July 28, 2019

2922 words 14 mins read

Paper Group ANR 388

Misspecified Linear Bandits. Interactive Learning from Policy-Dependent Human Feedback. Tomographic Reconstruction using Global Statistical Prior. High performance ultra-low-precision convolutions on mobile devices. Deep neural network initialization with decision trees. Unsupervised Learning of Morphological Forests. End to End Deep Neural Network …

Misspecified Linear Bandits


Title	Misspecified Linear Bandits
Authors	Avishek Ghosh, Sayak Ray Chowdhury, Aditya Gopalan
Abstract	We consider the problem of online learning in misspecified linear stochastic multi-armed bandit problems. Regret guarantees for state-of-the-art linear bandit algorithms such as Optimism in the Face of Uncertainty Linear bandit (OFUL) hold under the assumption that the arms expected rewards are perfectly linear in their features. It is, however, of interest to investigate the impact of potential misspecification in linear bandit models, where the expected rewards are perturbed away from the linear subspace determined by the arms features. Although OFUL has recently been shown to be robust to relatively small deviations from linearity, we show that any linear bandit algorithm that enjoys optimal regret performance in the perfectly linear setting (e.g., OFUL) must suffer linear regret under a sparse additive perturbation of the linear model. In an attempt to overcome this negative result, we define a natural class of bandit models characterized by a non-sparse deviation from linearity. We argue that the OFUL algorithm can fail to achieve sublinear regret even under models that have non-sparse deviation.We finally develop a novel bandit algorithm, comprising a hypothesis test for linearity followed by a decision to use either the OFUL or Upper Confidence Bound (UCB) algorithm. For perfectly linear bandit models, the algorithm provably exhibits OFULs favorable regret performance, while for misspecified models satisfying the non-sparse deviation property, the algorithm avoids the linear regret phenomenon and falls back on UCBs sublinear regret scaling. Numerical experiments on synthetic data, and on recommendation data from the public Yahoo! Learning to Rank Challenge dataset, empirically support our findings.
Tasks	Learning-To-Rank
Published	2017-04-23
URL	http://arxiv.org/abs/1704.06880v1
PDF	http://arxiv.org/pdf/1704.06880v1.pdf
PWC	https://paperswithcode.com/paper/misspecified-linear-bandits
Repo
Framework

Interactive Learning from Policy-Dependent Human Feedback


Title	Interactive Learning from Policy-Dependent Human Feedback
Authors	James MacGlashan, Mark K Ho, Robert Loftin, Bei Peng, David Roberts, Matthew E. Taylor, Michael L. Littman
Abstract	For agents and robots to become more useful, they must be able to quickly learn from non-technical users. This paper investigates the problem of interactively learning behaviors communicated by a human teacher using positive and negative feedback. Much previous work on this problem has made the assumption that people provide feedback for decisions that is dependent on the behavior they are teaching and is independent from the learner’s current policy. We present empirical results that show this assumption to be false—whether human trainers give a positive or negative feedback for a decision is influenced by the learner’s current policy. We argue that policy-dependent feedback, in addition to being commonplace, enables useful training strategies from which agents should benefit. Based on this insight, we introduce Convergent Actor-Critic by Humans (COACH), an algorithm for learning from policy-dependent feedback that converges to a local optimum. Finally, we demonstrate that COACH can successfully learn multiple behaviors on a physical robot, even with noisy image features.
Tasks
Published	2017-01-21
URL	http://arxiv.org/abs/1701.06049v1
PDF	http://arxiv.org/pdf/1701.06049v1.pdf
PWC	https://paperswithcode.com/paper/interactive-learning-from-policy-dependent
Repo
Framework

Tomographic Reconstruction using Global Statistical Prior


Title	Tomographic Reconstruction using Global Statistical Prior
Authors	Preeti Gopal, Ritwick Chaudhry, Sharat Chandran, Imants Svalbe, Ajit Rajwade
Abstract	Recent research in tomographic reconstruction is motivated by the need to efficiently recover detailed anatomy from limited measurements. One of the ways to compensate for the increasingly sparse sets of measurements is to exploit the information from templates, i.e., prior data available in the form of already reconstructed, structurally similar images. Towards this, previous work has exploited using a set of global and patch based dictionary priors. In this paper, we propose a global prior to improve both the speed and quality of tomographic reconstruction within a Compressive Sensing framework. We choose a set of potential representative 2D images referred to as templates, to build an eigenspace; this is subsequently used to guide the iterative reconstruction of a similar slice from sparse acquisition data. Our experiments across a diverse range of datasets show that reconstruction using an appropriate global prior, apart from being faster, gives a much lower reconstruction error when compared to the state of the art.
Tasks	Compressive Sensing
Published	2017-12-06
URL	http://arxiv.org/abs/1712.02423v1
PDF	http://arxiv.org/pdf/1712.02423v1.pdf
PWC	https://paperswithcode.com/paper/tomographic-reconstruction-using-global
Repo
Framework

High performance ultra-low-precision convolutions on mobile devices


Title	High performance ultra-low-precision convolutions on mobile devices
Authors	Andrew Tulloch, Yangqing Jia
Abstract	Many applications of mobile deep learning, especially real-time computer vision workloads, are constrained by computation power. This is particularly true for workloads running on older consumer phones, where a typical device might be powered by a single- or dual-core ARMv7 CPU. We provide an open-source implementation and a comprehensive analysis of (to our knowledge) the state of the art ultra-low-precision (<4 bit precision) implementation of the core primitives required for modern deep learning workloads on ARMv7 devices, and demonstrate speedups of 4x-20x over our additional state-of-the-art float32 and int8 baselines.
Tasks
Published	2017-12-06
URL	http://arxiv.org/abs/1712.02427v1
PDF	http://arxiv.org/pdf/1712.02427v1.pdf
PWC	https://paperswithcode.com/paper/high-performance-ultra-low-precision
Repo
Framework

Deep neural network initialization with decision trees


Title	Deep neural network initialization with decision trees
Authors	K. D. Humbird, J. L. Peterson, R. G. McClarren
Abstract	In this work a novel, automated process for constructing and initializing deep feed-forward neural networks based on decision trees is presented. The proposed algorithm maps a collection of decision trees trained on the data into a collection of initialized neural networks, with the structures of the networks determined by the structures of the trees. The tree-informed initialization acts as a warm-start to the neural network training process, resulting in efficiently trained, accurate networks. These models, referred to as “deep jointly-informed neural networks” (DJINN), demonstrate high predictive performance for a variety of regression and classification datasets, and display comparable performance to Bayesian hyper-parameter optimization at a lower computational cost. By combining the user-friendly features of decision tree models with the flexibility and scalability of deep neural networks, DJINN is an attractive algorithm for training predictive models on a wide range of complex datasets.
Tasks
Published	2017-07-03
URL	http://arxiv.org/abs/1707.00784v3
PDF	http://arxiv.org/pdf/1707.00784v3.pdf
PWC	https://paperswithcode.com/paper/deep-neural-network-initialization-with
Repo
Framework

Unsupervised Learning of Morphological Forests


Title	Unsupervised Learning of Morphological Forests
Authors	Jiaming Luo, Karthik Narasimhan, Regina Barzilay
Abstract	This paper focuses on unsupervised modeling of morphological families, collectively comprising a forest over the language vocabulary. This formulation enables us to capture edgewise properties reflecting single-step morphological derivations, along with global distributional properties of the entire forest. These global properties constrain the size of the affix set and encourage formation of tight morphological families. The resulting objective is solved using Integer Linear Programming (ILP) paired with contrastive estimation. We train the model by alternating between optimizing the local log-linear model and the global ILP objective. We evaluate our system on three tasks: root detection, clustering of morphological families and segmentation. Our experiments demonstrate that our model yields consistent gains in all three tasks compared with the best published results.
Tasks
Published	2017-02-22
URL	http://arxiv.org/abs/1702.07015v1
PDF	http://arxiv.org/pdf/1702.07015v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-learning-of-morphological
Repo
Framework

End to End Deep Neural Network Frequency Demodulation of Speech Signals


Title	End to End Deep Neural Network Frequency Demodulation of Speech Signals
Authors	Dan Elbaz, Michael Zibulevsky
Abstract	Frequency modulation (FM) is a form of radio broadcasting which is widely used nowadays and has been for almost a century. We suggest a software-defined-radio (SDR) receiver for FM demodulation that adopts an end-to-end learning based approach and utilizes the prior information of transmitted speech message in the demodulation process. The receiver detects and enhances speech from the in-phase and quadrature components of its base band version. The new system yields high performance detection for both acoustical disturbances, and communication channel noise and is foreseen to out-perform the established methods for low signal to noise ratio (SNR) conditions in both mean square error and in perceptual evaluation of speech quality score.
Tasks
Published	2017-04-06
URL	http://arxiv.org/abs/1704.02046v5
PDF	http://arxiv.org/pdf/1704.02046v5.pdf
PWC	https://paperswithcode.com/paper/end-to-end-deep-neural-network-frequency
Repo
Framework

A statistical interpretation of spectral embedding: the generalised random dot product graph


Title	A statistical interpretation of spectral embedding: the generalised random dot product graph
Authors	Patrick Rubin-Delanchy, Joshua Cape, Minh Tang, Carey E. Priebe
Abstract	A generalisation of a latent position network model known as the random dot product graph is considered. We show that, whether the normalised Laplacian or adjacency matrix is used, the vector representations of nodes obtained by spectral embedding, using the largest eigenvalues by magnitude, provide strongly consistent latent position estimates with asymptotically Gaussian error, up to indefinite orthogonal transformation. The mixed membership and standard stochastic block models constitute special cases where the latent positions live respectively inside or on the vertices of a simplex, crucially, without assuming the underlying block connectivity probability matrix is positive-definite. Estimation via spectral embedding can therefore be achieved by respectively estimating this simplicial support, or fitting a Gaussian mixture model. In the latter case, the use of $K$-means (with Euclidean distance), as has been previously recommended, is suboptimal and for identifiability reasons unsound. Indeed, Euclidean distances and angles are not preserved under indefinite orthogonal transformation, and we show stochastic block model examples where such quantities vary appreciably. Empirical improvements in link prediction (over the random dot product graph), as well as the potential to uncover richer latent structure (than posited under the mixed membership or standard stochastic block models) are demonstrated in a cyber-security example.
Tasks	Link Prediction
Published	2017-09-16
URL	https://arxiv.org/abs/1709.05506v4
PDF	https://arxiv.org/pdf/1709.05506v4.pdf
PWC	https://paperswithcode.com/paper/a-statistical-interpretation-of-spectral
Repo
Framework

Toward negotiable reinforcement learning: shifting priorities in Pareto optimal sequential decision-making


Title	Toward negotiable reinforcement learning: shifting priorities in Pareto optimal sequential decision-making
Authors	Andrew Critch
Abstract	Existing multi-objective reinforcement learning (MORL) algorithms do not account for objectives that arise from players with differing beliefs. Concretely, consider two players with different beliefs and utility functions who may cooperate to build a machine that takes actions on their behalf. A representation is needed for how much the machine’s policy will prioritize each player’s interests over time. Assuming the players have reached common knowledge of their situation, this paper derives a recursion that any Pareto optimal policy must satisfy. Two qualitative observations can be made from the recursion: the machine must (1) use each player’s own beliefs in evaluating how well an action will serve that player’s utility function, and (2) shift the relative priority it assigns to each player’s expected utilities over time, by a factor proportional to how well that player’s beliefs predict the machine’s inputs. Observation (2) represents a substantial divergence from na"{i}ve linear utility aggregation (as in Harsanyi’s utilitarian theorem, and existing MORL algorithms), which is shown here to be inadequate for Pareto optimal sequential decision-making on behalf of players with different beliefs.
Tasks	Decision Making
Published	2017-01-05
URL	http://arxiv.org/abs/1701.01302v3
PDF	http://arxiv.org/pdf/1701.01302v3.pdf
PWC	https://paperswithcode.com/paper/toward-negotiable-reinforcement-learning
Repo
Framework

Named Entity Recognition in Twitter using Images and Text


Title	Named Entity Recognition in Twitter using Images and Text
Authors	Diego Esteves, Rafael Peres, Jens Lehmann, Giulio Napolitano
Abstract	Named Entity Recognition (NER) is an important subtask of information extraction that seeks to locate and recognise named entities. Despite recent achievements, we still face limitations with correctly detecting and classifying entities, prominently in short and noisy text, such as Twitter. An important negative aspect in most of NER approaches is the high dependency on hand-crafted features and domain-specific knowledge, necessary to achieve state-of-the-art results. Thus, devising models to deal with such linguistically complex contexts is still challenging. In this paper, we propose a novel multi-level architecture that does not rely on any specific linguistic resource or encoded rule. Unlike traditional approaches, we use features extracted from images and text to classify named entities. Experimental tests against state-of-the-art NER for Twitter on the Ritter dataset present competitive results (0.59 F-measure), indicating that this approach may lead towards better NER models.
Tasks	Named Entity Recognition
Published	2017-10-30
URL	http://arxiv.org/abs/1710.11027v1
PDF	http://arxiv.org/pdf/1710.11027v1.pdf
PWC	https://paperswithcode.com/paper/named-entity-recognition-in-twitter-using
Repo
Framework

IoFClime: The fuzzy logic and the Internet of Things to control indoor temperature regarding the outdoor ambient conditions


Title	IoFClime: The fuzzy logic and the Internet of Things to control indoor temperature regarding the outdoor ambient conditions
Authors	Daniel Meana-Llorián, Cristian González García, B. Cristina Pelayo G-Bustelo, Juan Manuel Cueva Lovelle, Nestor Garcia-Fernandez
Abstract	The Internet of Things is arriving to our homes or cities through fields already known like Smart Homes, Smart Cities, or Smart Towns. The monitoring of environmental conditions of cities can help to adapt the indoor locations of the cities in order to be more comfortable for people who stay there. A way to improve the indoor conditions is an efficient temperature control, however, it depends on many factors like the different combinations of outdoor temperature and humidity. Therefore, adjusting the indoor temperature is not setting a value according to other value. There are many more factors to take into consideration, hence the traditional logic based in binary states cannot be used. Many problems cannot be solved with a set of binary solutions and we need a new way of development. Fuzzy logic is able to interpret many states, more than two states, giving to computers the capacity to react in a similar way to people. In this paper we will propose a new approach to control the temperature using the Internet of Things together its platforms and fuzzy logic regarding not only the indoor temperature but also the outdoor temperature and humidity in order to save energy and to set a more comfortable environment for their users. Finally, we will conclude that the fuzzy approach allows us to achieve an energy saving around 40% and thus, save money.
Tasks
Published	2017-01-10
URL	http://arxiv.org/abs/1701.02545v1
PDF	http://arxiv.org/pdf/1701.02545v1.pdf
PWC	https://paperswithcode.com/paper/iofclime-the-fuzzy-logic-and-the-internet-of
Repo
Framework

Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks


Title	Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks
Authors	Rahul Dey, Fathi M. Salem
Abstract	The paper evaluates three variants of the Gated Recurrent Unit (GRU) in recurrent neural networks (RNN) by reducing parameters in the update and reset gates. We evaluate the three variant GRU models on MNIST and IMDB datasets and show that these GRU-RNN variant models perform as well as the original GRU RNN model while reducing the computational expense.
Tasks
Published	2017-01-20
URL	http://arxiv.org/abs/1701.05923v1
PDF	http://arxiv.org/pdf/1701.05923v1.pdf
PWC	https://paperswithcode.com/paper/gate-variants-of-gated-recurrent-unit-gru
Repo
Framework

Joint 2D-3D-Semantic Data for Indoor Scene Understanding


Title	Joint 2D-3D-Semantic Data for Indoor Scene Understanding
Authors	Iro Armeni, Sasha Sax, Amir R. Zamir, Silvio Savarese
Abstract	We present a dataset of large-scale indoor spaces that provides a variety of mutually registered modalities from 2D, 2.5D and 3D domains, with instance-level semantic and geometric annotations. The dataset covers over 6,000m2 and contains over 70,000 RGB images, along with the corresponding depths, surface normals, semantic annotations, global XYZ images (all in forms of both regular and 360{\deg} equirectangular images) as well as camera information. It also includes registered raw and semantically annotated 3D meshes and point clouds. The dataset enables development of joint and cross-modal learning models and potentially unsupervised approaches utilizing the regularities present in large-scale indoor spaces. The dataset is available here: http://3Dsemantics.stanford.edu/
Tasks	Scene Understanding
Published	2017-02-03
URL	http://arxiv.org/abs/1702.01105v2
PDF	http://arxiv.org/pdf/1702.01105v2.pdf
PWC	https://paperswithcode.com/paper/joint-2d-3d-semantic-data-for-indoor-scene
Repo
Framework

Rough extreme learning machine: a new classification method based on uncertainty measure


Title	Rough extreme learning machine: a new classification method based on uncertainty measure
Authors	Lin Feng, Shuliang Xu, Feilong Wang, Shenglan Liu
Abstract	Extreme learning machine (ELM) is a new single hidden layer feedback neural network. The weights of the input layer and the biases of neurons in hidden layer are randomly generated, the weights of the output layer can be analytically determined. ELM has been achieved good results for a large number of classification tasks. In this paper, a new extreme learning machine called rough extreme learning machine (RELM) was proposed. RELM uses rough set to divide data into upper approximation set and lower approximation set, and the two approximation sets are utilized to train upper approximation neurons and lower approximation neurons. In addition, an attribute reduction is executed in this algorithm to remove redundant attributes. The experimental results showed, comparing with the comparison algorithms, RELM can get a better accuracy and repeatability in most cases, RELM can not only maintain the advantages of fast speed, but also effectively cope with the classification task for high-dimensional data.
Tasks
Published	2017-10-30
URL	http://arxiv.org/abs/1710.10824v2
PDF	http://arxiv.org/pdf/1710.10824v2.pdf
PWC	https://paperswithcode.com/paper/rough-extreme-learning-machine-a-new
Repo
Framework

Least Square Variational Bayesian Autoencoder with Regularization


Title	Least Square Variational Bayesian Autoencoder with Regularization
Authors	Gautam Ramachandra
Abstract	In recent years Variation Autoencoders have become one of the most popular unsupervised learning of complicated distributions.Variational Autoencoder (VAE) provides more efficient reconstructive performance over a traditional autoencoder. Variational auto enocders make better approximaiton than MCMC. The VAE defines a generative process in terms of ancestral sampling through a cascade of hidden stochastic layers. They are a directed graphic models. Variational autoencoder is trained to maximise the variational lower bound. Here we are trying maximise the likelihood and also at the same time we are trying to make a good approximation of the data. Its basically trading of the data log-likelihood and the KL divergence from the true posterior. This paper describes the scenario in which we wish to find a point-estimate to the parameters $\theta$ of some parametric model in which we generate each observations by first sampling a local latent variable and then sampling the associated observation. Here we use least square loss function with regularization in the the reconstruction of the image, the least square loss function was found to give better reconstructed images and had a faster training time.
Tasks
Published	2017-07-11
URL	http://arxiv.org/abs/1707.03134v1
PDF	http://arxiv.org/pdf/1707.03134v1.pdf
PWC	https://paperswithcode.com/paper/least-square-variational-bayesian-autoencoder
Repo
Framework