Paper Group ANR 348
In Search for Linear Relations in Sentence Embedding Spaces. Mining User Behaviour from Smartphone data: a literature review. Active Adversarial Evader Tracking with a Probabilistic Pursuer under the Pursuit-Evasion Game Framework. On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels. Properties and Extensio …
In Search for Linear Relations in Sentence Embedding Spaces
| Title | In Search for Linear Relations in Sentence Embedding Spaces |
| Authors | Petra Barančíková, Ondřej Bojar |
| Abstract | We present an introductory investigation into continuous-space vector representations of sentences. We acquire pairs of very similar sentences differing only by a small alterations (such as change of a noun, adding an adjective, noun or punctuation) from datasets for natural language inference using a simple pattern method. We look into how such a small change within the sentence text affects its representation in the continuous space and how such alterations are reflected by some of the popular sentence embedding models. We found that vector differences of some embeddings actually reflect small changes within a sentence. |
| Tasks | Natural Language Inference, Sentence Embedding |
| Published | 2019-10-08 |
| URL | https://arxiv.org/abs/1910.03375v1 |
| https://arxiv.org/pdf/1910.03375v1.pdf | |
| PWC | https://paperswithcode.com/paper/in-search-for-linear-relations-in-sentence |
| Repo | |
| Framework | |
Mining User Behaviour from Smartphone data: a literature review
| Title | Mining User Behaviour from Smartphone data: a literature review |
| Authors | Valentino Servizi, Francisco C. Pereira, Marie K. Anderson, Otto A. Nielsen |
| Abstract | To study users’ travel behaviour and travel time between origin and destination, researchers employ travel surveys. Although there is consensus in the field about the potential, after over ten years of research and field experimentation, Smartphone-based travel surveys still did not take off to a large scale. Here, computer intelligence algorithms take the role that operators have in Traditional Travel Surveys; since we train each algorithm on data, performances rest on the data quality, thus on the ground truth. Inaccurate validations affect negatively: labels, algorithms’ training, travel diaries precision, and therefore data validation, within a very critical loop. Interestingly, boundaries are proven burdensome to push even for Machine Learning methods. To support optimal investment decisions for practitioners, we expose the drivers they should consider when assessing what they need against what they get. This paper highlights and examines the critical aspects of the underlying research and provides some recommendations: (i) from the device perspective, on the main physical limitations; (ii) from the application perspective, the methodological framework deployed for the automatic generation of travel diaries; (iii)from the ground truth perspective, the relationship between user interaction, methods, and data. |
| Tasks | |
| Published | 2019-12-24 |
| URL | https://arxiv.org/abs/1912.11259v2 |
| https://arxiv.org/pdf/1912.11259v2.pdf | |
| PWC | https://paperswithcode.com/paper/mining-user-behaviour-from-smartphone-data-a |
| Repo | |
| Framework | |
Active Adversarial Evader Tracking with a Probabilistic Pursuer under the Pursuit-Evasion Game Framework
| Title | Active Adversarial Evader Tracking with a Probabilistic Pursuer under the Pursuit-Evasion Game Framework |
| Authors | Varun Chandra Jammula, Anshul Rai, Yezhou Yang |
| Abstract | Given a mapped environment, we formulate the problem of visually tracking and following an evader using a probabilistic framework. In this work, we consider a non-holonomic robot with a limited visibility depth sensor in an indoor environment with obstacles. The mobile robot that follows the target is considered a pursuer and the agent being followed is considered an evader. We propose a probabilistic framework for both the pursuer and evader to achieve their conflicting goals. We introduce a smart evader that has information about the location of the pursuer. The goal of this variant of the evader is to avoid being tracked by the pursuer by using the visibility region information obtained from the pursuer, to further challenge the proposed smart pursuer. To validate the efficiency of the framework, we conduct several experiments in simulation by using Gazebo and evaluate the success rate of tracking an evader in various environments with different pursuer to evader speed ratios. Through our experiments we validate our hypothesis that a smart pursuer tracks an evader more effectively than a pursuer that just navigates in the environment randomly. We also validate that an evader that is aware of the actions of the pursuer is more successful at avoiding getting tracked by a smart pursuer than a random evader. Finally, we empirically show that while a smart pursuer does increase it’s average success rate of tracking compared to a random pursuer, there is an increased variance in its success rate distribution when the evader becomes aware of its actions. |
| Tasks | |
| Published | 2019-04-19 |
| URL | http://arxiv.org/abs/1904.09307v1 |
| http://arxiv.org/pdf/1904.09307v1.pdf | |
| PWC | https://paperswithcode.com/paper/190409307 |
| Repo | |
| Framework | |
On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels
| Title | On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels |
| Authors | Tengyuan Liang, Alexander Rakhlin, Xiyu Zhai |
| Abstract | We study the risk of minimum-norm interpolants of data in Reproducing Kernel Hilbert Spaces. Our upper bounds on the risk are of a multiple-descent shape for the various scalings of $d = n^{\alpha}$, $\alpha\in(0,1)$, for the input dimension $d$ and sample size $n$. Empirical evidence supports our finding that minimum-norm interpolants in RKHS can exhibit this unusual non-monotonicity in sample size; furthermore, locations of the peaks in our experiments match our theoretical predictions. Since gradient flow on appropriately initialized wide neural networks converges to a minimum-norm interpolant with respect to a certain kernel, our analysis also yields novel estimation and generalization guarantees for these over-parametrized models. At the heart of our analysis is a study of spectral properties of the random kernel matrix restricted to a filtration of eigen-spaces of the population covariance operator, and may be of independent interest. |
| Tasks | |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10292v2 |
| https://arxiv.org/pdf/1908.10292v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-risk-of-minimum-norm-interpolants-and |
| Repo | |
| Framework | |
Properties and Extensions of Alternating Path Relevance - I
| Title | Properties and Extensions of Alternating Path Relevance - I |
| Authors | David A. Plaisted |
| Abstract | When proving theorems from large sets of logical assertions, it can be helpful to restrict the search for a proof to those assertions that are relevant, that is, closely related to the theorem in some sense. For example, in the Watson system, a large knowledge base must rapidly be searched for relevant facts. It is possible to define formal concepts of relevance for propositional and first-order logic. Various concepts of relevance have been defined for this, and some have yielded good results on large problems. We consider here in particular a concept based on alternating paths.We present efficient graph-based methods for computing alternating path relevance and give some results indicating its effectiveness. We also propose an alternating path based extension of this relevance method to DPLL with an improved time bound, and give other extensions to alternating path relevance intended to improve its performance. |
| Tasks | |
| Published | 2019-05-21 |
| URL | https://arxiv.org/abs/1905.08842v1 |
| https://arxiv.org/pdf/1905.08842v1.pdf | |
| PWC | https://paperswithcode.com/paper/properties-and-extensions-of-alternating-path |
| Repo | |
| Framework | |
Image Based Identification of Ghanaian Timbers Using the XyloTron: Opportunities, Risks and Challenges
| Title | Image Based Identification of Ghanaian Timbers Using the XyloTron: Opportunities, Risks and Challenges |
| Authors | Prabu Ravindran, Emmanuel Ebanyenle, Alberta Asi Ebeheakey, Kofi Bonsu Abban, Ophilious Lambog, Richard Soares, Adriana Costa, Alex C. Wiedenhoeft |
| Abstract | Computer vision systems for wood identification have the potential to empower both producer and consumer countries to combat illegal logging if they can be deployed effectively in the field. In this work, carried out as part of an active international partnership with the support of UNIDO, we constructed and curated a field-relevant image data set to train a classifier for wood identification of $15$ commercial Ghanaian woods using the XyloTron system. We tested model performance in the laboratory, and then collected real-world field performance data across multiple sites using multiple XyloTron devices. We present efficacies of the trained model in the laboratory and in the field, discuss practical implications and challenges of deploying machine learning wood identification models, and conclude that field testing is a necessary step - and should be considered the gold-standard - for validating computer vision wood identification systems. |
| Tasks | |
| Published | 2019-12-01 |
| URL | https://arxiv.org/abs/1912.00296v1 |
| https://arxiv.org/pdf/1912.00296v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-based-identification-of-ghanaian |
| Repo | |
| Framework | |
Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems
| Title | Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems |
| Authors | Fei Mi, Minlie Huang, Jiyong Zhang, Boi Faltings |
| Abstract | Natural language generation (NLG) is an essential component of task-oriented dialogue systems. Despite the recent success of neural approaches for NLG, they are typically developed for particular domains with rich annotated training examples. In this paper, we study NLG in a low-resource setting to generate sentences in new scenarios with handful training examples. We formulate the problem from a meta-learning perspective, and propose a generalized optimization-based approach (Meta-NLG) based on the well-recognized model-agnostic meta-learning (MAML) algorithm. Meta-NLG defines a set of meta tasks, and directly incorporates the objective of adapting to new low-resource NLG tasks into the meta-learning optimization process. Extensive experiments are conducted on a large multi-domain dataset (MultiWoz) with diverse linguistic variations. We show that Meta-NLG significantly outperforms other training procedures in various low-resource configurations. We analyze the results, and demonstrate that Meta-NLG adapts extremely fast and well to low-resource situations. |
| Tasks | Meta-Learning, Task-Oriented Dialogue Systems, Text Generation |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05644v1 |
| https://arxiv.org/pdf/1905.05644v1.pdf | |
| PWC | https://paperswithcode.com/paper/meta-learning-for-low-resource-natural |
| Repo | |
| Framework | |
Adaptation Across Extreme Variations using Unlabeled Domain Bridges
| Title | Adaptation Across Extreme Variations using Unlabeled Domain Bridges |
| Authors | Shuyang Dai, Kihyuk Sohn, Yi-Hsuan Tsai, Lawrence Carin, Manmohan Chandraker |
| Abstract | We tackle an unsupervised domain adaptation problem for which the domain discrepancy between labeled source and unlabeled target domains is large, due to many factors of inter and intra-domain variation. While deep domain adaptation methods have been realized by reducing the domain discrepancy, these are difficult to apply when domains are significantly unalike. In this work, we propose to decompose domain discrepancy into multiple but smaller, and thus easier to minimize, discrepancies by introducing unlabeled bridging domains that connect the source and target domains. We realize our proposal through an extension of the domain adversarial neural network with multiple discriminators, each of which accounts for reducing discrepancies between unlabeled (bridge, target) domains and a mix of all precedent domains including source. We validate the effectiveness of our method on several adaptation tasks including object recognition and semantic segmentation. |
| Tasks | Domain Adaptation, Object Recognition, Semantic Segmentation, Unsupervised Domain Adaptation |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.02238v1 |
| https://arxiv.org/pdf/1906.02238v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptation-across-extreme-variations-using |
| Repo | |
| Framework | |
Semi-Supervised Learning, Causality and the Conditional Cluster Assumption
| Title | Semi-Supervised Learning, Causality and the Conditional Cluster Assumption |
| Authors | Julius von Kügelgen, Alexander Mey, Marco Loog, Bernhard Schölkopf |
| Abstract | While the success of semi-supervised learning (SSL) is still not fully understood, Sch"olkopf et al. (2012) have established a link to the principle of independent causal mechanisms. They conclude that SSL should be impossible when predicting a target variable from its causes, but possible when predicting it from its effects. Since both these cases are somewhat restrictive, we extend their work by considering classification using cause and effect features at the same time, such as predicting a disease from both risk factors and symptoms. While standard SSL exploits information contained in the marginal distribution of the inputs (to improve our estimate of the conditional distribution of target given inputs), we argue that in our more general setting we can use information in the conditional of effect features given causal features. We explore how this insight generalizes the previous understanding, and how it relates to and can be exploited for SSL. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.12081v2 |
| https://arxiv.org/pdf/1905.12081v2.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-learning-causality-and-the |
| Repo | |
| Framework | |
Light-Field for RF
| Title | Light-Field for RF |
| Authors | Manikanta Kotaru, Guy Satat, Ramesh Raskar, Sachin Katti |
| Abstract | Most computer vision systems and computational photography systems are visible light based which is a small fraction of the electromagnetic (EM) spectrum. In recent years radio frequency (RF) hardware has become more widely available, for example, many cars are equipped with a RADAR, and almost every home has a WiFi device. In the context of imaging, RF spectrum holds many advantages compared to visible light systems. In particular, in this regime, EM energy effectively interacts in different ways with matter. This property allows for many novel applications such as privacy preserving computer vision and imaging through absorbing and scattering materials in visible light such as walls. Here, we expand many of the concepts in computational photography in visible light to RF cameras. The main limitation of imaging with RF is the large wavelength that limits the imaging resolution when compared to visible light. However, the output of RF cameras is usually processed by computer vision and perception algorithms which would benefit from multi-modal sensing of the environment, and from sensing in situations in which visible light systems fail. To bridge the gap between computational photography and RF imaging, we expand the concept of light-field to RF. This work paves the way to novel computational sensing systems with RF. |
| Tasks | RF-based Pose Estimation |
| Published | 2019-01-13 |
| URL | http://arxiv.org/abs/1901.03953v1 |
| http://arxiv.org/pdf/1901.03953v1.pdf | |
| PWC | https://paperswithcode.com/paper/light-field-for-rf |
| Repo | |
| Framework | |
Efficient Batch Black-box Optimization with Deterministic Regret Bounds
| Title | Efficient Batch Black-box Optimization with Deterministic Regret Bounds |
| Authors | Yueming Lyu, Yuan Yuan, Ivor W. Tsang |
| Abstract | In this work, we investigate black-box optimization from the perspective of frequentist kernel methods. We propose a novel batch optimization algorithm, which jointly maximizes the acquisition function and select points from a whole batch in a holistic way. Theoretically, we derive regret bounds for both the noise-free and perturbation settings irrespective of the choice of kernel. Moreover, we analyze the property of the adversarial regret that is required by a robust initialization for Bayesian Optimization (BO). We prove that the adversarial regret bounds decrease with the decrease of covering radius, which provides a criterion for generating a point set to minimize the bound. We then propose fast searching algorithms to generate a point set with a small covering radius for the robust initialization. Experimental results on both synthetic benchmark problems and real-world problems show the effectiveness of the proposed algorithms. |
| Tasks | |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10041v3 |
| https://arxiv.org/pdf/1905.10041v3.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-batch-black-box-optimization-with |
| Repo | |
| Framework | |
Water Distribution System Design Using Multi-Objective Genetic Algorithm with External Archive and Local Search
| Title | Water Distribution System Design Using Multi-Objective Genetic Algorithm with External Archive and Local Search |
| Authors | Mahesh Patil, M. Naveen Naidu, A. Vasan, Murari R. R. Varma |
| Abstract | Hybridisation of the multi-objective optimisation algorithm NSGA-II and local search is proposed for water distribution system design. Results obtained with the proposed algorithm are presented for four medium-size water networks taken from the literature. Local search is found to be beneficial for one of the networks in terms of finding new solutions not reported earlier. It is also shown that simply using an external archive to save all non-dominated solutions visited by the population, even without local search, leads to substantial improvement in the non-dominated set produced by the algorithm. |
| Tasks | |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.08105v1 |
| https://arxiv.org/pdf/1905.08105v1.pdf | |
| PWC | https://paperswithcode.com/paper/water-distribution-system-design-using-multi-1 |
| Repo | |
| Framework | |
Unsupervised Deep Contrast Enhancement with Power Constraint for OLED Displays
| Title | Unsupervised Deep Contrast Enhancement with Power Constraint for OLED Displays |
| Authors | Yong-Goo Shin, Seung Park, Yoon-Jae Yeo, Min-Jae Yoo, Sung-Jea Ko |
| Abstract | Various power-constrained contrast enhancement (PCCE) techniques have been applied to an organic light emitting diode (OLED) display for reducing the power demands of the display while preserving the image quality. In this paper, we propose a new deep learning-based PCCE scheme that constrains the power consumption of the OLED displays while enhancing the contrast of the displayed image. In the proposed method, the power consumption is constrained by simply reducing the brightness a certain ratio, whereas the perceived visual quality is preserved as much as possible by enhancing the contrast of the image using a convolutional neural network (CNN). Furthermore, our CNN can learn the PCCE technique without a reference image by unsupervised learning. Experimental results show that the proposed method is superior to conventional ones in terms of image quality assessment metrics such as a visual saliency-induced index (VSI) and a measure of enhancement (EME). |
| Tasks | Image Quality Assessment |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.05916v5 |
| https://arxiv.org/pdf/1905.05916v5.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-deep-power-saving-and-contrast |
| Repo | |
| Framework | |
Learning piecewise Lipschitz functions in changing environments
| Title | Learning piecewise Lipschitz functions in changing environments |
| Authors | Maria-Florina Balcan, Travis Dick, Dravyansh Sharma |
| Abstract | Optimization in the presence of sharp (non-Lipschitz), unpredictable (w.r.t.\ time and amount) changes is a challenging and largely unexplored problem of great significance. We consider the class of piecewise Lipschitz functions, which is the most general online setting considered in the literature for the problem, and arises naturally in various combinatorial algorithm selection problems where utility functions can have sharp discontinuities. The usual performance metric of `static’ regret minimizes the gap between the payoff accumulated and that of the best fixed point for the entire duration, and thus fails to capture changing environments. Shifting regret is a useful alternative, which allows for up to $s$ environment {\it shifts}. In this work we provide an $O(\sqrt{sdT\log T}+sT^{1-\beta})$ regret bound for $\beta$-dispersed functions, where $\beta$ roughly quantifies the rate at which discontinuities appear in the utility functions in expectation (typically $\beta\ge1/2$ in problems of practical interest). We also present a lower bound tight up to sub-logarithmic factors. We further obtain improved bounds when selecting from a small pool of experts. We empirically demonstrate a key application of our algorithms to online clustering problems on popular benchmarks. | |
| Tasks | |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09137v3 |
| https://arxiv.org/pdf/1907.09137v3.pdf | |
| PWC | https://paperswithcode.com/paper/online-optimization-of-piecewise-lipschitz |
| Repo | |
| Framework | |
Training on test data: Removing near duplicates in Fashion-MNIST
| Title | Training on test data: Removing near duplicates in Fashion-MNIST |
| Authors | Christopher Geier |
| Abstract | MNIST and Fashion MNIST are extremely popular for testing in the machine learning space. Fashion MNIST improves on MNIST by introducing a harder problem, increasing the diversity of testing sets, and more accurately representing a modern computer vision task. In order to increase the data quality of FashionMNIST, this paper investigates near duplicate images between training and testing sets. Near-duplicates between testing and training sets artificially increase the testing accuracy of machine learning models. This paper identifies near-duplicate images in Fashion MNIST and proposes a dataset with near-duplicates removed. |
| Tasks | |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.08255v1 |
| https://arxiv.org/pdf/1906.08255v1.pdf | |
| PWC | https://paperswithcode.com/paper/training-on-test-data-removing-near |
| Repo | |
| Framework | |
