Paper Group ANR 147
A Priori Estimates of the Population Risk for Two-layer Neural Networks. Latent Transformations for Object View Points Synthesis. Adversarial Regression for Detecting Attacks in Cyber-Physical Systems. A Brand-level Ranking System with the Customized Attention-GRU Model. Principles of design and software development models of ontological-driven com …
A Priori Estimates of the Population Risk for Two-layer Neural Networks
Title | A Priori Estimates of the Population Risk for Two-layer Neural Networks |
Authors | Weinan E, Chao Ma, Lei Wu |
Abstract | New estimates for the population risk are established for two-layer neural networks. These estimates are nearly optimal in the sense that the error rates scale in the same way as the Monte Carlo error rates. They are equally effective in the over-parametrized regime when the network size is much larger than the size of the dataset. These new estimates are a priori in nature in the sense that the bounds depend only on some norms of the underlying functions to be fitted, not the parameters in the model, in contrast with most existing results which are a posteriori in nature. Using these a priori estimates, we provide a perspective for understanding why two-layer neural networks perform better than the related kernel methods. |
Tasks | |
Published | 2018-10-15 |
URL | https://arxiv.org/abs/1810.06397v3 |
https://arxiv.org/pdf/1810.06397v3.pdf | |
PWC | https://paperswithcode.com/paper/a-priori-estimates-for-two-layer-neural |
Repo | |
Framework | |
Latent Transformations for Object View Points Synthesis
Title | Latent Transformations for Object View Points Synthesis |
Authors | Sangpil Kim, Nick Winovich, Guang Lin, Karthik Ramani |
Abstract | We propose a fully-convolutional conditional generative model, the latent transformation neural network (LTNN), capable of view synthesis using a light-weight neural network suited for real-time applications. In contrast to existing conditional generative models which incorporate conditioning information via concatenation, we introduce a dedicated network component, the conditional transformation unit (CTU), designed to learn the latent space transformations corresponding to specified target views. In addition, a consistency loss term is defined to guide the network toward learning the desired latent space mappings, a task-divided decoder is constructed to refine the quality of generated views, and an adaptive discriminator is introduced to improve the adversarial training process. The generality of the proposed methodology is demonstrated on a collection of three diverse tasks: multi-view reconstruction on real hand depth images, view synthesis of real and synthetic faces, and the rotation of rigid objects. The proposed model is shown to exceed state-of-the-art results in each category while simultaneously achieving a reduction in the computational demand required for inference by 30% on average. |
Tasks | |
Published | 2018-07-12 |
URL | http://arxiv.org/abs/1807.04812v4 |
http://arxiv.org/pdf/1807.04812v4.pdf | |
PWC | https://paperswithcode.com/paper/latent-transformations-for-object-view-points |
Repo | |
Framework | |
Adversarial Regression for Detecting Attacks in Cyber-Physical Systems
Title | Adversarial Regression for Detecting Attacks in Cyber-Physical Systems |
Authors | Amin Ghafouri, Yevgeniy Vorobeychik, Xenofon Koutsoukos |
Abstract | Attacks in cyber-physical systems (CPS) which manipulate sensor readings can cause enormous physical damage if undetected. Detection of attacks on sensors is crucial to mitigate this issue. We study supervised regression as a means to detect anomalous sensor readings, where each sensor’s measurement is predicted as a function of other sensors. We show that several common learning approaches in this context are still vulnerable to \emph{stealthy attacks}, which carefully modify readings of compromised sensors to cause desired damage while remaining undetected. Next, we model the interaction between the CPS defender and attacker as a Stackelberg game in which the defender chooses detection thresholds, while the attacker deploys a stealthy attack in response. We present a heuristic algorithm for finding an approximately optimal threshold for the defender in this game, and show that it increases system resilience to attacks without significantly increasing the false alarm rate. |
Tasks | |
Published | 2018-04-30 |
URL | http://arxiv.org/abs/1804.11022v1 |
http://arxiv.org/pdf/1804.11022v1.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-regression-for-detecting-attacks |
Repo | |
Framework | |
A Brand-level Ranking System with the Customized Attention-GRU Model
Title | A Brand-level Ranking System with the Customized Attention-GRU Model |
Authors | Yu Zhu, Junxiong Zhu, Jie Hou, Yongliang Li, Beidou Wang, Ziyu Guan, Deng Cai |
Abstract | In e-commerce websites like Taobao, brand is playing a more important role in influencing users’ decision of click/purchase, partly because users are now attaching more importance to the quality of products and brand is an indicator of quality. However, existing ranking systems are not specifically designed to satisfy this kind of demand. Some design tricks may partially alleviate this problem, but still cannot provide satisfactory results or may create additional interaction cost. In this paper, we design the first brand-level ranking system to address this problem. The key challenge of this system is how to sufficiently exploit users’ rich behavior in e-commerce websites to rank the brands. In our solution, we firstly conduct the feature engineering specifically tailored for the personalized brand ranking problem and then rank the brands by an adapted Attention-GRU model containing three important modifications. Note that our proposed modifications can also apply to many other machine learning models on various tasks. We conduct a series of experiments to evaluate the effectiveness of our proposed ranking model and test the response to the brand-level ranking system from real users on a large-scale e-commerce platform, i.e. Taobao. |
Tasks | Feature Engineering |
Published | 2018-05-23 |
URL | http://arxiv.org/abs/1805.08958v2 |
http://arxiv.org/pdf/1805.08958v2.pdf | |
PWC | https://paperswithcode.com/paper/a-brand-level-ranking-system-with-the |
Repo | |
Framework | |
Principles of design and software development models of ontological-driven computer systems
Title | Principles of design and software development models of ontological-driven computer systems |
Authors | A. V. Palagin, N. G. Petrenko, V. Yu. Velychko, K. S. Malakhov, O. V. Karun |
Abstract | This paper describes the design principles of methodology of knowledge-oriented information systems based on ontological approach. Such systems implement technology subject-oriented extraction of knowledge from the set of natural language texts and their formal and logical presentation and application processing |
Tasks | |
Published | 2018-02-13 |
URL | http://arxiv.org/abs/1802.06829v1 |
http://arxiv.org/pdf/1802.06829v1.pdf | |
PWC | https://paperswithcode.com/paper/principles-of-design-and-software-development |
Repo | |
Framework | |
Learning from the experts: From expert systems to machine-learned diagnosis models
Title | Learning from the experts: From expert systems to machine-learned diagnosis models |
Authors | Murali Ravuri, Anitha Kannan, Geoffrey J. Tso, Xavier Amatriain |
Abstract | Expert diagnostic support systems have been extensively studied. The practical applications of these systems in real-world scenarios have been somewhat limited due to well-understood shortcomings, such as lack of extensibility. More recently, machine-learned models for medical diagnosis have gained momentum, since they can learn and generalize patterns found in very large datasets like electronic health records. These models also have shortcomings - in particular, there is no easy way to incorporate prior knowledge from existing literature or experts. In this paper, we present a method to merge both approaches by using expert systems as generative models that create simulated data on which models can be learned. We demonstrate that such a learned model not only preserves the original properties of the expert systems but also addresses some of their limitations. Furthermore, we show how this approach can also be used as the starting point to combine expert knowledge with knowledge extracted from other data sources, such as electronic health records. |
Tasks | Medical Diagnosis |
Published | 2018-04-21 |
URL | http://arxiv.org/abs/1804.08033v3 |
http://arxiv.org/pdf/1804.08033v3.pdf | |
PWC | https://paperswithcode.com/paper/learning-from-the-experts-from-expert-systems |
Repo | |
Framework | |
Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information
Title | Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information |
Authors | Yichong Xu, Sivaraman Balakrishnan, Aarti Singh, Artur Dubrawski |
Abstract | In supervised learning, we typically leverage a fully labeled dataset to design methods for function estimation or prediction. In many practical situations, we are able to obtain alternative feedback, possibly at a low cost. A broad goal is to understand the usefulness of, and to design algorithms to exploit, this alternative feedback. In this paper, we consider a semi-supervised regression setting, where we obtain additional ordinal (or comparison) information for the unlabeled samples. We consider ordinal feedback of varying qualities where we have either a perfect ordering of the samples, a noisy ordering of the samples or noisy pairwise comparisons between the samples. We provide a precise quantification of the usefulness of these types of ordinal feedback in both nonparametric and linear regression, showing that in many cases it is possible to accurately estimate an underlying function with a very small labeled set, effectively \emph{escaping the curse of dimensionality}. We also present lower bounds, that establish fundamental limits for the task and show that our algorithms are optimal in a variety of settings. Finally, we present extensive experiments on new datasets that demonstrate the efficacy and practicality of our algorithms and investigate their robustness to various sources of noise and model misspecification. |
Tasks | |
Published | 2018-06-08 |
URL | https://arxiv.org/abs/1806.03286v2 |
https://arxiv.org/pdf/1806.03286v2.pdf | |
PWC | https://paperswithcode.com/paper/nonparametric-regression-with-comparisons |
Repo | |
Framework | |
Domain Adaptation for Reinforcement Learning on the Atari
Title | Domain Adaptation for Reinforcement Learning on the Atari |
Authors | Thomas Carr, Maria Chli, George Vogiatzis |
Abstract | Deep reinforcement learning agents have recently been successful across a variety of discrete and continuous control tasks; however, they can be slow to train and require a large number of interactions with the environment to learn a suitable policy. This is borne out by the fact that a reinforcement learning agent has no prior knowledge of the world, no pre-existing data to depend on and so must devote considerable time to exploration. Transfer learning can alleviate some of the problems by leveraging learning done on some source task to help learning on some target task. Our work presents an algorithm for initialising the hidden feature representation of the target task. We propose a domain adaptation method to transfer state representations and demonstrate transfer across domains, tasks and action spaces. We utilise adversarial domain adaptation ideas combined with an adversarial autoencoder architecture. We align our new policies’ representation space with a pre-trained source policy, taking target task data generated from a random policy. We demonstrate that this initialisation step provides significant improvement when learning a new reinforcement learning task, which highlights the wide applicability of adversarial adaptation methods; even as the task and label/action space also changes. |
Tasks | Continuous Control, Domain Adaptation, Transfer Learning |
Published | 2018-12-18 |
URL | http://arxiv.org/abs/1812.07452v1 |
http://arxiv.org/pdf/1812.07452v1.pdf | |
PWC | https://paperswithcode.com/paper/domain-adaptation-for-reinforcement-learning |
Repo | |
Framework | |
Robust Facial Landmark Localization Based on Texture and Pose Correlated Initialization
Title | Robust Facial Landmark Localization Based on Texture and Pose Correlated Initialization |
Authors | Yiyun Pan, Junwei Zhou, Yongsheng Gao, Shengwu Xiong |
Abstract | Robust facial landmark localization remains a challenging task when faces are partially occluded. Recently, the cascaded pose regression has attracted increasing attentions, due to it’s superior performance in facial landmark localization and occlusion detection. However, such an approach is sensitive to initialization, where an improper initialization can severly degrade the performance. In this paper, we propose a Robust Initialization for Cascaded Pose Regression (RICPR) by providing texture and pose correlated initial shapes for the testing face. By examining the correlation of local binary patterns histograms between the testing face and the training faces, the shapes of the training faces that are most correlated with the testing face are selected as the texture correlated initialization. To make the initialization more robust to various poses, we estimate the rough pose of the testing face according to five fiducial landmarks located by multitask cascaded convolutional networks. Then the pose correlated initial shapes are constructed by the mean face’s shape and the rough testing face pose. Finally, the texture correlated and the pose correlated initial shapes are joined together as the robust initialization. We evaluate RICPR on the challenging dataset of COFW. The experimental results demonstrate that the proposed scheme achieves better performances than the state-of-the-art methods in facial landmark localization and occlusion detection. |
Tasks | Face Alignment |
Published | 2018-05-15 |
URL | http://arxiv.org/abs/1805.05612v1 |
http://arxiv.org/pdf/1805.05612v1.pdf | |
PWC | https://paperswithcode.com/paper/robust-facial-landmark-localization-based-on |
Repo | |
Framework | |
Semi-supervised multi-task learning for lung cancer diagnosis
Title | Semi-supervised multi-task learning for lung cancer diagnosis |
Authors | Naji Khosravan, Ulas Bagci |
Abstract | Early detection of lung nodules is of great importance in lung cancer screening. Existing research recognizes the critical role played by CAD systems in early detection and diagnosis of lung nodules. However, many CAD systems, which are used as cancer detection tools, produce a lot of false positives (FP) and require a further FP reduction step. Furthermore, guidelines for early diagnosis and treatment of lung cancer are consist of different shape and volume measurements of abnormalities. Segmentation is at the heart of our understanding of nodules morphology making it a major area of interest within the field of computer aided diagnosis systems. This study set out to test the hypothesis that joint learning of false positive (FP) nodule reduction and nodule segmentation can improve the computer aided diagnosis (CAD) systems’ performance on both tasks. To support this hypothesis we propose a 3D deep multi-task CNN to tackle these two problems jointly. We tested our system on LUNA16 dataset and achieved an average dice similarity coefficient (DSC) of 91% as segmentation accuracy and a score of nearly 92% for FP reduction. As a proof of our hypothesis, we showed improvements of segmentation and FP reduction tasks over two baselines. Our results support that joint training of these two tasks through a multi-task learning approach improves system performance on both. We also showed that a semi-supervised approach can be used to overcome the limitation of lack of labeled data for the 3D segmentation task. |
Tasks | Lung Cancer Diagnosis, Multi-Task Learning |
Published | 2018-02-17 |
URL | http://arxiv.org/abs/1802.06181v2 |
http://arxiv.org/pdf/1802.06181v2.pdf | |
PWC | https://paperswithcode.com/paper/semi-supervised-multi-task-learning-for-lung |
Repo | |
Framework | |
The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint
Title | The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint |
Authors | Stephen Tu, Benjamin Recht |
Abstract | The effectiveness of model-based versus model-free methods is a long-standing question in reinforcement learning (RL). Motivated by recent empirical success of RL on continuous control tasks, we study the sample complexity of popular model-based and model-free algorithms on the Linear Quadratic Regulator (LQR). We show that for policy evaluation, a simple model-based plugin method requires asymptotically less samples than the classical least-squares temporal difference (LSTD) estimator to reach the same quality of solution; the sample complexity gap between the two methods can be at least a factor of state dimension. For policy evaluation, we study a simple family of problem instances and show that nominal (certainty equivalence principle) control also requires several factors of state and input dimension fewer samples than the policy gradient method to reach the same level of control performance on these instances. Furthermore, the gap persists even when employing commonly used baselines. To the best of our knowledge, this is the first theoretical result which demonstrates a separation in the sample complexity between model-based and model-free methods on a continuous control task. |
Tasks | Continuous Control |
Published | 2018-12-09 |
URL | http://arxiv.org/abs/1812.03565v2 |
http://arxiv.org/pdf/1812.03565v2.pdf | |
PWC | https://paperswithcode.com/paper/the-gap-between-model-based-and-model-free |
Repo | |
Framework | |
Unsupervised Generation of Optical Flow Datasets
Title | Unsupervised Generation of Optical Flow Datasets |
Authors | Hoang-An Le, Tushar Nimbhorkar, Thomas Mensink, Anil S. Baslamisli, Sezer Karaoglu, Theo Gevers |
Abstract | Dense optical flow ground truths of non-rigid motion for real-world images are not available due to the non-intuitive annotation. Aiming at training optical flow deep networks, we present an unsupervised algorithm to generate optical flow ground truth from real-world videos. The algorithm extracts and matches objects of interest from pairs of images in videos to find initial constraints, and applies as-rigid-as-possible deformation over the objects of interest to obtain dense flow fields. The ground truth correctness is enforced by warping the objects in the first frames using the flow fields. We apply the algorithm on the DAVIS dataset to obtain optical flow ground truths for non-rigid movement of real-world objects, using either ground truth or predicted segmentation. We discuss several methods to increase the optical flow variations in the dataset. Extensive experimental results show that training on non-rigid real motion is beneficial compared to training on rigid synthetic data. Moreover, we show that our pipeline generates training data suitable to train successfully FlowNet-S, PWC-Net, and LiteFlowNet deep networks. |
Tasks | Optical Flow Estimation |
Published | 2018-12-05 |
URL | http://arxiv.org/abs/1812.01946v3 |
http://arxiv.org/pdf/1812.01946v3.pdf | |
PWC | https://paperswithcode.com/paper/unsupervised-generation-of-optical-flow |
Repo | |
Framework | |
A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies
Title | A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies |
Authors | Homanga Bharadhwaj, Zihan Wang, Yoshua Bengio, Liam Paull |
Abstract | Learning effective visuomotor policies for robots purely from data is challenging, but also appealing since a learning-based system should not require manual tuning or calibration. In the case of a robot operating in a real environment the training process can be costly, time-consuming, and even dangerous since failures are common at the start of training. For this reason, it is desirable to be able to leverage \textit{simulation} and \textit{off-policy} data to the extent possible to train the robot. In this work, we introduce a robust framework that plans in simulation and transfers well to the real environment. Our model incorporates a gradient-descent based planning module, which, given the initial image and goal image, encodes the images to a lower dimensional latent state and plans a trajectory to reach the goal. The model, consisting of the encoder and planner modules, is trained through a meta-learning strategy in simulation first. We subsequently perform adversarial domain transfer on the encoder by using a bank of unlabelled but random images from the simulation and real environments to enable the encoder to map images from the real and simulated environments to a similarly distributed latent representation. By fine tuning the entire model (encoder + planner) with far fewer real world expert demonstrations, we show successful planning performances in different navigation tasks. |
Tasks | Calibration, Meta-Learning |
Published | 2018-10-11 |
URL | http://arxiv.org/abs/1810.04871v1 |
http://arxiv.org/pdf/1810.04871v1.pdf | |
PWC | https://paperswithcode.com/paper/a-data-efficient-framework-for-training-and |
Repo | |
Framework | |
Efficient transfer learning and online adaptation with latent variable models for continuous control
Title | Efficient transfer learning and online adaptation with latent variable models for continuous control |
Authors | Christian F. Perez, Felipe Petroski Such, Theofanis Karaletsos |
Abstract | Traditional model-based RL relies on hand-specified or learned models of transition dynamics of the environment. These methods are sample efficient and facilitate learning in the real world but fail to generalize to subtle variations in the underlying dynamics, e.g., due to differences in mass, friction, or actuators across robotic agents or across time. We propose using variational inference to learn an explicit latent representation of unknown environment properties that accelerates learning and facilitates generalization on novel environments at test time. We use Online Bayesian Inference of these learned latents to rapidly adapt online to changes in environments without retaining large replay buffers of recent data. Combined with a neural network ensemble that models dynamics and captures uncertainty over dynamics, our approach demonstrates positive transfer during training and online adaptation on the continuous control task HalfCheetah. |
Tasks | Bayesian Inference, Continuous Control, Latent Variable Models, Transfer Learning |
Published | 2018-12-08 |
URL | http://arxiv.org/abs/1812.03399v1 |
http://arxiv.org/pdf/1812.03399v1.pdf | |
PWC | https://paperswithcode.com/paper/efficient-transfer-learning-and-online |
Repo | |
Framework | |
An empirical evaluation of imbalanced data strategies from a practitioner’s point of view
Title | An empirical evaluation of imbalanced data strategies from a practitioner’s point of view |
Authors | Jacques Wainer, Rodrigo A. Franceschinell |
Abstract | This research tested the following well known strategies to deal with binary imbalanced data on 82 different real life data sets (sampled to imbalance rates of 5%, 3%, 1%, and 0.1%): class weight, SMOTE, Underbagging, and a baseline (just the base classifier). As base classifiers we used SVM with RBF kernel, random forests, and gradient boosting machines and we measured the quality of the resulting classifier using 6 different metrics (Area under the curve, Accuracy, F-measure, G-mean, Matthew’s correlation coefficient and Balanced accuracy). The best strategy strongly depends on the metric used to measure the quality of the classifier. For AUC and accuracy class weight and the baseline perform better; for F-measure and MCC, SMOTE performs better; and for G-mean and balanced accuracy, underbagging. |
Tasks | |
Published | 2018-10-16 |
URL | http://arxiv.org/abs/1810.07168v1 |
http://arxiv.org/pdf/1810.07168v1.pdf | |
PWC | https://paperswithcode.com/paper/an-empirical-evaluation-of-imbalanced-data |
Repo | |
Framework | |