We propose a novel Neyman-Pearson (NP) classifier that is both online and nonlinear as the first time in the literature. The proposed classifier operates on a binary labeled data stream in an online manner, and maximizes the detection power about a user-specified and controllable false positive rate. Our NP classifier is a single hidden layer feedforward neural network (SLFN), which is initialized with random Fourier features (RFFs) to construct the kernel space of the radial basis function at its hidden layer with sinusoidal activation. Not only does this use of RFFs provide an excellent initialization with great nonlinear modeling capability, but it also exponentially reduces the parameter complexity and compactifies the network to mitigate overfitting while improving the processing efficiency substantially. We sequentially learn the SLFN with stochastic gradient descent updates based on a Lagrangian NP objective. As a result, we obtain an expedited online adaptation and powerful nonlinear Neyman-Pearson modeling. Our algorithm is appropriate for large scale data applications and provides a decent false positive rate controllability with real time processing since it only has O(N) computational and O(1) space complexity (N: number of data instances). In our extensive set of experiments on several real datasets, our algorithm is highly superior over the competing state-of-the-art techniques, either by outperforming in terms of the NP classification objective with a comparable computational as well as space complexity or by achieving a comparable performance with significantly lower complexity. Designing a binary classifier with asymmetrical costs for the errors of type I (false positive) and type II (false negative) [1]-[3], or equivalently designing a Neyman-Pearson classifier [4], is required in various applications ranging from facial age estimation [5], multi-view learning [6] and software defect prediction [7] to video surveillance [8] and data imputation [9]. For example, in medical diagnostics, type II error (misdiagnosing as healthy) has perhaps more severe consequences, whereas type I error (misdiagnosing as unhealthy) may result in devastating psychological effects [10].

Response process data collected from human-computer interactive items contain rich information about respondents' behavioral patterns and cognitive processes. Their irregular formats as well as their large sizes make standard statistical tools difficult to apply. This paper develops a computationally efficient method for exploratory analysis of such process data. The new approach segments a lengthy individual process into a sequence of short subprocesses to achieve complexity reduction, easy clustering and meaningful interpretation. Each subprocess is considered a subtask. The segmentation is based on sequential action predictability using a parsimonious predictive model combined with the Shannon entropy. Simulation studies are conducted to assess performance of the new methods. We use the process data from PIAAC 2012 to demonstrate how exploratory analysis of process data can be done with the new approach.

We study the community detection problem on a Gaussian mixture model, in which vertices are divided into $k\geq 2$ distinct communities. The major difference in our model is that the intensities for Gaussian perturbations are different for different entries in the observation matrix, and we do not assume that every community has the same number of vertices. We explicitly find the threshold for the exact recovery of the maximum likelihood estimation. Applications include the community detection on hypergraphs.

Federated learning platforms are gaining popularity. One of the major benefits is to mitigate the privacy risks as the learning of algorithms can be achieved without collecting or sharing data. While federated learning (i.e., many based on stochastic gradient algorithms) has shown great promise, there are still many challenging problems in protecting privacy, especially during the process of gradients update and exchange. This paper presents the first gradient-free federated learning framework called GRAFFL for learning a Bayesian generative model based on approximate Bayesian computation. Unlike conventional federated learning algorithms based on gradients, our framework does not require to disassemble a model (i.e., to linear components) or to perturb data (or encryption of data for aggregation) to preserve privacy. Instead, this framework uses implicit information derived from each participating institution to learn posterior distributions of parameters. The implicit information is summary statistics derived from SuffiAE that is a neural network developed in this study to create compressed and linearly separable representations thereby protecting sensitive information from leakage. As a sufficient dimensionality reduction technique, this is proved to provide sufficient summary statistics. We propose the GRAFFL-based Bayesian Gaussian mixture model to serve as a proof-of-concept of the framework. Using several datasets, we demonstrated the feasibility and usefulness of our model in terms of privacy protection and prediction performance (i.e., close to an ideal setting). The trained model as a quasi-global model can generate informative samples involving information from other institutions and enhances data analysis of each institution.

Advances in transportation systems have resulted in the generation of a large amount of traffic data from various sources [1-3]. In everyday life, GPS sensors installed in smartphones carried by millions of people can collect crowd flow data. Furthermore, taximeters and bus card readers can collect crowd demand data, and vehicle loop detectors can collect traffic flow or speed data. In the mean time, Deep Neural Networks (DNNs) have achieved promising performance improvements in various application areas. They can classify images into thousands of classes [4,5] as well as recognize human speech [6,7], with only small errors.

Hidden Markov chains are widely applied statistical models of stochastic processes, from fundamental physics and chemistry to finance, health, and artificial intelligence. The hidden Markov processes they generate are notoriously complicated, however, even if the chain is finite state: no finite expression for their Shannon entropy rate exists, as the set of their predictive features is generically infinite. As such, to date one cannot make general statements about how random they are nor how structured. Here, we address the first part of this challenge by showing how to efficiently and accurately calculate their entropy rates. We also show how this method gives the minimal set of infinite predictive features. A sequel addresses the challenge's second part on structure.

The p-tensor Ising model is a one-parameter discrete exponential family for modeling dependent binary data, where the sufficient statistic is a multi-linear form of degree p 2. This is a natural generalization of the matrix Ising model, that provides a convenient mathematical framework for capturing, not just pairwise, but higher-order dependencies in complex relational data. In this paper, we consider the problem of estimating the natural parameter of the p-tensor Ising model given a single sample from the distribution on N nodes. Our estimate is based on the maximum pseudo-likelihood (MPL) method, which provides a computationally efficient algorithm for estimating the parameter that avoids computing the intractable partition function. We derive general conditions under which the MPL estimate is N-consistent, that is, it converges to the true parameter at rate 1/ N. Our conditions are robust enough to handle a variety of commonly used tensor Ising models, including spin glass models with random interactions and models where the rate of estimation undergoes a phase transition. In particular, this includes results on N-consistency of the MPL estimate in the well-known p-spin Sherrington-Kirkpatrick (SK) model, spin systems on general p-uniform hypergraphs, and Ising models on the hypergraph stochastic block model (HSBM). In fact, for the HSBM we pin down the exact location of the phase transition threshold, which is determined by the positivity of a certain mean-field variational problem, such that above this threshold the MPL estimate is N-consistent, while below the threshold no estimator is consistent. Finally, we derive the precise fluctuations of the MPL estimate in the special case of the p-tensor Curie-Weiss model, which is the Ising model on the complete p-uniform hypergraph. An interesting consequence of our results is that the MPL estimate in the Curie-Weiss model saturates the Cramer-Rao lower bound at all points above the estimation threshold, that is, the MPL estimate incurs no loss in asymptotic statistical efficiency in the estimability regime, even though it is obtained by minimizing only an approximation of the true likelihood function for computational tractability.

Marketing mix models (MMMs) are statistical models for measuring the effectiveness of various marketing activities such as promotion, media advertisement, etc. In this research, we propose a comprehensive marketing mix model that captures the hierarchical structure and the carryover, shape and scale effects of certain marketing activities, as well as sign restrictions on certain coefficients that are consistent with common business sense. In contrast to commonly adopted approaches in practice, which estimate parameters in a multi-stage process, the proposed approach estimates all the unknown parameters/coefficients simultaneously using a constrained maximum likelihood approach and solved with the Hamiltonian Monte Carlo algorithm. We present results on real datasets to illustrate the use of the proposed solution algorithm.

Markov decision processes (MDPs) are a fundamental mathematical abstraction for sequential decision making under uncertainty and they serve as a basic modeling tool in reinforcement learning (RL) and stochastic control [5, 24, 30]. Two prominent classes of MDPs are average-reward MDPs (AMDPs) and discounted MDPs (DMDPs). Each have been studied extensively; AMDPs are applicable to optimal control, learning automata, and various real-world reinforcement learning settings [17, 3, 22] and DMDPs have a number of nice theoretical properties including reward convergence and operator monotonicity [6]. In this paper we consider the prevalent computational learning problem of finding an approximately optimal policy of an MDP given only restricted access to the model. In particular, we consider the problem of computing an ɛ-optimal policy, i.e. a policy with an additive ɛ error in expected cumulative reward over infinite horizon, under the standard assumption of a generative model [14, 13], which allows one to sample from state-transitions given the current state-action pair. This problem is well-studied and there are multiple known upper and lower bounds on its sample complexity [4, 32, 28, 31]. In this work, we provide a unified framework based on primal-dual stochastic mirror descent (SMD) for learning an ɛ-optimal policies for both AMDPs and DMDPs with a generative model.

The Variational Autoencoder (VAE) is a powerful deep generative model that is now extensively used to represent high-dimensional complex data via a low-dimensional latent space that is learned in an unsupervised manner. In the original VAE model, input data vectors are processed independently. In the recent years, a series of papers have presented different extensions of the VAE to sequential data, that not only model the latent space, but also model the temporal dependencies within a sequence of data vectors and/or corresponding latent vectors, relying on recurrent neural networks or state space models. In this paper we perform an extensive literature review of these models. Importantly, we introduce and discuss a general class of models called Dynamical Variational Autoencoders (DVAEs) that encompass a large subset of these temporal VAE extensions. Then we present in details seven different instances of DVAE that were recently proposed in the literature, with an effort to homogenize the notations and presentation lines, as well as to relate those models with existing classical temporal models (that are also presented for the sake of completeness). We reimplemented those seven DVAE models and we present the results of an experimental benchmark that we conducted on the speech analysis-resynthesis task (the PyTorch code will be made publicly available). An extensive discussion is presented at the end of the paper, aiming to comment on important issues concerning the DVAE class of models and to describe future research guidelines.