Paper Group ANR 1027
On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems. Probabilistic Modeling for Novelty Detection with Applications to Fraud Identification. Empirical effect of graph embeddings on fraud detection/ risk mitigation. A Bootstrap-based Inference Framework for Testing Similarity of Paired Networks. Deep Learning-based Radiomic Features fo …
On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems
| Title | On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems |
| Authors | Tianyi Lin, Chi Jin, Michael I. Jordan |
| Abstract | We consider nonconvex-concave minimax problems, $\min_{\mathbf{x}} \max_{\mathbf{y} \in \mathcal{Y}} f(\mathbf{x}, \mathbf{y})$, where $f$ is nonconvex in $\mathbf{x}$ but concave in $\mathbf{y}$ and $\mathcal{Y}$ is a convex and bounded set. One of the most popular algorithms for solving this problem is the celebrated gradient descent ascent (GDA) algorithm, which has been widely used in machine learning, control theory and economics. Despite the extensive convergence results for the convex-concave setting, GDA with equal stepsize can converge to limit cycles or even diverge in a general setting. In this paper, we present the complexity results on two-time-scale GDA for solving nonconvex-concave minimax problems, showing that the algorithm can find a stationary point of the function $\Phi(\cdot) := \max_{\mathbf{y} \in \mathcal{Y}} f(\cdot, \mathbf{y})$ efficiently. To the best our knowledge, this is the first nonasymptotic analysis for two-time-scale GDA in this setting, shedding light on its superior practical performance in training generative adversarial networks (GANs) and other real applications. |
| Tasks | |
| Published | 2019-06-02 |
| URL | https://arxiv.org/abs/1906.00331v4 |
| https://arxiv.org/pdf/1906.00331v4.pdf | |
| PWC | https://paperswithcode.com/paper/190600331 |
| Repo | |
| Framework | |
Probabilistic Modeling for Novelty Detection with Applications to Fraud Identification
| Title | Probabilistic Modeling for Novelty Detection with Applications to Fraud Identification |
| Authors | Rémi Domingues |
| Abstract | Novelty detection is the unsupervised problem of identifying anomalies in test data which significantly differ from the training set. Novelty detection is one of the classic challenges in Machine Learning and a core component of several research areas such as fraud detection, intrusion detection, medical diagnosis, data cleaning, and fault prevention. While numerous algorithms were designed to address this problem, most methods are only suitable to model continuous numerical data. Tackling datasets composed of mixed-type features, such as numerical and categorical data, or temporal datasets describing discrete event sequences is a challenging task. In addition to the supported data types, the key criteria for efficient novelty detection methods are the ability to accurately dissociate novelties from nominal samples, the interpretability, the scalability and the robustness to anomalies located in the training data. In this thesis, we investigate novel ways to tackle these issues. In particular, we propose (i) an experimental comparison of novelty detection methods for mixed-type data (ii) an experimental comparison of novelty detection methods for sequence data, (iii) a probabilistic nonparametric novelty detection method for mixed-type data based on Dirichlet process mixtures and exponential-family distributions and (iv) an autoencoder-based novelty detection model with encoder/decoder modelled as deep Gaussian processes. |
| Tasks | Fraud Detection, Gaussian Processes, Intrusion Detection, Medical Diagnosis |
| Published | 2019-03-05 |
| URL | http://arxiv.org/abs/1903.01730v1 |
| http://arxiv.org/pdf/1903.01730v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-modeling-for-novelty-detection |
| Repo | |
| Framework | |
Empirical effect of graph embeddings on fraud detection/ risk mitigation
| Title | Empirical effect of graph embeddings on fraud detection/ risk mitigation |
| Authors | Sida Zhou |
| Abstract | Graph embedding technics are studied with interest on public datasets, such as BlogCatalog, with the common practice of maximizing scoring on graph reconstruction, link prediction metrics etc. However, in the financial sector the important metrics are often more business related, for example fraud detection rates. With our privileged position of having large amount of real-world non-public P2P-lending social data, we aim to study empirically whether recent advances in graph embedding technics provide a useful signal for metrics more closely related to business interests, such as fraud detection rate. |
| Tasks | Fraud Detection, Graph Embedding, Link Prediction |
| Published | 2019-03-05 |
| URL | http://arxiv.org/abs/1903.05976v1 |
| http://arxiv.org/pdf/1903.05976v1.pdf | |
| PWC | https://paperswithcode.com/paper/empirical-effect-of-graph-embeddings-on-fraud |
| Repo | |
| Framework | |
A Bootstrap-based Inference Framework for Testing Similarity of Paired Networks
| Title | A Bootstrap-based Inference Framework for Testing Similarity of Paired Networks |
| Authors | Somnath Bhadra, Kaustav Chakraborty, Srijan Sengupta, Soumendra Lahiri |
| Abstract | We live in an interconnected world where network valued data arises in many domains, and, fittingly, statistical network analysis has emerged as an active area in the literature. However, the topic of inference in networks has received relatively less attention. In this work, we consider the paired network inference problem where one is given two networks on the same set of nodes, and the goal is to test whether the given networks are stochastically similar in terms of some notion of similarity. We develop a general inferential framework based on parametric bootstrap to address this problem. Under this setting, we address two specific and important problems: the equality problem, i.e., whether the two networks are generated from the same random graph model, and the scaling problem, i.e., whether the underlying probability matrices of the two random graph models are scaled versions of each other. |
| Tasks | |
| Published | 2019-11-15 |
| URL | https://arxiv.org/abs/1911.06869v2 |
| https://arxiv.org/pdf/1911.06869v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-bootstrap-based-inference-framework-for |
| Repo | |
| Framework | |
Deep Learning-based Radiomic Features for Improving Neoadjuvant Chemoradiation Response Prediction in Locally Advanced Rectal Cancer
| Title | Deep Learning-based Radiomic Features for Improving Neoadjuvant Chemoradiation Response Prediction in Locally Advanced Rectal Cancer |
| Authors | Jie Fu, Xinran Zhong, Ning Li, Ritchell Van Dams, John Lewis, Kyunghyun Sung, Ann C. Raldow, Jing Jin, X. Sharon Qi |
| Abstract | Radiomic features achieve promising results in cancer diagnosis, treatment response prediction, and survival prediction. Our goal is to compare the handcrafted (explicitly designed) and deep learning (DL)-based radiomic features extracted from pre-treatment diffusion-weighted magnetic resonance images (DWIs) for predicting neoadjuvant chemoradiation treatment (nCRT) response in patients with locally advanced rectal cancer (LARC). 43 patients receiving nCRT were included. All patients underwent DWIs before nCRT and total mesorectal excision surgery 6-12 weeks after completion of nCRT. Gross tumor volume (GTV) contours were drawn by an experienced radiation oncologist on DWIs. The patient-cohort was split into the responder group (n=22) and the non-responder group (n=21) based on the post-nCRT response assessed by postoperative pathology, MRI or colonoscopy. Handcrafted and DL-based features were extracted from the apparent diffusion coefficient (ADC) map of the DWI using conventional computer-aided diagnosis methods and a pre-trained convolution neural network, respectively. Least absolute shrinkage and selection operator (LASSO)-logistic regression models were constructed using extracted features for predicting treatment response. The model performance was evaluated with repeated 20 times stratified 4-fold cross-validation using receiver operating characteristic (ROC) curves and compared using the corrected resampled t-test. The model built with handcrafted features achieved the mean area under the ROC curve (AUC) of 0.64, while the one built with DL-based features yielded the mean AUC of 0.73. The corrected resampled t-test on AUC showed P-value < 0.05. DL-based features extracted from pre-treatment DWIs achieved significantly better classification performance compared with handcrafted features for predicting nCRT response in patients with LARC. |
| Tasks | |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.04012v1 |
| https://arxiv.org/pdf/1909.04012v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-based-radiomic-features-for |
| Repo | |
| Framework | |
Training the Convolutional Neural Network with Statistical Dependence of the Response on the Input Data Distortion
| Title | Training the Convolutional Neural Network with Statistical Dependence of the Response on the Input Data Distortion |
| Authors | Igor Janiszewski, Dmitry Slugin, Vladimir V. Arlazarov |
| Abstract | The paper proposes an approach to training a convolutional neural network using information on the level of distortion of input data. The learning process is modified with an additional layer, which is subsequently deleted, so the architecture of the original network does not change. As an example, the LeNet5 architecture network with training data based on the MNIST symbols and a distortion model as Gaussian blur with a variable level of distortion is considered. This approach does not have quality loss of the network and has a significant error-free zone in responses on the test data which is absent in the traditional approach to training. The responses are statistically dependent on the level of input image’s distortions and there is a presence of a strong relationship between them. |
| Tasks | |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00664v1 |
| https://arxiv.org/pdf/1912.00664v1.pdf | |
| PWC | https://paperswithcode.com/paper/training-the-convolutional-neural-network |
| Repo | |
| Framework | |
A Survey of Deep Reinforcement Learning in Video Games
| Title | A Survey of Deep Reinforcement Learning in Video Games |
| Authors | Kun Shao, Zhentao Tang, Yuanheng Zhu, Nannan Li, Dongbin Zhao |
| Abstract | Deep reinforcement learning (DRL) has made great achievements since proposed. Generally, DRL agents receive high-dimensional inputs at each step, and make actions according to deep-neural-network-based policies. This learning mechanism updates the policy to maximize the return with an end-to-end method. In this paper, we survey the progress of DRL methods, including value-based, policy gradient, and model-based algorithms, and compare their main techniques and properties. Besides, DRL plays an important role in game artificial intelligence (AI). We also take a review of the achievements of DRL in various video games, including classical Arcade games, first-person perspective games and multi-agent real-time strategy games, from 2D to 3D, and from single-agent to multi-agent. A large number of video game AIs with DRL have achieved super-human performance, while there are still some challenges in this domain. Therefore, we also discuss some key points when applying DRL methods to this field, including exploration-exploitation, sample efficiency, generalization and transfer, multi-agent learning, imperfect information, and delayed spare rewards, as well as some research directions. |
| Tasks | Real-Time Strategy Games |
| Published | 2019-12-23 |
| URL | https://arxiv.org/abs/1912.10944v2 |
| https://arxiv.org/pdf/1912.10944v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-of-deep-reinforcement-learning-in |
| Repo | |
| Framework | |
Multimodal Volume-Aware Detection and Segmentation for Brain Metastases Radiosurgery
| Title | Multimodal Volume-Aware Detection and Segmentation for Brain Metastases Radiosurgery |
| Authors | Szu-Yeu Hu, Wei-Hung Weng, Shao-Lun Lu, Yueh-Hung Cheng, Furen Xiao, Feng-Ming Hsu, Jen-Tang Lu |
| Abstract | Stereotactic radiosurgery (SRS), which delivers high doses of irradiation in a single or few shots to small targets, has been a standard of care for brain metastases. While very effective, SRS currently requires manually intensive delineation of tumors. In this work, we present a deep learning approach for automated detection and segmentation of brain metastases using multimodal imaging and ensemble neural networks. In order to address small and multiple brain metastases, we further propose a volume-aware Dice loss which optimizes model performance using the information of lesion size. This work surpasses current benchmark levels and demonstrates a reliable AI-assisted system for SRS treatment planning for multiple brain metastases. |
| Tasks | |
| Published | 2019-08-15 |
| URL | https://arxiv.org/abs/1908.05418v1 |
| https://arxiv.org/pdf/1908.05418v1.pdf | |
| PWC | https://paperswithcode.com/paper/multimodal-volume-aware-detection-and |
| Repo | |
| Framework | |
A resnet-based universal method for speckle reduction in optical coherence tomography images
| Title | A resnet-based universal method for speckle reduction in optical coherence tomography images |
| Authors | Cai Ning, Shi Fei, Hu Dianlin, Chen Yang |
| Abstract | In this work we propose a ResNet-based universal method for speckle reduction in optical coherence tomography (OCT) images. The proposed model contains 3 main modules: Convolution-BN-ReLU, Branch and Residual module. Unlike traditional algorithms, the model can learn from training data instead of selecting parameters manually such as noise level. Application of this proposed method to the OCT images shows a more than 22 dB signal-to-noise ratio improvement in speckle noise reduction with minimal structure blurring. The proposed method provides strong generalization ability and can process noisy other types of OCT images without retraining. It outperforms other filtering methods in suppressing speckle noises and revealing subtle features. |
| Tasks | |
| Published | 2019-03-22 |
| URL | http://arxiv.org/abs/1903.09330v1 |
| http://arxiv.org/pdf/1903.09330v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-resnet-based-universal-method-for-speckle |
| Repo | |
| Framework | |
A dual Newton based preconditioned proximal point algorithm for exclusive lasso models
| Title | A dual Newton based preconditioned proximal point algorithm for exclusive lasso models |
| Authors | Meixia Lin, Defeng Sun, Kim-Chuan Toh, Yancheng Yuan |
| Abstract | The exclusive lasso (also known as elitist lasso) regularization has become popular recently due to its superior performance on group sparsity. Compared to the group lasso regularization which enforces the competition on variables among different groups, the exclusive lasso regularization also enforces the competition within each group. In this paper, we propose a highly efficient dual Newton based preconditioned proximal point algorithm (PPDNA) to solve machine learning models involving the exclusive lasso regularizer. As an important ingredient, we provide a rigorous proof for deriving the closed-form solution to the proximal mapping of the weighted exclusive lasso regularizer. In addition, we derive the corresponding HS-Jacobian to the proximal mapping and analyze its structure — which plays an essential role in the efficient computation of the PPA subproblem via applying a semismooth Newton method on its dual. Various numerical experiments in this paper demonstrate the superior performance of the proposed PPDNA against other state-of-the-art numerical algorithms. |
| Tasks | |
| Published | 2019-02-01 |
| URL | https://arxiv.org/abs/1902.00151v2 |
| https://arxiv.org/pdf/1902.00151v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-closed-form-proximal-mapping-and |
| Repo | |
| Framework | |
Anatomy-Aware Self-supervised Fetal MRI Synthesis from Unpaired Ultrasound Images
| Title | Anatomy-Aware Self-supervised Fetal MRI Synthesis from Unpaired Ultrasound Images |
| Authors | Jianbo Jiao, Ana I. L. Namburete, Aris T. Papageorghiou, J. Alison Noble |
| Abstract | Fetal brain magnetic resonance imaging (MRI) offers exquisite images of the developing brain but is not suitable for anomaly screening. For this ultrasound (US) is employed. While expert sonographers are adept at reading US images, MR images are much easier for non-experts to interpret. Hence in this paper we seek to produce images with MRI-like appearance directly from clinical US images. Our own clinical motivation is to seek a way to communicate US findings to patients or clinical professionals unfamiliar with US, but in medical image analysis such a capability is potentially useful, for instance, for US-MRI registration or fusion. Our model is self-supervised and end-to-end trainable. Specifically, based on an assumption that the US and MRI data share a similar anatomical latent space, we first utilise an extractor to determine shared latent features, which are then used for data synthesis. Since paired data was unavailable for our study (and rare in practice), we propose to enforce the distributions to be similar instead of employing pixel-wise constraints, by adversarial learning in both the image domain and latent space. Furthermore, we propose an adversarial structural constraint to regularise the anatomical structures between the two modalities during the synthesis. A cross-modal attention scheme is proposed to leverage non-local spatial correlations. The feasibility of the approach to produce realistic looking MR images is demonstrated quantitatively and with a qualitative evaluation compared to real fetal MR images. |
| Tasks | |
| Published | 2019-09-08 |
| URL | https://arxiv.org/abs/1909.03483v1 |
| https://arxiv.org/pdf/1909.03483v1.pdf | |
| PWC | https://paperswithcode.com/paper/anatomy-aware-self-supervised-fetal-mri |
| Repo | |
| Framework | |
Online Non-Monotone DR-submodular Maximization
| Title | Online Non-Monotone DR-submodular Maximization |
| Authors | Nguyen Kim Thang, Abhinav Srivastav |
| Abstract | In this paper, we study problems at the interface of two important fields: \emph{submodular optimization} and \emph{online learning}. Submodular functions play a vital role in modelling cost functions that naturally arise in many areas of discrete optimization. These functions have been studied under various models of computation. Independently, submodularity has been considered in continuous domains. In fact, many problems arising in machine learning and statistics have been modelled using continuous DR-submodular functions. In this work, we are study the problem of maximizing \textit{non-monotone} continuous DR-submodular functions within the framework of online learning. We provide three main results. First, we present an online algorithm (in full-information setting) that achieves an approximation guarantee (depending on the search space) for the problem of maximizing non-monotone continuous DR-submodular functions over a \emph{general} convex domain. To best of our knowledge, no prior approximation algorithm in full-information setting was known for the non-monotone continuous DR submodular functions even for the \emph{down-closed} convex domain. Second, we show that the online stochastic mirror ascent algorithm (in full information setting) achieves an improved approximation ratio of $(1/4)$ for maximizing the non-monotone continuous DR-submodular functions over a \emph{down-closed} convex domain. At last, we extend our second result to the bandit setting where we present the first approximation guarantee of $(1/4)$. To best of our knowledge, no approximation algorithm for non-monotone submodular maximization was known in the bandit setting. |
| Tasks | |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11426v1 |
| https://arxiv.org/pdf/1909.11426v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-non-monotone-dr-submodular |
| Repo | |
| Framework | |
A Local Approach to Forward Model Learning: Results on the Game of Life Game
| Title | A Local Approach to Forward Model Learning: Results on the Game of Life Game |
| Authors | Simon M. Lucas, Alexander Dockhorn, Vanessa Volz, Chris Bamford, Raluca D. Gaina, Ivan Bravi, Diego Perez-Liebana, Sanaz Mostaghim, Rudolf Kruse |
| Abstract | This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent. We transform Conway’s Game of Life simulation into a single-player game where the objective can be either to preserve as much life as possible or to extinguish all life as quickly as possible. In order to learn the forward model of the game, we formulate the problem in a novel way that learns the local cell transition function by creating a set of supervised training data and predicting the next state of each cell in the grid based on its current state and immediate neighbours. Using this method we are able to harvest sufficient data to learn perfect forward models by observing only a few complete state transitions, using either a look-up table, a decision tree or a neural network. In contrast, learning the complete state transition function is a much harder task and our initial efforts to do this using deep convolutional auto-encoders were less successful. We also investigate the effects of imperfect learned models on prediction errors and game-playing performance, and show that even models with significant errors can provide good performance. |
| Tasks | |
| Published | 2019-03-29 |
| URL | http://arxiv.org/abs/1903.12508v1 |
| http://arxiv.org/pdf/1903.12508v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-local-approach-to-forward-model-learning |
| Repo | |
| Framework | |
Determining input variable ranges in Industry 4.0: A heuristic for estimating the domain of a real-valued function or trained regression model given an output range
| Title | Determining input variable ranges in Industry 4.0: A heuristic for estimating the domain of a real-valued function or trained regression model given an output range |
| Authors | Noelia Oses, Aritz Legarretaetxebarria, Marco Quartulli, Igor García, Mikel Serrano |
| Abstract | Industrial process control systems try to keep an output variable within a given tolerance around a target value. PID control systems have been widely used in industry to control input variables in order to reach this goal. However, this kind of Transfer Function based approach cannot be extended to complex processes where input data might be non-numeric, high dimensional, sparse, etc. In such cases, there is still a need for determining the subspace of input data that produces an output within a given range. This paper presents a non-stochastic heuristic to determine input values for a mathematical function or trained regression model given an output range. The proposed method creates a synthetic training data set of input combinations with a class label that indicates whether the output is within the given target range or not. Then, a decision tree classifier is used to determine the subspace of input data of interest. This method is more general than a traditional controller as the target range for the output does not have to be centered around a reference value and it can be applied given a regression model of the output variable, which may have categorical variables as inputs and may be high dimensional, sparse… The proposed heuristic is validated with a proof of concept on a real use case where the quality of a lamination factory is established to identify the suitable subspace of production variable values. |
| Tasks | |
| Published | 2019-04-03 |
| URL | http://arxiv.org/abs/1904.02655v1 |
| http://arxiv.org/pdf/1904.02655v1.pdf | |
| PWC | https://paperswithcode.com/paper/determining-input-variable-ranges-in-industry |
| Repo | |
| Framework | |
On the Sample Complexity of Actor-Critic Method for Reinforcement Learning with Function Approximation
| Title | On the Sample Complexity of Actor-Critic Method for Reinforcement Learning with Function Approximation |
| Authors | Harshat Kumar, Alec Koppel, Alejandro Ribeiro |
| Abstract | Reinforcement learning, mathematically described by Markov Decision Problems, may be approached either through dynamic programming or policy search. Actor-critic algorithms combine the merits of both approaches by alternating between steps to estimate the value function and policy gradient updates. Due to the fact that the updates exhibit correlated noise and biased gradient updates, only the asymptotic behavior of actor-critic is known by connecting its behavior to dynamical systems. This work puts forth a new variant of actor-critic that employs Monte Carlo rollouts during the policy search updates, which results in controllable bias that depends on the number of critic evaluations. As a result, we are able to provide for the first time the convergence rate of actor-critic algorithms when the policy search step employs policy gradient, agnostic to the choice of policy evaluation technique. In particular, we establish conditions under which the sample complexity is comparable to stochastic gradient method for non-convex problems or slower as a result of the critic estimation error, which is the main complexity bottleneck. These results hold for in continuous state and action spaces with linear function approximation for the value function. We then specialize these conceptual results to the case where the critic is estimated by Temporal Difference, Gradient Temporal Difference, and Accelerated Gradient Temporal Difference. These learning rates are then corroborated on a navigation problem involving an obstacle, which suggests that learning more slowly may lead to improved limit points, providing insight into the interplay between optimization and generalization in reinforcement learning. |
| Tasks | |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08412v1 |
| https://arxiv.org/pdf/1910.08412v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-sample-complexity-of-actor-critic |
| Repo | |
| Framework | |
