July 27, 2019

3230 words 16 mins read

Paper Group ANR 611

Multi-step Reinforcement Learning: A Unifying Algorithm. Local nearest neighbour classification with applications to semi-supervised learning. Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning. Subsampling for Ridge Regression via Regularized Volume Sampling. Vision-based Real-Time Aerial Object Localization an …

Multi-step Reinforcement Learning: A Unifying Algorithm


Title	Multi-step Reinforcement Learning: A Unifying Algorithm
Authors	Kristopher De Asis, J. Fernando Hernandez-Garcia, G. Zacharias Holland, Richard S. Sutton
Abstract	Unifying seemingly disparate algorithmic ideas to produce better performing algorithms has been a longstanding goal in reinforcement learning. As a primary example, TD($\lambda$) elegantly unifies one-step TD prediction with Monte Carlo methods through the use of eligibility traces and the trace-decay parameter $\lambda$. Currently, there are a multitude of algorithms that can be used to perform TD control, including Sarsa, $Q$-learning, and Expected Sarsa. These methods are often studied in the one-step case, but they can be extended across multiple time steps to achieve better performance. Each of these algorithms is seemingly distinct, and no one dominates the others for all problems. In this paper, we study a new multi-step action-value algorithm called $Q(\sigma)$ which unifies and generalizes these existing algorithms, while subsuming them as special cases. A new parameter, $\sigma$, is introduced to allow the degree of sampling performed by the algorithm at each step during its backup to be continuously varied, with Sarsa existing at one extreme (full sampling), and Expected Sarsa existing at the other (pure expectation). $Q(\sigma)$ is generally applicable to both on- and off-policy learning, but in this work we focus on experiments in the on-policy case. Our results show that an intermediate value of $\sigma$, which results in a mixture of the existing algorithms, performs better than either extreme. The mixture can also be varied dynamically which can result in even greater performance.
Tasks	Q-Learning
Published	2017-03-03
URL	http://arxiv.org/abs/1703.01327v2
PDF	http://arxiv.org/pdf/1703.01327v2.pdf
PWC	https://paperswithcode.com/paper/multi-step-reinforcement-learning-a-unifying
Repo
Framework

Local nearest neighbour classification with applications to semi-supervised learning


Title	Local nearest neighbour classification with applications to semi-supervised learning
Authors	Timothy I. Cannings, Thomas B. Berrett, Richard J. Samworth
Abstract	We derive a new asymptotic expansion for the global excess risk of a local-$k$-nearest neighbour classifier, where the choice of $k$ may depend upon the test point. This expansion elucidates conditions under which the dominant contribution to the excess risk comes from the decision boundary of the optimal Bayes classifier, but we also show that if these conditions are not satisfied, then the dominant contribution may arise from the tails of the marginal distribution of the features. Moreover, we prove that, provided the $d$-dimensional marginal distribution of the features has a finite $\rho$th moment for some $\rho > 4$ (as well as other regularity conditions), a local choice of $k$ can yield a rate of convergence of the excess risk of $O(n^{-4/(d+4)})$, where $n$ is the sample size, whereas for the standard $k$-nearest neighbour classifier, our theory would require $d \geq 5$ and $\rho > 4d/(d-4)$ finite moments to achieve this rate. These results motivate a new $k$-nearest neighbour classifier for semi-supervised learning problems, where the unlabelled data are used to obtain an estimate of the marginal feature density, and fewer neighbours are used for classification when this density estimate is small. Our worst-case rates are complemented by a minimax lower bound, which reveals that the local, semi-supervised $k$-nearest neighbour classifier attains the minimax optimal rate over our classes for the excess risk, up to a subpolynomial factor in $n$. These theoretical improvements over the standard $k$-nearest neighbour classifier are also illustrated through a simulation study.
Tasks
Published	2017-04-03
URL	https://arxiv.org/abs/1704.00642v3
PDF	https://arxiv.org/pdf/1704.00642v3.pdf
PWC	https://paperswithcode.com/paper/local-nearest-neighbour-classification-with
Repo
Framework

Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning


Title	Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning
Authors	Ziliang Chen, Keze Wang, Xiao Wang, Pai Peng, Ebroul Izquierdo, Liang Lin
Abstract	Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS). Unlike many conventional semi-supervised learning methods usually performing within a fixed feature space, our DCS gradually propagates information from labeled samples to unlabeled ones along with deep feature learning. We regard deep feature learning as a series of steps pursuing feature transformation, i.e., projecting the samples from a previous space into a new one, which tends to select the reliable unlabeled samples with respect to this setting. Specifically, for each unlabeled image instance, we measure its reliability by calculating the category variations of feature transformation from two different neighborhood variation perspectives, and merged them into an unified sample mining criterion deriving from Hellinger distance. Then, those samples keeping stable correlation to their neighboring samples (i.e., having small category variation in distribution) across the successive feature space transformation, are automatically received labels and incorporated into the model for incrementally training in terms of classification. Our extensive experiments on standard image classification benchmarks (e.g., Caltech-256 and SUN-397) demonstrate that the proposed framework is capable of effectively mining from large-scale unlabeled images, which boosts image classification performance and achieves promising results compared to other semi-supervised learning methods.
Tasks	Image Classification
Published	2017-07-28
URL	http://arxiv.org/abs/1707.09119v1
PDF	http://arxiv.org/pdf/1707.09119v1.pdf
PWC	https://paperswithcode.com/paper/deep-co-space-sample-mining-across-feature
Repo
Framework

Subsampling for Ridge Regression via Regularized Volume Sampling


Title	Subsampling for Ridge Regression via Regularized Volume Sampling
Authors	Michał Dereziński, Manfred K. Warmuth
Abstract	Given $n$ vectors $\mathbf{x}_i\in \mathbb{R}^d$, we want to fit a linear regression model for noisy labels $y_i\in\mathbb{R}$. The ridge estimator is a classical solution to this problem. However, when labels are expensive, we are forced to select only a small subset of vectors $\mathbf{x}_i$ for which we obtain the labels $y_i$. We propose a new procedure for selecting the subset of vectors, such that the ridge estimator obtained from that subset offers strong statistical guarantees in terms of the mean squared prediction error over the entire dataset of $n$ labeled vectors. The number of labels needed is proportional to the statistical dimension of the problem which is often much smaller than $d$. Our method is an extension of a joint subsampling procedure called volume sampling. A second major contribution is that we speed up volume sampling so that it is essentially as efficient as leverage scores, which is the main i.i.d. subsampling procedure for this task. Finally, we show theoretically and experimentally that volume sampling has a clear advantage over any i.i.d. sampling when labels are expensive.
Tasks
Published	2017-10-14
URL	http://arxiv.org/abs/1710.05110v2
PDF	http://arxiv.org/pdf/1710.05110v2.pdf
PWC	https://paperswithcode.com/paper/subsampling-for-ridge-regression-via
Repo
Framework

Vision-based Real-Time Aerial Object Localization and Tracking for UAV Sensing System


Title	Vision-based Real-Time Aerial Object Localization and Tracking for UAV Sensing System
Authors	Yuanwei Wu, Yao Sui, Guanghui Wang
Abstract	The paper focuses on the problem of vision-based obstacle detection and tracking for unmanned aerial vehicle navigation. A real-time object localization and tracking strategy from monocular image sequences is developed by effectively integrating the object detection and tracking into a dynamic Kalman model. At the detection stage, the object of interest is automatically detected and localized from a saliency map computed via the image background connectivity cue at each frame; at the tracking stage, a Kalman filter is employed to provide a coarse prediction of the object state, which is further refined via a local detector incorporating the saliency map and the temporal information between two consecutive frames. Compared to existing methods, the proposed approach does not require any manual initialization for tracking, runs much faster than the state-of-the-art trackers of its kind, and achieves competitive tracking performance on a large number of image sequences. Extensive experiments demonstrate the effectiveness and superior performance of the proposed approach.
Tasks	Object Detection, Object Localization
Published	2017-03-19
URL	http://arxiv.org/abs/1703.06527v1
PDF	http://arxiv.org/pdf/1703.06527v1.pdf
PWC	https://paperswithcode.com/paper/vision-based-real-time-aerial-object
Repo
Framework

Enhancing the Performance of Convolutional Neural Networks on Quality Degraded Datasets


Title	Enhancing the Performance of Convolutional Neural Networks on Quality Degraded Datasets
Authors	Jonghwa Yim, Kyung-Ah Sohn
Abstract	Despite the appeal of deep neural networks that largely replace the traditional handmade filters, they still suffer from isolated cases that cannot be properly handled only by the training of convolutional filters. Abnormal factors, including real-world noise, blur, or other quality degradations, ruin the output of a neural network. These unexpected problems can produce critical complications, and it is surprising that there has only been minimal research into the effects of noise in the deep neural network model. Therefore, we present an exhaustive investigation into the effect of noise in image classification and suggest a generalized architecture of a dual-channel model to treat quality degraded input images. We compare the proposed dual-channel model with a simple single model and show it improves the overall performance of neural networks on various types of quality degraded input datasets.
Tasks	Image Classification
Published	2017-10-18
URL	http://arxiv.org/abs/1710.06805v1
PDF	http://arxiv.org/pdf/1710.06805v1.pdf
PWC	https://paperswithcode.com/paper/enhancing-the-performance-of-convolutional
Repo
Framework

Hawkes Processes for Invasive Species Modeling and Management


Title	Hawkes Processes for Invasive Species Modeling and Management
Authors	Amrita Gupta, Mehrdad Farajtabar, Bistra Dilkina, Hongyuan Zha
Abstract	The spread of invasive species to new areas threatens the stability of ecosystems and causes major economic losses in agriculture and forestry. We propose a novel approach to minimizing the spread of an invasive species given a limited intervention budget. We first model invasive species propagation using Hawkes processes, and then derive closed-form expressions for characterizing the effect of an intervention action on the invasion process. We use this to obtain an optimal intervention plan based on an integer programming formulation, and compare the optimal plan against several ecologically-motivated heuristic strategies used in practice. We present an empirical study of two variants of the invasive control problem: minimizing the final rate of invasions, and minimizing the number of invasions at the end of a given time horizon. Our results show that the optimized intervention achieves nearly the same level of control that would be attained by completely eradicating the species, with a 20% cost saving. Additionally, we design a heuristic intervention strategy based on a combination of the density and life stage of the invasive individuals, and find that it comes surprisingly close to the optimized strategy, suggesting that this could serve as a good rule of thumb in invasive species management.
Tasks
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04386v1
PDF	http://arxiv.org/pdf/1712.04386v1.pdf
PWC	https://paperswithcode.com/paper/hawkes-processes-for-invasive-species
Repo
Framework

Probabilistic Pursuits on Graphs


Title	Probabilistic Pursuits on Graphs
Authors	Michael Amir, Alfred M. Bruckstein
Abstract	We consider discrete dynamical systems of “ant-like” agents engaged in a sequence of pursuits on a graph environment. The agents emerge one by one at equal time intervals from a source vertex $s$ and pursue each other by greedily attempting to close the distance to their immediate predecessor, the agent that emerged just before them from $s$, until they arrive at the destination point $t$. Such pursuits have been investigated before in the continuous setting and in discrete time when the underlying environment is a regular grid. In both these settings the agents’ walks provably converge to a shortest path from $s$ to $t$. Furthermore, assuming a certain natural probability distribution over the move choices of the agents on the grid (in case there are multiple shortest paths between an agent and its predecessor), the walks converge to the uniform distribution over all shortest paths from $s$ to $t$. We study the evolution of agent walks over a general finite graph environment $G$. Our model is a natural generalization of the pursuit rule proposed for the case of the grid. The main results are as follows. We show that “convergence” to the shortest paths in the sense of previous work extends to all pseudo-modular graphs (i.e. graphs in which every three pairwise intersecting disks have a nonempty intersection), and also to environments obtained by taking graph products, generalizing previous results in two different ways. We show that convergence to the shortest paths is also obtained by chordal graphs, and discuss some further positive and negative results for planar graphs. In the most general case, convergence to the shortest paths is not guaranteed, and the agents may get stuck on sets of recurrent, non-optimal walks from $s$ to $t$. However, we show that the limiting distributions of the agents’ walks will always be uniform distributions over some set of walks of equal length.
Tasks
Published	2017-10-23
URL	http://arxiv.org/abs/1710.08107v3
PDF	http://arxiv.org/pdf/1710.08107v3.pdf
PWC	https://paperswithcode.com/paper/probabilistic-pursuits-on-graphs
Repo
Framework

Pedestrian Prediction by Planning using Deep Neural Networks


Title	Pedestrian Prediction by Planning using Deep Neural Networks
Authors	Eike Rehder, Florian Wirth, Martin Lauer, Christoph Stiller
Abstract	Accurate traffic participant prediction is the prerequisite for collision avoidance of autonomous vehicles. In this work, we predict pedestrians by emulating their own motion planning. From online observations, we infer a mixture density function for possible destinations. We use this result as the goal states of a planning stage that performs motion prediction based on common behavior patterns. The entire system is modeled as one monolithic neural network and trained via inverse reinforcement learning. Experimental validation on real world data shows the system’s ability to predict both, destinations and trajectories accurately.
Tasks	Autonomous Vehicles, Motion Planning, motion prediction
Published	2017-06-19
URL	http://arxiv.org/abs/1706.05904v2
PDF	http://arxiv.org/pdf/1706.05904v2.pdf
PWC	https://paperswithcode.com/paper/pedestrian-prediction-by-planning-using-deep
Repo
Framework

Intelligent bidirectional rapidly-exploring random trees for optimal motion planning in complex cluttered environments


Title	Intelligent bidirectional rapidly-exploring random trees for optimal motion planning in complex cluttered environments
Authors	Ahmed Hussain Qureshi, Yasar Ayaz
Abstract	The sampling based motion planning algorithm known as Rapidly-exploring Random Trees (RRT) has gained the attention of many researchers due to their computational efficiency and effectiveness. Recently, a variant of RRT called RRT* has been proposed that ensures asymptotic optimality. Subsequently its bidirectional version has also been introduced in the literature known as Bidirectional-RRT* (B-RRT). We introduce a new variant called Intelligent Bidirectional-RRT (IB-RRT) which is an improved variant of the optimal RRT and bidirectional version of RRT* (B-RRT) algorithms and is specially designed for complex cluttered environments. IB-RRT utilizes the bidirectional trees approach and introduces intelligent sample insertion heuristic for fast convergence to the optimal path solution using uniform sampling heuristics. The proposed algorithm is evaluated theoretically and experimental results are presented that compares IB-RRT* with RRT* and B-RRT. Moreover, experimental results demonstrate the superior efficiency of IB-RRT in comparison with RRT* and B-RRT in complex cluttered environments.
Tasks	Motion Planning, Optimal Motion Planning
Published	2017-03-27
URL	http://arxiv.org/abs/1703.08944v1
PDF	http://arxiv.org/pdf/1703.08944v1.pdf
PWC	https://paperswithcode.com/paper/intelligent-bidirectional-rapidly-exploring
Repo
Framework

Autoencoder Regularized Network For Driving Style Representation Learning


Title	Autoencoder Regularized Network For Driving Style Representation Learning
Authors	Weishan Dong, Ting Yuan, Kai Yang, Changsheng Li, Shilei Zhang
Abstract	In this paper, we study learning generalized driving style representations from automobile GPS trip data. We propose a novel Autoencoder Regularized deep neural Network (ARNet) and a trip encoding framework trip2vec to learn drivers’ driving styles directly from GPS records, by combining supervised and unsupervised feature learning in a unified architecture. Experiments on a challenging driver number estimation problem and the driver identification problem show that ARNet can learn a good generalized driving style representation: It significantly outperforms existing methods and alternative architectures by reaching the least estimation error on average (0.68, less than one driver) and the highest identification accuracy (by at least 3% improvement) compared with traditional supervised learning methods.
Tasks	Representation Learning
Published	2017-01-05
URL	http://arxiv.org/abs/1701.01272v1
PDF	http://arxiv.org/pdf/1701.01272v1.pdf
PWC	https://paperswithcode.com/paper/autoencoder-regularized-network-for-driving
Repo
Framework

Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation


Title	Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation
Authors	Markus Wulfmeier, Alex Bewley, Ingmar Posner
Abstract	Appearance changes due to weather and seasonal conditions represent a strong impediment to the robust implementation of machine learning systems in outdoor robotics. While supervised learning optimises a model for the training domain, it will deliver degraded performance in application domains that underlie distributional shifts caused by these changes. Traditionally, this problem has been addressed via the collection of labelled data in multiple domains or by imposing priors on the type of shift between both domains. We frame the problem in the context of unsupervised domain adaptation and develop a framework for applying adversarial techniques to adapt popular, state-of-the-art network architectures with the additional objective to align features across domains. Moreover, as adversarial training is notoriously unstable, we first perform an extensive ablation study, adapting many techniques known to stabilise generative adversarial networks, and evaluate on a surrogate classification task with the same appearance change. The distilled insights are applied to the problem of free-space segmentation for motion planning in autonomous driving.
Tasks	Autonomous Driving, Domain Adaptation, Motion Planning, Unsupervised Domain Adaptation
Published	2017-03-04
URL	http://arxiv.org/abs/1703.01461v2
PDF	http://arxiv.org/pdf/1703.01461v2.pdf
PWC	https://paperswithcode.com/paper/addressing-appearance-change-in-outdoor
Repo
Framework

Deep Sparse Subspace Clustering


Title	Deep Sparse Subspace Clustering
Authors	Xi Peng, Jiashi Feng, Shijie Xiao, Jiwen Lu, Zhang Yi, Shuicheng Yan
Abstract	In this paper, we present a deep extension of Sparse Subspace Clustering, termed Deep Sparse Subspace Clustering (DSSC). Regularized by the unit sphere distribution assumption for the learned deep features, DSSC can infer a new data affinity matrix by simultaneously satisfying the sparsity principle of SSC and the nonlinearity given by neural networks. One of the appealing advantages brought by DSSC is: when original real-world data do not meet the class-specific linear subspace distribution assumption, DSSC can employ neural networks to make the assumption valid with its hierarchical nonlinear transformations. To the best of our knowledge, this is among the first deep learning based subspace clustering methods. Extensive experiments are conducted on four real-world datasets to show the proposed DSSC is significantly superior to 12 existing methods for subspace clustering.
Tasks
Published	2017-09-25
URL	http://arxiv.org/abs/1709.08374v1
PDF	http://arxiv.org/pdf/1709.08374v1.pdf
PWC	https://paperswithcode.com/paper/deep-sparse-subspace-clustering
Repo
Framework

Improving Distributed Representations of Tweets - Present and Future


Title	Improving Distributed Representations of Tweets - Present and Future
Authors	Ganesh J
Abstract	Unsupervised representation learning for tweets is an important research field which helps in solving several business applications such as sentiment analysis, hashtag prediction, paraphrase detection and microblog ranking. A good tweet representation learning model must handle the idiosyncratic nature of tweets which poses several challenges such as short length, informal words, unusual grammar and misspellings. However, there is a lack of prior work which surveys the representation learning models with a focus on tweets. In this work, we organize the models based on its objective function which aids the understanding of the literature. We also provide interesting future directions, which we believe are fruitful in advancing this field by building high-quality tweet representation learning models.
Tasks	Representation Learning, Sentiment Analysis, Unsupervised Representation Learning
Published	2017-06-29
URL	http://arxiv.org/abs/1706.09673v1
PDF	http://arxiv.org/pdf/1706.09673v1.pdf
PWC	https://paperswithcode.com/paper/improving-distributed-representations-of-1
Repo
Framework

Enhancing human color vision by breaking binocular redundancy


Title	Enhancing human color vision by breaking binocular redundancy
Authors	Bradley S. Gundlach, Michel Frising, Alireza Shahsafi, Gregory Vershbow, Chenghao Wan, Jad Salman, Bas Rokers, Laurent Lessard, Mikhail A. Kats
Abstract	To see color, the human visual system combines the response of three types of cone cells in the retina–a compressive process that discards a significant amount of spectral information. Here, we present an approach to enhance human color vision by breaking its inherent binocular redundancy, providing different spectral content to each eye. We fabricated a set of optical filters that “splits” the response of the short-wavelength cone between the two eyes in individuals with typical trichromatic vision, simulating the presence of approximately four distinct cone types (“tetrachromacy”). Such an increase in the number of effective cone types can reduce the prevalence of metamers–pairs of distinct spectra that resolve to the same tristimulus values. This technique may result in an enhancement of spectral perception, with applications ranging from camouflage detection and anti-counterfeiting to new types of artwork and data visualization.
Tasks
Published	2017-03-02
URL	http://arxiv.org/abs/1703.04392v3
PDF	http://arxiv.org/pdf/1703.04392v3.pdf
PWC	https://paperswithcode.com/paper/enhancing-human-color-vision-by-breaking
Repo
Framework