April 1, 2020

3326 words 16 mins read

Paper Group ANR 453

On the Minimum Achievable Age of Information for General Service-Time Distributions. Advances in Bandits with Knapsacks. Thermal coupling and effect of subharmonic synchronization in a system of two VO2 based oscillators. Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks. CookGAN: Meal Image Synthesis from Ingredients. The …

On the Minimum Achievable Age of Information for General Service-Time Distributions


Title	On the Minimum Achievable Age of Information for General Service-Time Distributions
Authors	Jaya Prakash Champati, Ramana R. Avula, Tobias J. Oechtering, James Gross
Abstract	There is a growing interest in analysing the freshness of data in networked systems. Age of Information (AoI) has emerged as a popular metric to quantify this freshness at a given destination. There has been a significant research effort in optimizing this metric in communication and networking systems under different settings. In contrast to previous works, we are interested in a fundamental question, what is the minimum achievable AoI in any single-server-single-source queuing system for a given service-time distribution? To address this question, we study a problem of optimizing AoI under service preemptions. Our main result is on the characterization of the minimum achievable average peak AoI (PAoI). We obtain this result by showing that a fixed-threshold policy is optimal in the set of all randomized-threshold causal policies. We use the characterization to provide necessary and sufficient conditions for the service-time distributions under which preemptions are beneficial.
Tasks
Published	2020-01-19
URL	https://arxiv.org/abs/2001.06831v1
PDF	https://arxiv.org/pdf/2001.06831v1.pdf
PWC	https://paperswithcode.com/paper/on-the-minimum-achievable-age-of-information
Repo
Framework

Advances in Bandits with Knapsacks


Title	Advances in Bandits with Knapsacks
Authors	Karthik Abinav Sankararaman, Aleksandrs Slivkins
Abstract	“Bandits with Knapsacks” (\BwK) is a general model for multi-armed bandits under supply/budget constraints. While worst-case regret bounds for \BwK are well-understood, we focus on logarithmic instance-dependent regret bounds. We largely resolve them for one limited resource other than time, and for known, deterministic resource consumption. We also bound regret within a given round (“simple regret”). One crucial technique analyzes the sum of the confidence terms of the chosen arms. This technique allows to import the insights from prior work on bandits without resources, which leads to several extensions.
Tasks	Multi-Armed Bandits
Published	2020-02-01
URL	https://arxiv.org/abs/2002.00253v1
PDF	https://arxiv.org/pdf/2002.00253v1.pdf
PWC	https://paperswithcode.com/paper/advances-in-bandits-with-knapsacks
Repo
Framework

Thermal coupling and effect of subharmonic synchronization in a system of two VO2 based oscillators


Title	Thermal coupling and effect of subharmonic synchronization in a system of two VO2 based oscillators
Authors	Andrei Velichko, Maksim Belyaev, Vadim Putrolaynen, Valentin Perminov, Alexander Pergament
Abstract	We explore a prototype of an oscillatory neural network (ONN) based on vanadium dioxide switching devices. The model system under study represents two oscillators based on thermally coupled VO2 switches. Numerical simulation shows that the effective action radius RTC of coupling depends both on the total energy released during switching and on the average power. It is experimentally and numerically proved that the temperature change dT commences almost synchronously with the released power peak and T-coupling reveals itself up to a frequency of about 10 kHz. For the studied switching structure configuration, the RTC value varies over a wide range from 4 to 45 mkm, depending on the external circuit capacitance C and resistance Ri, but the variation of Ri is more promising from the practical viewpoint. In the case of a “weak” coupling, synchronization is accompanied by attraction effect and decrease of the main spectra harmonics width. In the case of a “strong” coupling, the number of effects increases, synchronization can occur on subharmonics resulting in multilevel stable synchronization of two oscillators. An advanced algorithm for synchronization efficiency and subharmonic ratio calculation is proposed. It is shown that of the two oscillators the leading one is that with a higher main frequency, and, in addition, the frequency stabilization effect is observed. Also, in the case of a strong thermal coupling, the limit of the supply current parameters, for which the oscillations exist, expands by ~ 10 %. The obtained results have a universal character and open up a new kind of coupling in ONNs, namely, T-coupling, which allows for easy transition from 2D to 3D integration. The effect of subharmonic synchronization hold promise for application in classification and pattern recognition.
Tasks
Published	2020-01-06
URL	https://arxiv.org/abs/2001.01382v1
PDF	https://arxiv.org/pdf/2001.01382v1.pdf
PWC	https://paperswithcode.com/paper/thermal-coupling-and-effect-of-subharmonic
Repo
Framework

Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks


Title	Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks
Authors	Russell Tsuchida, Tim Pearce, Christopher van der Heide, Fred Roosta, Marcus Gallagher
Abstract	Analysing and computing with Gaussian processes arising from infinitely wide neural networks has recently seen a resurgence in popularity. Despite this, many explicit covariance functions of networks with activation functions used in modern networks remain unknown. Furthermore, while the kernels of deep networks can be computed iteratively, theoretical understanding of deep kernels is lacking, particularly with respect to fixed-point dynamics. Firstly, we derive the covariance functions of MLPs with exponential linear units and Gaussian error linear units and evaluate the performance of the limiting Gaussian processes on some benchmarks. Secondly, and more generally, we introduce a framework for analysing the fixed-point dynamics of iterated kernels corresponding to a broad range of activation functions. We find that unlike some previously studied neural network kernels, these new kernels exhibit non-trivial fixed-point dynamics which are mirrored in finite-width neural networks.
Tasks	Gaussian Processes
Published	2020-02-20
URL	https://arxiv.org/abs/2002.08517v2
PDF	https://arxiv.org/pdf/2002.08517v2.pdf
PWC	https://paperswithcode.com/paper/avoiding-kernel-fixed-points-computing-with
Repo
Framework

CookGAN: Meal Image Synthesis from Ingredients


Title	CookGAN: Meal Image Synthesis from Ingredients
Authors	Fangda Han, Ricardo Guerrero, Vladimir Pavlovic
Abstract	In this work we propose a new computational framework, based on generative deep models, for synthesis of photo-realistic food meal images from textual list of its ingredients. Previous works on synthesis of images from text typically rely on pre-trained text models to extract text features, followed by generative neural networks (GAN) aimed to generate realistic images conditioned on the text features. These works mainly focus on generating spatially compact and well-defined categories of objects, such as birds or flowers, but meal images are significantly more complex, consisting of multiple ingredients whose appearance and spatial qualities are further modified by cooking methods. To generate real-like meal images from ingredients, we propose Cook Generative Adversarial Networks (CookGAN), CookGAN first builds an attention-based ingredients-image association model, which is then used to condition a generative neural network tasked with synthesizing meal images. Furthermore, a cycle-consistent constraint is added to further improve image quality and control appearance. Experiments show our model is able to generate meal images corresponding to the ingredients.
Tasks	Image Generation
Published	2020-02-25
URL	https://arxiv.org/abs/2002.11493v1
PDF	https://arxiv.org/pdf/2002.11493v1.pdf
PWC	https://paperswithcode.com/paper/cookgan-meal-image-synthesis-from-ingredients
Repo
Framework


Title	The growing echo chamber of social media: Measuring temporal and social contagion dynamics for over 150 languages on Twitter for 2009–2020
Authors	Thayer Alshaabi, David R. Dewhurst, Joshua R. Minot, Michael V. Arnold, Jane L. Adams, Christopher M. Danforth, Peter Sheridan Dodds
Abstract	Working from a dataset of 118 billion messages running from the start of 2009 to the end of 2019, we identify and explore the relative daily use of over 150 languages on Twitter. We find that eight languages comprise 80% of all tweets, with English, Japanese, Spanish, and Portuguese being the most dominant. To quantify each language’s level of being a Twitter `echo chamber' over time, we compute the` contagion ratio’: the balance of retweets to organic messages. We find that for the most common languages on Twitter there is a growing tendency, though not universal, to retweet rather than share new content. By the end of 2019, the contagion ratios for half of the top 30 languages, including English and Spanish, had reached above 1—the naive contagion threshold. In 2019, the top 5 languages with the highest average daily ratios were, in order, Thai (7.3), Hindi, Tamil, Urdu, and Catalan, while the bottom 5 were Russian, Swedish, Esperanto, Cebuano, and Finnish (0.26). Further, we show that over time, the contagion ratios for most common languages are growing more strongly than those of rare languages.
Tasks
Published	2020-03-07
URL	https://arxiv.org/abs/2003.03667v2
PDF	https://arxiv.org/pdf/2003.03667v2.pdf
PWC	https://paperswithcode.com/paper/the-growing-echo-chamber-of-social-media
Repo
Framework

Deep Learning-based End-to-end Diagnosis System for Avascular Necrosis of Femoral Head


Title	Deep Learning-based End-to-end Diagnosis System for Avascular Necrosis of Femoral Head
Authors	Yang Li, Yan Li, Hua Tian
Abstract	As the first diagnostic imaging modality of avascular necrosis of the femoral head (AVNFH), accurately staging AVNFH from a plain radiograph is critical and challenging for orthopedists. Thus, we propose a deep learning-based AVNFH diagnosis system (AVN-net). The proposed AVN-net reads plain radiographs of the pelvis, conducts diagnosis, and visualizes results automatically. Deep convolutional neural networks are trained to provide an end-to-end diagnosis solution, covering femoral head detection, exam-view/sides identification, AVNFH diagnosis, and key clinical note generation subtasks. AVN-net is able to obtain state-of-the-art testing AUC of 0.95 (95% CI: 0.92-0.98) in AVNFH detection and significantly greater F1 scores (p<0.01) than less-to-moderately experienced orthopedists in all diagnostic tests. Furthermore, two real-world pilot studies were conducted for diagnosis support and education assistance, respectively, to assess the utility of AVN-net. The experimental results are promising. With the AVN-net diagnosis as a reference, the diagnostic accuracy and consistency of all orthopedists considerably improved while requiring only 1/4 of the time. Students self-studying the AVNFH diagnosis using AVN-net can learn better and faster than the control group. To the best of our knowledge, this study is the first research on the prospective use of a deep learning-based diagnosis system for AVNFH by conducting two pilot studies representing real-world application scenarios. We have demonstrated that the proposed AVN-net achieves expert-level AVNFH diagnosis performance, provides efficient support in clinical decision-making, and effectively passes clinical experience to students.
Tasks	Decision Making, Head Detection
Published	2020-02-12
URL	https://arxiv.org/abs/2002.05536v1
PDF	https://arxiv.org/pdf/2002.05536v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-end-to-end-diagnosis
Repo
Framework

Robotic Cane as a Soft SuperLimb for Elderly Sit-to-Stand Assistance


Title	Robotic Cane as a Soft SuperLimb for Elderly Sit-to-Stand Assistance
Authors	Xia Wu, Haiyuan Liu, Ziqi Liu, Mingdong Chen, Fang Wan, Chenglong Fu, Harry Asada, Zheng Wang, Chaoyang Song
Abstract	Many researchers have identified robotics as a potential solution to the aging population faced by many developed and developing countries. If so, how should we address the cognitive acceptance and ambient control of elderly assistive robots through design? In this paper, we proposed an explorative design of an ambient SuperLimb (Supernumerary Robotic Limb) system that involves a pneumatically-driven robotic cane for at-home motion assistance, an inflatable vest for compliant human-robot interaction, and a depth sensor for ambient intention detection. The proposed system aims at providing active assistance during the sit-to-stand transition for at-home usage by the elderly at the bedside, in the chair, and on the toilet. We proposed a modified biomechanical model with a linear cane robot for closed-loop control implementation. We validated the design feasibility of the proposed ambient SuperLimb system including the biomechanical model, our result showed the advantages in reducing lower limb efforts and elderly fall risks, yet the detection accuracy using depth sensing and adjustments on the model still require further research in the future. Nevertheless, we summarized empirical guidelines to support the ambient design of elderly-assistive SuperLimb systems for lower limb functional augmentation.
Tasks
Published	2020-02-29
URL	https://arxiv.org/abs/2003.02080v1
PDF	https://arxiv.org/pdf/2003.02080v1.pdf
PWC	https://paperswithcode.com/paper/robotic-cane-as-a-soft-superlimb-for-elderly
Repo
Framework

Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination


Title	Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination
Authors	Pratul P. Srinivasan, Ben Mildenhall, Matthew Tancik, Jonathan T. Barron, Richard Tucker, Noah Snavely
Abstract	We present a deep learning solution for estimating the incident illumination at any 3D location within a scene from an input narrow-baseline stereo image pair. Previous approaches for predicting global illumination from images either predict just a single illumination for the entire scene, or separately estimate the illumination at each 3D location without enforcing that the predictions are consistent with the same 3D scene. Instead, we propose a deep learning model that estimates a 3D volumetric RGBA model of a scene, including content outside the observed field of view, and then uses standard volume rendering to estimate the incident illumination at any 3D location within that volume. Our model is trained without any ground truth 3D data and only requires a held-out perspective view near the input stereo pair and a spherical panorama taken within each scene as supervision, as opposed to prior methods for spatially-varying lighting estimation, which require ground truth scene geometry for training. We demonstrate that our method can predict consistent spatially-varying lighting that is convincing enough to plausibly relight and insert highly specular virtual objects into real images.
Tasks
Published	2020-03-18
URL	https://arxiv.org/abs/2003.08367v1
PDF	https://arxiv.org/pdf/2003.08367v1.pdf
PWC	https://paperswithcode.com/paper/lighthouse-predicting-lighting-volumes-for
Repo
Framework

TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation


Title	TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation
Authors	Shaojie Jiang, Thomas Wolf, Christof Monz, Maarten de Rijke
Abstract	Natural Language Generation (NLG) models are prone to generating repetitive utterances. In this work, we study the repetition problem for encoder-decoder models, using both recurrent neural network (RNN) and transformer architectures. To this end, we consider the chit-chat task, where the problem is more prominent than in other tasks that need encoder-decoder architectures. We first study the influence of model architectures. By using pre-attention and highway connections for RNNs, we manage to achieve lower repetition rates. However, this method does not generalize to other models such as transformers. We hypothesize that the deeper reason is that in the training corpora, there are hard tokens that are more difficult for a generative model to learn than others and, once learning has finished, hard tokens are still under-learned, so that repetitive generations are more likely to happen. Based on this hypothesis, we propose token loss dynamic reweighting (TLDR) that applies differentiable weights to individual token losses. By using higher weights for hard tokens and lower weights for easy tokens, NLG models are able to learn individual tokens at different paces. Experiments on chit-chat benchmark datasets show that TLDR is more effective in repetition reduction for both RNN and transformer architectures than baselines using different weighting functions.
Tasks	Text Generation
Published	2020-03-26
URL	https://arxiv.org/abs/2003.11963v1
PDF	https://arxiv.org/pdf/2003.11963v1.pdf
PWC	https://paperswithcode.com/paper/tldr-token-loss-dynamic-reweighting-for
Repo
Framework

Constrained Deep Reinforcement Learning for Energy Sustainable Multi-UAV based Random Access IoT Networks with NOMA


Title	Constrained Deep Reinforcement Learning for Energy Sustainable Multi-UAV based Random Access IoT Networks with NOMA
Authors	Sami Khairy, Prasanna Balaprakash, Lin X. Cai, Yu Cheng
Abstract	In this paper, we apply the Non-Orthogonal Multiple Access (NOMA) technique to improve the massive channel access of a wireless IoT network where solar-powered Unmanned Aerial Vehicles (UAVs) relay data from IoT devices to remote servers. Specifically, IoT devices contend for accessing the shared wireless channel using an adaptive $p$-persistent slotted Aloha protocol; and the solar-powered UAVs adopt Successive Interference Cancellation (SIC) to decode multiple received data from IoT devices to improve access efficiency. To enable an energy-sustainable capacity-optimal network, we study the joint problem of dynamic multi-UAV altitude control and multi-cell wireless channel access management of IoT devices as a stochastic control problem with multiple energy constraints. To learn an optimal control policy, we first formulate this problem as a Constrained Markov Decision Process (CMDP), and propose an online model-free Constrained Deep Reinforcement Learning (CDRL) algorithm based on Lagrangian primal-dual policy optimization to solve the CMDP. Extensive simulations demonstrate that our proposed algorithm learns a cooperative policy among UAVs in which the altitude of UAVs and channel access probability of IoT devices are dynamically and jointly controlled to attain the maximal long-term network capacity while maintaining energy sustainability of UAVs. The proposed algorithm outperforms Deep RL based solutions with reward shaping to account for energy costs, and achieves a temporal average system capacity which is $82.4%$ higher than that of a feasible DRL based solution, and only $6.47%$ lower compared to that of the energy-constraint-free system.
Tasks
Published	2020-01-31
URL	https://arxiv.org/abs/2002.00073v2
PDF	https://arxiv.org/pdf/2002.00073v2.pdf
PWC	https://paperswithcode.com/paper/constrained-deep-reinforcement-learning-for
Repo
Framework

Convolutional Neural Networks as Summary Statistics for Approximate Bayesian Computation


Title	Convolutional Neural Networks as Summary Statistics for Approximate Bayesian Computation
Authors	Mattias Åkesson, Prashant Singh, Fredrik Wrede, Andreas Hellander
Abstract	Approximate Bayesian Computation is widely used in systems biology for inferring parameters in stochastic gene regulatory network models. Its performance hinges critically on the ability to summarize high-dimensional system responses such as time series into a few informative, low-dimensional summary statistics. The quality of those statistics critically affect the accuracy of the inference. Existing methods to select the best subset out of a pool of candidate statistics do not scale well with large pools. Since it is imperative for good performance this becomes a serious bottleneck when doing inference on complex and high-dimensional problems. This paper proposes a convolutional neural network architecture for automatically learning informative summary statistics of temporal responses. We show that the proposed network can effectively circumvent the statistics selection problem as a preprocessing step to ABC for a challenging inference problem learning parameters in a high-dimensional stochastic genetic oscillator. We also study the impact of experimental design on network performance by comparing different data richness and different data acquisition strategies.
Tasks	Time Series
Published	2020-01-31
URL	https://arxiv.org/abs/2001.11760v1
PDF	https://arxiv.org/pdf/2001.11760v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-networks-as-summary
Repo
Framework

Genetic Algorithms for Redundancy in Interaction Testing


Title	Genetic Algorithms for Redundancy in Interaction Testing
Authors	Ryan E. Dougherty
Abstract	It is imperative for testing to determine if the components within large-scale software systems operate functionally. Interaction testing involves designing a suite of tests, which guarantees to detect a fault if one exists among a small number of components interacting together. The cost of this testing is typically modeled by the number of tests, and thus much effort has been taken in reducing this number. Here, we incorporate redundancy into the model, which allows for testing in non-deterministic environments. Existing algorithms for constructing these test suites usually involve one “fast” algorithm for generating most of the tests, and another “slower” algorithm to “complete” the test suite. We employ a genetic algorithm that generalizes these approaches that also incorporates redundancy by increasing the number of algorithms chosen, which we call “stages.” By increasing the number of stages, we show that not only can the number of tests be reduced compared to existing techniques, but the computational time in generating them is also greatly reduced.
Tasks
Published	2020-02-13
URL	https://arxiv.org/abs/2002.05421v1
PDF	https://arxiv.org/pdf/2002.05421v1.pdf
PWC	https://paperswithcode.com/paper/genetic-algorithms-for-redundancy-in
Repo
Framework

Utilizing Network Properties to Detect Erroneous Inputs


Title	Utilizing Network Properties to Detect Erroneous Inputs
Authors	Matt Gorbett, Nathaniel Blanchard
Abstract	Neural networks are vulnerable to a wide range of erroneous inputs such as adversarial, corrupted, out-of-distribution, and misclassified examples. In this work, we train a linear SVM classifier to detect these four types of erroneous data using hidden and softmax feature vectors of pre-trained neural networks. Our results indicate that these faulty data types generally exhibit linearly separable activation properties from correct examples, giving us the ability to reject bad inputs with no extra training or overhead. We experimentally validate our findings across a diverse range of datasets, domains, pre-trained models, and adversarial attacks.
Tasks
Published	2020-02-28
URL	https://arxiv.org/abs/2002.12520v1
PDF	https://arxiv.org/pdf/2002.12520v1.pdf
PWC	https://paperswithcode.com/paper/utilizing-network-properties-to-detect
Repo
Framework

Efficient, Noise-Tolerant, and Private Learning via Boosting


Title	Efficient, Noise-Tolerant, and Private Learning via Boosting
Authors	Mark Bun, Marco Leandro Carmosino, Jessica Sorrell
Abstract	We introduce a simple framework for designing private boosting algorithms. We give natural conditions under which these algorithms are differentially private, efficient, and noise-tolerant PAC learners. To demonstrate our framework, we use it to construct noise-tolerant and private PAC learners for large-margin halfspaces whose sample complexity does not depend on the dimension. We give two sample complexity bounds for our large-margin halfspace learner. One bound is based only on differential privacy, and uses this guarantee as an asset for ensuring generalization. This first bound illustrates a general methodology for obtaining PAC learners from privacy, which may be of independent interest. The second bound uses standard techniques from the theory of large-margin classification (the fat-shattering dimension) to match the best known sample complexity for differentially private learning of large-margin halfspaces, while additionally tolerating random label noise.
Tasks
Published	2020-02-04
URL	https://arxiv.org/abs/2002.01100v1
PDF	https://arxiv.org/pdf/2002.01100v1.pdf
PWC	https://paperswithcode.com/paper/efficient-noise-tolerant-and-private-learning
Repo
Framework