April 3, 2020

3431 words 17 mins read

Paper Group ANR 71

Student/Teacher Advising through Reward Augmentation. A General Framework to Analyze Stochastic Linear Bandit. Improving the Adversarial Robustness of Transfer Learning via Noisy Feature Distillation. Amortized variance reduction for doubly stochastic objectives. i-flow: High-dimensional Integration and Sampling with Normalizing Flows. BLCS: Brain- …

Student/Teacher Advising through Reward Augmentation


Title	Student/Teacher Advising through Reward Augmentation
Authors	Cameron Reid
Abstract	Transfer learning is an important new subfield of multiagent reinforcement learning that aims to help an agent learn about a problem by using knowledge that it has gained solving another problem, or by using knowledge that is communicated to it by an agent who already knows the problem. This is useful when one wishes to change the architecture or learning algorithm of an agent (so that the new knowledge need not be built “from scratch”), when new agents are frequently introduced to the environment with no knowledge, or when an agent must adapt to similar but different problems. Great progress has been made in the agent-to-agent case using the Teacher/Student framework proposed by (Torrey and Taylor 2013). However, that approach requires that learning from a teacher be treated differently from learning in every other reinforcement learning context. In this paper, I propose a method which allows the teacher/student framework to be applied in a way that fits directly and naturally into the more general reinforcement learning framework by integrating the teacher feedback into the reward signal received by the learning agent. I show that this approach can significantly improve the rate of learning for an agent playing a one-player stochastic game; I give examples of potential pitfalls of the approach; and I propose further areas of research building on this framework.
Tasks	Transfer Learning
Published	2020-02-07
URL	https://arxiv.org/abs/2002.02938v1
PDF	https://arxiv.org/pdf/2002.02938v1.pdf
PWC	https://paperswithcode.com/paper/studentteacher-advising-through-reward
Repo
Framework

A General Framework to Analyze Stochastic Linear Bandit


Title	A General Framework to Analyze Stochastic Linear Bandit
Authors	Nima Hamidi, Mohsen Bayati
Abstract	In this paper we study the well-known stochastic linear bandit problem where a decision-maker sequentially chooses among a set of given actions in R^d, observes their noisy reward, and aims to maximize her cumulative expected reward over a horizon of length T. We introduce a general family of algorithms for the problem and prove that they are rate optimal. We also show that several well-known algorithms for the problem such as optimism in the face of uncertainty linear bandit (OFUL) and Thompson sampling (TS) are special cases of our family of algorithms. Therefore, we obtain a unified proof of rate optimality for both of these algorithms. Our results include both adversarial action sets (when actions are potentially selected by an adversary) and stochastic action sets (when actions are independently drawn from an unknown distribution). In terms of regret, our results apply to both Bayesian and worst-case regret settings. Our new unified analysis technique also yields a number of new results and solves two open problems known in the literature. Most notably, (1) we show that TS can incur a linear worst-case regret, unless it uses inflated (by a factor of $\sqrt{d}$) posterior variances at each step. This shows that the best known worst-case regret bound for TS, that is given by (Agrawal & Goyal, 2013; Abeille et al., 2017) and is worse (by a factor of \sqrt(d)) than the best known Bayesian regret bound given by Russo and Van Roy (2014) for TS, is tight. This settles an open problem stated in Russo et al., 2018. (2) Our proof also shows that TS can incur a linear Bayesian regret if it does not use the correct prior or noise distribution. (3) Under a generalized gap assumption and a margin condition, as in Goldenshluger & Zeevi, 2013, we obtain a poly-logarithmic (in $T$) regret bound for OFUL and TS in the stochastic setting.
Tasks
Published	2020-02-12
URL	https://arxiv.org/abs/2002.05152v1
PDF	https://arxiv.org/pdf/2002.05152v1.pdf
PWC	https://paperswithcode.com/paper/a-general-framework-to-analyze-stochastic
Repo
Framework

Improving the Adversarial Robustness of Transfer Learning via Noisy Feature Distillation


Title	Improving the Adversarial Robustness of Transfer Learning via Noisy Feature Distillation
Authors	Ting-Wu Chin, Cha Zhang, Diana Marculescu
Abstract	Fine-tuning through knowledge transfer from a pre-trained model on a large-scale dataset is a widely spread approach to effectively build models on small-scale datasets. However, recent literature has shown that such a fine-tuning approach is vulnerable to adversarial examples based on the pre-trained model, which raises security concerns for many industrial applications. In contrast, models trained with random initialization are much more robust to such attacks, although these models often exhibit much lower accuracy. In this work, we propose noisy feature distillation, a new transfer learning method that trains a network from random initialization while achieving clean-data performance competitive with fine-tuning. In addition, the method is shown empirically to significantly improve the robustness compared to fine-tuning with 15x reduction in attack success rate for ResNet-50, from 66% to 4.4% averaged across Stanford 120 Dogs, Caltech-UCSD 200 Birds, Stanford 40 Actions, MIT 67 Indoor Scenes, and Oxford 102 Flowers datasets. Code is available at https://github.com/cmu-enyac/Renofeation.
Tasks	Transfer Learning
Published	2020-02-07
URL	https://arxiv.org/abs/2002.02998v1
PDF	https://arxiv.org/pdf/2002.02998v1.pdf
PWC	https://paperswithcode.com/paper/improving-the-adversarial-robustness-of
Repo
Framework

Amortized variance reduction for doubly stochastic objectives


Title	Amortized variance reduction for doubly stochastic objectives
Authors	Ayman Boustati, Sattar Vakili, James Hensman, ST John
Abstract	Approximate inference in complex probabilistic models such as deep Gaussian processes requires the optimisation of doubly stochastic objective functions. These objectives incorporate randomness both from mini-batch subsampling of the data and from Monte Carlo estimation of expectations. If the gradient variance is high, the stochastic optimisation problem becomes difficult with a slow rate of convergence. Control variates can be used to reduce the variance, but past approaches do not take into account how mini-batch stochasticity affects sampling stochasticity, resulting in sub-optimal variance reduction. We propose a new approach in which we use a recognition network to cheaply approximate the optimal control variate for each mini-batch, with no additional model gradient computations. We illustrate the properties of this proposal and test its performance on logistic regression and deep Gaussian processes.
Tasks	Gaussian Processes
Published	2020-03-09
URL	https://arxiv.org/abs/2003.04125v1
PDF	https://arxiv.org/pdf/2003.04125v1.pdf
PWC	https://paperswithcode.com/paper/amortized-variance-reduction-for-doubly
Repo
Framework

i-flow: High-dimensional Integration and Sampling with Normalizing Flows


Title	i-flow: High-dimensional Integration and Sampling with Normalizing Flows
Authors	Christina Gao, Joshua Isaacson, Claudius Krause
Abstract	In many fields of science, high-dimensional integration is required. Numerical methods have been developed to evaluate these complex integrals. We introduce the code i-flow, a python package that performs high-dimensional numerical integration utilizing normalizing flows. Normalizing flows are machine-learned, bijective mappings between two distributions. i-flow can also be used to sample random points according to complicated distributions in high dimensions. We compare i-flow to other algorithms for high-dimensional numerical integration and show that i-flow outperforms them for high dimensional correlated integrals.
Tasks
Published	2020-01-15
URL	https://arxiv.org/abs/2001.05486v1
PDF	https://arxiv.org/pdf/2001.05486v1.pdf
PWC	https://paperswithcode.com/paper/i-flow-high-dimensional-integration-and
Repo
Framework

BLCS: Brain-Like based Distributed Control Security in Cyber Physical Systems


Title	BLCS: Brain-Like based Distributed Control Security in Cyber Physical Systems
Authors	Hui Yang, Kaixuan Zhan, Michel Kadoch, Yongshen Liang, Mohamed Cheriet
Abstract	Cyber-physical system (CPS) has operated, controlled and coordinated the physical systems integrated by a computing and communication core applied in industry 4.0. To accommodate CPS services, fog radio and optical networks (F-RON) has become an important supporting physical cyber infrastructure taking advantage of both the inherent ubiquity of wireless technology and the large capacity of optical networks. However, cyber security is the biggest issue in CPS scenario as there is a tradeoff between security control and privacy exposure in F-RON. To deal with this issue, we propose a brain-like based distributed control security (BLCS) architecture for F-RON in CPS, by introducing a brain-like security (BLS) scheme. BLCS can accomplish the secure cross-domain control among tripartite controllers verification in the scenario of decentralized F-RON for distributed computing and communications, which has no need to disclose the private information of each domain against cyber-attacks. BLS utilizes parts of information to perform control identification through relation network and deep learning of behavior library. The functional modules of BLCS architecture are illustrated including various controllers and brain-like knowledge base. The interworking procedures in distributed control security modes based on BLS are described. The overall feasibility and efficiency of architecture are experimentally verified on the software defined network testbed in terms of average mistrust rate, path provisioning latency, packet loss probability and blocking probability. The emulation results are obtained and dissected based on the testbed.
Tasks
Published	2020-02-08
URL	https://arxiv.org/abs/2002.06259v1
PDF	https://arxiv.org/pdf/2002.06259v1.pdf
PWC	https://paperswithcode.com/paper/blcs-brain-like-based-distributed-control
Repo
Framework

mmFall: Fall Detection using 4D MmWave Radar and Variational Recurrent Autoencoder


Title	mmFall: Fall Detection using 4D MmWave Radar and Variational Recurrent Autoencoder
Authors	Feng Jin, Arindam Sengupta, Siyang Cao
Abstract	In this paper we propose mmFall - a novel fall detection system, which comprises of (i) the emerging millimeter-wave (mmWave) radar sensor to collect the human body’s point cloud along with the body centroid, and (ii) a variational recurrent autoencoder (VRAE) to compute the anomaly level of the body motion based on the acquired point cloud. A fall is claimed to have occurred when the spike in anomaly level and the drop in centroid height occur simultaneously. The mmWave radar sensor provides several advantages, such as privacycompliance and high-sensitivity to motion, over the traditional sensing modalities. However, (i) randomness in radar point cloud data and (ii) difficulties in fall collection/labeling in the traditional supervised fall detection approaches are the two main challenges. To overcome the randomness in radar data, the proposed VRAE uses variational inference, a probabilistic approach rather than the traditional deterministic approach, to infer the posterior probability of the body’s latent motion state at each frame, followed by a recurrent neural network (RNN) to learn the temporal features of the motion over multiple frames. Moreover, to circumvent the difficulties in fall data collection/labeling, the VRAE is built upon an autoencoder architecture in a semi-supervised approach, and trained on only normal activities of daily living (ADL) such that in the inference stage the VRAE will generate a spike in the anomaly level once an abnormal motion, such as fall, occurs. During the experiment, we implemented the VRAE along with two other baselines, and tested on the dataset collected in an apartment. The receiver operating characteristic (ROC) curve indicates that our proposed model outperforms the other two baselines, and achieves 98% detection out of 50 falls at the expense of just 2 false alarms.
Tasks
Published	2020-03-05
URL	https://arxiv.org/abs/2003.02386v3
PDF	https://arxiv.org/pdf/2003.02386v3.pdf
PWC	https://paperswithcode.com/paper/mmfall-fall-detection-using-4d-mmwave-radar
Repo
Framework

Exploring BERT Parameter Efficiency on the Stanford Question Answering Dataset v2.0


Title	Exploring BERT Parameter Efficiency on the Stanford Question Answering Dataset v2.0
Authors	Eric Hulburd
Abstract	In this paper we explore the parameter efficiency of BERT arXiv:1810.04805 on version 2.0 of the Stanford Question Answering dataset (SQuAD2.0). We evaluate the parameter efficiency of BERT while freezing a varying number of final transformer layers as well as including the adapter layers proposed in arXiv:1902.00751. Additionally, we experiment with the use of context-aware convolutional (CACNN) filters, as described in arXiv:1709.08294v3, as a final augmentation layer for the SQuAD2.0 tasks. This exploration is motivated in part by arXiv:1907.10597, which made a compelling case for broadening the evaluation criteria of artificial intelligence models to include various measures of resource efficiency. While we do not evaluate these models based on their floating point operation efficiency as proposed in arXiv:1907.10597, we examine efficiency with respect to training time, inference time, and total number of model parameters. Our results largely corroborate those of arXiv:1902.00751 for adapter modules, while also demonstrating that gains in F1 score from adding context-aware convolutional filters are not practical due to the increase in training and inference time.
Tasks	Question Answering
Published	2020-02-25
URL	https://arxiv.org/abs/2002.10670v2
PDF	https://arxiv.org/pdf/2002.10670v2.pdf
PWC	https://paperswithcode.com/paper/exploring-bert-parameter-efficiency-on-the
Repo
Framework

Inverse design of multilayer nanoparticles using artificial neural networks and genetic algorithm


Title	Inverse design of multilayer nanoparticles using artificial neural networks and genetic algorithm
Authors	Cankun Qiu, Zhi Luo, Xia Wu, Huidong Yang, Bo Huang
Abstract	The light scattering of multilayer nanoparticles can be solved by Maxwell equations. However, it is difficult to solve the inverse design of multilayer nanoparticles by using the traditional trial-and-error method. Here, we present a method for forward simulation and inverse design of multilayer nanoparticles. We combine the global search ability of genetic algorithm with the local search ability of neural network. First, the genetic algorithm is used to find a suitable solution, and then the neural network is used to fine-tune it. Due to the non-unique relationship between physical structures and optical responses, we first train a forward neural network, and then it is applied to the inverse design of multilayer nanoparticles. Not only here, this method can easily be extended to predict and find the best design parameters for other optical structures.
Tasks
Published	2020-03-16
URL	https://arxiv.org/abs/2003.08356v1
PDF	https://arxiv.org/pdf/2003.08356v1.pdf
PWC	https://paperswithcode.com/paper/inverse-design-of-multilayer-nanoparticles
Repo
Framework

Random Forest Classifier Based Prediction of Rogue waves on Deep Oceans


Title	Random Forest Classifier Based Prediction of Rogue waves on Deep Oceans
Authors	Pujan Pokhrel, Elias Ioup, Md Tamjidul Hoque, Julian Simeonov, Mahdi Abdelguerfi
Abstract	In this paper, we present a novel approach for the prediction of rogue waves in oceans using statistical machine learning methods. Since the ocean is composed of many wave systems, the change from a bimodal or multimodal directional distribution to unimodal one is taken as the warning criteria. Likewise, we explore various features that help in predicting rogue waves. The analysis of the results shows that the Spectral features are significant in predicting rogue waves. We find that nonlinear classifiers have better prediction accuracy than the linear ones. Finally, we propose a Random Forest Classifier based algorithm to predict rogue waves in oceanic conditions. The proposed algorithm has an Overall Accuracy of 89.57% to 91.81%, and the Balanced Accuracy varies between 79.41% to 89.03% depending on the forecast time window. Moreover, due to the model-free nature of the evaluation criteria and interdisciplinary characteristics of the approach, similar studies may be motivated in other nonlinear dispersive media, such as nonlinear optics, plasma, and solids, governed by similar equations, which will allow for the early detection of extreme waves
Tasks
Published	2020-03-13
URL	https://arxiv.org/abs/2003.06431v1
PDF	https://arxiv.org/pdf/2003.06431v1.pdf
PWC	https://paperswithcode.com/paper/random-forest-classifier-based-prediction-of
Repo
Framework

Lipschitz and Comparator-Norm Adaptivity in Online Learning


Title	Lipschitz and Comparator-Norm Adaptivity in Online Learning
Authors	Zakaria Mhammedi, Wouter M. Koolen
Abstract	We study Online Convex Optimization in the unbounded setting where neither predictions nor gradient are constrained. The goal is to simultaneously adapt to both the sequence of gradients and the comparator. We first develop parameter-free and scale-free algorithms for a simplified setting with hints. We present two versions: the first adapts to the squared norms of both comparator and gradients separately using $O(d)$ time per round, the second adapts to their squared inner products (which measure variance only in the comparator direction) in time $O(d^3)$ per round. We then generalize two prior reductions to the unbounded setting; one to not need hints, and a second to deal with the range ratio problem (which already arises in prior work). We discuss their optimality in light of prior and new lower bounds. We apply our methods to obtain sharper regret bounds for scale-invariant online prediction with linear models.
Tasks
Published	2020-02-27
URL	https://arxiv.org/abs/2002.12242v1
PDF	https://arxiv.org/pdf/2002.12242v1.pdf
PWC	https://paperswithcode.com/paper/lipschitz-and-comparator-norm-adaptivity-in
Repo
Framework

Road Network and Travel Time Extraction from Multiple Look Angles with SpaceNet Data


Title	Road Network and Travel Time Extraction from Multiple Look Angles with SpaceNet Data
Authors	Adam Van Etten, Jacob Shermeyer, Daniel Hogan, Nicholas Weir, Ryan Lewis
Abstract	Identification of road networks and optimal routes directly from remote sensing is of critical importance to a broad array of humanitarian and commercial applications. Yet while identification of road pixels has been attempted before, estimation of route travel times from overhead imagery remains a novel problem, particularly for off-nadir overhead imagery. To this end, we extract road networks with travel time estimates from the SpaceNet MVOI dataset. Utilizing the CRESIv2 framework, we demonstrate the ability to extract road networks in various observation angles and quantify performance at 27 unique nadir angles with the graph-theoretic APLS_length and APLS_time metrics. A minimal gap of 0.03 between APLS_length and APLS_time scores indicates that our approach yields speed limits and travel times with very high fidelity. We also explore the utility of incorporating all available angles during model training, and find a peak score of APLS_time = 0.56. The combined model exhibits greatly improved robustness over angle-specific models, despite the very different appearance of road networks at extremely oblique off-nadir angles versus images captured from directly overhead.
Tasks
Published	2020-01-16
URL	https://arxiv.org/abs/2001.05923v1
PDF	https://arxiv.org/pdf/2001.05923v1.pdf
PWC	https://paperswithcode.com/paper/road-network-and-travel-time-extraction-from
Repo
Framework

Rigid-Soft Interactive Learning for Robust Grasping


Title	Rigid-Soft Interactive Learning for Robust Grasping
Authors	Linhan Yang, Fang Wan, Haokun Wang, Xiaobo Liu, Yujia Liu, Jia Pan, Chaoyang Song
Abstract	Inspired by widely used soft fingers on grasping, we propose a method of rigid-soft interactive learning, aiming at reducing the time of data collection. In this paper, we classify the interaction categories into Rigid-Rigid, Rigid-Soft, Soft-Rigid according to the interaction surface between grippers and target objects. We find experimental evidence that the interaction types between grippers and target objects play an essential role in the learning methods. We use soft, stuffed toys for training, instead of everyday objects, to reduce the integration complexity and computational burden and exploit such rigid-soft interaction by changing the gripper fingers to the soft ones when dealing with rigid, daily-life items such as the Yale-CMU-Berkeley (YCB) objects. With a small data collection of 5K picking attempts in total, our results suggest that such Rigid-Soft and Soft-Rigid interactions are transferable. Moreover, the combination of different grasp types shows better performance on the grasping test. We achieve the best grasping performance at 97.5% for easy YCB objects and 81.3% for difficult YCB objects while using a precise grasp with a two-soft-finger gripper to collect training data and power grasp with a four-soft-finger gripper to test.
Tasks
Published	2020-02-29
URL	https://arxiv.org/abs/2003.01584v1
PDF	https://arxiv.org/pdf/2003.01584v1.pdf
PWC	https://paperswithcode.com/paper/rigid-soft-interactive-learning-for-robust
Repo
Framework

Component Analysis for Visual Question Answering Architectures


Title	Component Analysis for Visual Question Answering Architectures
Authors	Camila Kolling, Jônatas Wehrmann, Rodrigo C. Barros
Abstract	Recent research advances in Computer Vision and Natural Language Processing have introduced novel tasks that are paving the way for solving AI-complete problems. One of those tasks is called Visual Question Answering (VQA). A VQA system must take an image and a free-form, open-ended natural language question about the image, and produce a natural language answer as the output. Such a task has drawn great attention from the scientific community, which generated a plethora of approaches that aim to improve the VQA predictive accuracy. Most of them comprise three major components: (i) independent representation learning of images and questions; (ii) feature fusion so the model can use information from both sources to answer visual questions; and (iii) the generation of the correct answer in natural language. With so many approaches being recently introduced, it became unclear the real contribution of each component for the ultimate performance of the model. The main goal of this paper is to provide a comprehensive analysis regarding the impact of each component in VQA models. Our extensive set of experiments cover both visual and textual elements, as well as the combination of these representations in form of fusion and attention mechanisms. Our major contribution is to identify core components for training VQA models so as to maximize their predictive performance.
Tasks	Question Answering, Representation Learning, Visual Question Answering
Published	2020-02-12
URL	https://arxiv.org/abs/2002.05104v2
PDF	https://arxiv.org/pdf/2002.05104v2.pdf
PWC	https://paperswithcode.com/paper/component-analysis-for-visual-question
Repo
Framework

Inter-slice image augmentation based on frame interpolation for boosting medical image segmentation accuracy


Title	Inter-slice image augmentation based on frame interpolation for boosting medical image segmentation accuracy
Authors	Zhaotao Wu, Jia Wei, Wenguang Yuan, Jiabing Wang, Tolga Tasdizen
Abstract	We introduce the idea of inter-slice image augmentation whereby the numbers of the medical images and the corresponding segmentation labels are increased between two consecutive images in order to boost medical image segmentation accuracy. Unlike conventional data augmentation methods in medical imaging, which only increase the number of training samples directly by adding new virtual samples using simple parameterized transformations such as rotation, flipping, scaling, etc., we aim to augment data based on the relationship between two consecutive images, which increases not only the number but also the information of training samples. For this purpose, we propose a frame-interpolation-based data augmentation method to generate intermediate medical images and the corresponding segmentation labels between two consecutive images. We train and test a supervised U-Net liver segmentation network on SLIVER07 and CHAOS2019, respectively, with the augmented training samples, and obtain segmentation scores exhibiting significant improvement compared to the conventional augmentation methods.
Tasks	Data Augmentation, Image Augmentation, Liver Segmentation, Medical Image Segmentation, Semantic Segmentation
Published	2020-01-31
URL	https://arxiv.org/abs/2001.11698v1
PDF	https://arxiv.org/pdf/2001.11698v1.pdf
PWC	https://paperswithcode.com/paper/inter-slice-image-augmentation-based-on-frame
Repo
Framework