Convolution operations designed for graph-structured data usually utilize the graph Laplacian, which can be seen as message passing between the adjacent neighbors through a generic random walk. In this paper, we propose PAN, a new graph convolution framework that involves every path linking the message sender and receiver with learnable weights depending on the path length, which corresponds to the maximal entropy random walk. PAN generalizes the graph Laplacian to a new transition matrix we call \emph{maximal entropy transition} (MET) matrix derived from a path integral formalism. Most previous graph convolutional network architectures can be adapted to our framework, and many variations and derivatives based on the path integral idea can be developed. Experimental results show that the path integral based graph neural networks have great learnability and fast convergence rate, and achieve state-of-the-art performance on benchmark tasks.
Despite the impressive performance of deep neural networks (DNNs) on numerous vision tasks, they still exhibit yet-to-understand uncouth behaviours. One puzzling behaviour is the subtle sensitive reaction of DNNs to various noise attacks. Such a nuisance has strengthened the line of research around developing and training noise-robust networks. In this work, we propose a new training regularizer that aims to minimize the probabilistic expected training loss of a DNN subject to a generic Gaussian input. We provide an efficient and simple approach to approximate such a regularizer for arbitrary deep networks. This is done by leveraging the analytic expression of the output mean of a shallow neural network; avoiding the need for the memory and computationally expensive data augmentation. We conduct extensive experiments on LeNet and AlexNet on various datasets including MNIST, CIFAR10, and CIFAR100 demonstrating the effectiveness of our proposed regularizer. In particular, we show that networks that are trained with the proposed regularizer benefit from a boost in robustness equivalent to performing 3-21 folds of data augmentation.
Change point detection in time series has attracted substantial interest, but most of the existing results have been focused on detecting change points in the time domain. This paper considers the situation where nonlinear time series have potential change points in the state domain. We apply a density-weighted anti-symmetric kernel function to the state domain and therefore propose a nonparametric procedure to test the existence of change points. When the existence of change points is affirmative, we further introduce an algorithm to estimate their number together with their locations and show the convergence result on the estimation procedure. Numerical simulations and a real data application are given to illustrate our results.
Graph structured data are abundant in the real world. Among different graph types, directed acyclic graphs (DAGs) are of particular interests to machine learning researchers, as many machine learning models are realized as computations on DAGs, including neural networks and Bayesian networks. In this paper, we study deep generative models for DAGs, and propose a novel DAG variational autoencoder (D-VAE). To encode DAGs into the latent space, we leverage graph neural networks. We propose a DAG-style asynchronous message passing scheme that allows encoding the computations defined by DAGs, rather than using existing simultaneous message passing schemes to encode the graph structures. We demonstrate the effectiveness of our proposed D-VAE through two tasks: neural architecture search and Bayesian network structure learning. Experiments show that our model not only generates novel and valid DAGs, but also produces a smooth latent space that facilitates searching for DAGs with better performance through Bayesian optimization.
We present a transductive deep learning-based formulation for the sparse representation-based classification (SRC) method. The proposed network consists of a convolutional autoencoder along with a fully-connected layer. The role of the autoencoder network is to learn robust deep features for classification. On the other hand, the fully-connected layer, which is placed in between the encoder and the decoder networks, is responsible for finding the sparse representation. The estimated sparse codes are then used for classification. Various experiments on three different datasets show that the proposed network leads to sparse representations that give better classification results than state-of-the-art SRC methods. The source code is available at: github.com/mahdiabavisani/DSRC.
Anomaly detection is the process of finding data points that deviate from a baseline. In a real-life setting, anomalies are usually unknown or extremely rare. Moreover, the detection must be accomplished in a timely manner or the risk of corrupting the system might grow exponentially. In this work, we propose a two level framework for detecting anomalies in sequences of discrete elements. First, we assess whether we can obtain enough information from the statistics collected from the discriminator’s layers to discriminate between out of distribution and in distribution samples. We then build an unsupervised anomaly detection module based on these statistics. As to augment the data and keep track of classes of known data, we lean toward a semi-supervised adversarial learning applied to discrete elements.
We study the problem of detecting a common change point in large panel data based on a mean shift model, wherein the errors exhibit both temporal and cross-sectional dependence. A least squares based procedure is used to estimate the location of the change point. Further, we establish the convergence rate and obtain the asymptotic distribution of the least squares estimator. The form of the distribution is determined by the behavior of the norm difference of the means before and after the change point. Since the behavior of this norm difference is, a priori, unknown to the practitioner, we also develop a novel data driven adaptive procedure that provides valid confidence intervals for the common change point, without requiring any such knowledge. Numerical work based on synthetic data illustrates the performance of the estimator in finite samples under different settings of temporal and cross-sectional dependence, sample size and number of panels. Finally, we examine an application to financial stock data and discuss the identified change points.
Gradient Boosting Decision Tree (GBDT) are popular machine learning algorithms with implementations such as LightGBM and in popular machine learning toolkits like Scikit-Learn. Many implementations can only produce trees in an offline manner and in a greedy manner. We explore ways to convert existing GBDT implementations to known neural network architectures with minimal performance loss in order to allow decision splits to be updated in an online manner and provide extensions to allow splits points to be altered as a neural architecture search problem. We provide learning bounds for our neural network.
This paper considers improved forecasting in possibly nonlinear dynamic settings, with high-dimension predictors (‘big data’ environments). To overcome the curse of dimensionality and manage data and model complexity, we examine shrinkage estimation of a back-propagation algorithm of a deep neural net with skip-layer connections. We expressly include both linear and nonlinear components. This is a high-dimensional learning approach including both sparsity L1 and smoothness L2 penalties, allowing high-dimensionality and nonlinearity to be accommodated in one step. This approach selects significant predictors as well as the topology of the neural network. We estimate optimal values of shrinkage hyperparameters by incorporating a gradient-based optimization technique resulting in robust predictions with improved reproducibility. The latter has been an issue in some approaches. This is statistically interpretable and unravels some network structure, commonly left to a black box. An additional advantage is that the nonlinear part tends to get pruned if the underlying process is linear. In an application to forecasting equity returns, the proposed approach captures nonlinear dynamics between equities to enhance forecast performance. It offers an appreciable improvement over current univariate and multivariate models by RMSE and actual portfolio performance.
In this paper, we investigate the research problem of unsupervised multi-view feature selection. Conventional solutions first simply combine multiple pre-constructed view-specific similarity structures into a collaborative similarity structure, and then perform the subsequent feature selection. These two processes are separate and independent. The collaborative similarity structure remains fixed during feature selection. Further, the simple undirected view combination may adversely reduce the reliability of the ultimate similarity structure for feature selection, as the view-specific similarity structures generally involve noises and outlying entries. To alleviate these problems, we propose an adaptive collaborative similarity learning (ACSL) for multi-view feature selection. We propose to dynamically learn the collaborative similarity structure, and further integrate it with the ultimate feature selection into a unified framework. Moreover, a reasonable rank constraint is devised to adaptively learn an ideal collaborative similarity structure with proper similarity combination weights and desirable neighbor assignment, both of which could positively facilitate the feature selection. An effective solution guaranteed with the proved convergence is derived to iteratively tackle the formulated optimization problem. Experiments demonstrate the superiority of the proposed approach.
Graph based clustering is one of the major clustering methods. Most of it work in three separate steps: similarity graph construction, clustering label relaxing and label discretization with k-means. Such common practice has three disadvantages: 1) the predefined similarity graph is often fixed and may not be optimal for the subsequent clustering. 2) the relaxing process of cluster labels may cause significant information loss. 3) label discretization may deviate from the real clustering result since k-means is sensitive to the initialization of cluster centroids. To tackle these problems, in this paper, we propose an effective discrete optimal graph clustering (DOGC) framework. A structured similarity graph that is theoretically optimal for clustering performance is adaptively learned with a guidance of reasonable rank constraint. Besides, to avoid the information loss, we explicitly enforce a discrete transformation on the intermediate continuous label, which derives a tractable optimization problem with discrete solution. Further, to compensate the unreliability of the learned labels and enhance the clustering accuracy, we design an adaptive robust module that learns prediction function for the unseen data based on the learned discrete cluster labels. Finally, an iterative optimization strategy guaranteed with convergence is developed to directly solve the clustering results. Extensive experiments conducted on both real and synthetic datasets demonstrate the superiority of our proposed methods compared with several state-of-the-art clustering approaches.
Anomaly detectors address the difficult problem of detecting automatically exceptions in an arbitrary background image. Detection methods have been proposed by the thousands because each problem requires a different background model. By analyzing the existing approaches, we show that the problem can be reduced to detecting anomalies in residual images (extracted from the target image) in which noise and anomalies prevail. Hence, the general and impossible background modeling problem is replaced by simpler noise modeling, and allows the calculation of rigorous thresholds based on the a contrario detection theory. Our approach is therefore unsupervised and works on arbitrary images.
In multi-task learning (MTL), related tasks learn jointly to improve generalization performance. To exploit the high learning speed of extreme learning machines (ELMs), we apply the ELM framework to the MTL problem, where the output weights of ELMs for all the tasks are learned collaboratively. We first present the ELM based MTL problem in the centralized setting, which is solved by the proposed MTL-ELM (multi-task learning extreme learning machine) algorithm. Due to the fact that many data sets of different tasks are geo-distributed, decentralized machine learning is studied. We formulate the decentralized MTL problem based on ELM as majorized multi-block optimization with coupled bi-convex objective functions. To solve the problem, we propose the DMTL-ELM algorithm, which is a hybrid Jacobian and Gauss-Seidel Proximal multi-block alternating direction method of multipliers (ADMM). Further, to reduce the computation load of DMTL-ELM, DMTL-ELM with first-order approximation (FO-DMTL-ELM) is presented. Theoretical analysis shows that the convergence to the stationary point of DMTL-ELM and FO-DMTL-ELM can be guaranteed conditionally. Through simulations, we demonstrate the convergence of proposed MTL-ELM, DMTL-ELM, and FO-DMTL-ELM algorithms, and also show that they can outperform existing MTL methods. Moreover, by adjusting the dimension of hidden feature space, there exists a trade-off between communication load and learning accuracy for DMTL-ELM.
Generative Adversarial Net (GAN) has been proven to be a powerful machine learning tool in image data analysis and generation. In this paper, we propose to use Conditional Generative Adversarial Net (CGAN) to learn and simulate time series data. The conditions can be both categorical and continuous variables containing different kinds of auxiliary information. Our simulation studies show that CGAN is able to learn different kinds of normal and heavy tail distributions, as well as dependent structures of different time series and it can further generate conditional predictive distributions consistent with the training data distributions. We also provide an in-depth discussion on the rationale of GAN and the neural network as hierarchical splines to draw a clear connection with the existing statistical method for distribution generation. In practice, CGAN has a wide range of applications in the market risk and counterparty risk analysis: it can be applied to learn the historical data and generate scenarios for the calculation of Value-at-Risk (VaR) and Expected Shortfall (ES) and predict the movement of the market risk factors. We present a real data analysis including a backtesting to demonstrate CGAN is able to outperform the Historic Simulation, a popular method in market risk analysis for the calculation of VaR. CGAN can also be applied in the economic time series modeling and forecasting, and an example of hypothetical shock analysis for economic models and the generation of potential CCAR scenarios by CGAN is given at the end of the paper.
Deception plays a key role in adversarial or strategic interactions for the purpose of self-defence and survival. This paper introduces a general framework and solution to address deception. Most existing approaches for deception consider obfuscating crucial information to rational adversaries with abundant memory and computation resources. In this paper, we consider deceiving adversaries with bounded rationality and in terms of expected rewards. This problem is commonly encountered in many applications especially involving human adversaries. Leveraging the cognitive bias of humans in reward evaluation under stochastic outcomes, we introduce a framework to optimally assign resources of a limited quantity to optimally defend against human adversaries. Modeling such cognitive biases follows the so-called prospect theory from behavioral psychology literature. Then we formulate the resource allocation problem as a signomial program to minimize the defender’s cost in an environment modeled as a Markov decision process. We use police patrol hour assignment as an illustrative example and provide detailed simulation results based on real-world data.
We consider the age of information in a multicast network where there is a single source node that sends time-sensitive updates to $n$ receiver nodes. Each status update is one of two kinds: type I or type II. To study the age of information experienced by the receiver nodes for both types of updates, we consider two cases: update streams are generated by the source node at-will and update streams arrive exogenously to the source node. We show that using an earliest $k_1$ and $k_2$ transmission scheme for type I and type II updates, respectively, the age of information of both update streams at the receiver nodes can be made a constant independent of $n$. In particular, the source node transmits each type I update packet to the earliest $k_1$ and each type II update packet to the earliest $k_2$ of $n$ receiver nodes. We determine the optimum $k_1$ and $k_2$ stopping thresholds for arbitrary shifted exponential link delays to individually and jointly minimize the average age of both update streams and characterize the pareto optimal curve for the two ages.