the average absolute value of MF weights for multiple targets within a scene. Experiments with three well known hyperspectral datasets show that our method can always identify the water absorption and other low signal-to-noise (SNR) bands that are usually chosen as bad bands manually.
Tasks
Published	2016-10-19
URL	http://arxiv.org/abs/1610.05929v1
PDF	http://arxiv.org/pdf/1610.05929v1.pdf
PWC	https://paperswithcode.com/paper/an-automatic-bad-band-preremoval-algorithm
Repo
Framework

CP-mtML: Coupled Projection multi-task Metric Learning for Large Scale Face Retrieval


Title	CP-mtML: Coupled Projection multi-task Metric Learning for Large Scale Face Retrieval
Authors	Binod Bhattarai, Gaurav Sharma, Frederic Jurie
Abstract	We propose a novel Coupled Projection multi-task Metric Learning (CP-mtML) method for large scale face retrieval. In contrast to previous works which were limited to low dimensional features and small datasets, the proposed method scales to large datasets with high dimensional face descriptors. It utilises pairwise (dis-)similarity constraints as supervision and hence does not require exhaustive class annotation for every training image. While, traditionally, multi-task learning methods have been validated on same dataset but different tasks, we work on the more challenging setting with heterogeneous datasets and different tasks. We show empirical validation on multiple face image datasets of different facial traits, e.g. identity, age and expression. We use classic Local Binary Pattern (LBP) descriptors along with the recent Deep Convolutional Neural Network (CNN) features. The experiments clearly demonstrate the scalability and improved performance of the proposed method on the tasks of identity and age based face image retrieval compared to competitive existing methods, on the standard datasets and with the presence of a million distractor face images.
Tasks	Face Image Retrieval, Image Retrieval, Metric Learning, Multi-Task Learning
Published	2016-04-11
URL	http://arxiv.org/abs/1604.02975v1
PDF	http://arxiv.org/pdf/1604.02975v1.pdf
PWC	https://paperswithcode.com/paper/cp-mtml-coupled-projection-multi-task-metric
Repo
Framework