This thesis develops a conceptual framework considering social data as representing the surface layer of a hierarchy of human social behaviours, needs and cognition which is employed to transform social data into representations that preserve social behaviours and their causalities. Based on this framework two platforms were built to capture insights from fast-paced and slow-paced social data. For fast-paced, a self-structuring and incremental learning technique was developed to automatically capture salient topics and corresponding dynamics over time. An event detection technique was developed to automatically monitor those identified topic pathways for significant fluctuations in social behaviours using multiple indicators such as volume and sentiment. This platform is demonstrated using two large datasets with over 1 million tweets. The separated topic pathways were representative of the key topics of each entity and coherent against topic coherence measures. Identified events were validated against contemporary events reported in news. Secondly for the slow-paced social data, a suite of new machine learning and natural language processing techniques were developed to automatically capture self-disclosed information of the individuals such as demographics, emotions and timeline of personal events. This platform was trialled on a large text corpus of over 4 million posts collected from online support groups. This was further extended to transform prostate cancer related online support group discussions into a multidimensional representation and investigated the self-disclosed quality of life of patients (and partners) against time, demographics and clinical factors. The capabilities of this extended platform have been demonstrated using a text corpus collected from 10 prostate cancer online support groups comprising of 609,960 prostate cancer discussions and 22,233 patients.

Motivated by models for multiway comparison data, we consider the problem of estimating a coordinate-wise isotonic function on the domain $[0, 1]^d$ from noisy observations collected on a uniform lattice, but where the design points have been permuted along each dimension. While the univariate and bivariate versions of this problem have received significant attention, our focus is on the multivariate case $d \geq 3$. We study both the minimax risk of estimation (in empirical $L_2$ loss) and the fundamental limits of adaptation (quantified by the adaptivity index) to a family of piecewise constant functions. We provide a computationally efficient Mirsky partition estimator that is minimax optimal while also achieving the smallest adaptivity index possible for polynomial time procedures. Thus, from a worst-case perspective and in sharp contrast to the bivariate case, the latent permutations in the model do not introduce significant computational difficulties over and above vanilla isotonic regression. On the other hand, the fundamental limits of adaptation are significantly different with and without unknown permutations: Assuming a hardness conjecture from average-case complexity theory, a statistical-computational gap manifests in the former case. In a complementary direction, we show that natural modifications of existing estimators fail to satisfy at least one of the desiderata of optimal worst-case statistical performance, computational efficiency, and fast adaptation. Along the way to showing our results, we improve adaptation results in the special case $d = 2$ and establish some properties of estimators for vanilla isotonic regression, both of which may be of independent interest.

There has been an increasing necessity for scalable optimization methods, especially due to the explosion in the size of datasets and model complexity in modern machine learning applications. Scalable solvers often distribute the computation over a network of processing units. For simple algorithms such as gradient descent the dependency of the convergence time with the topology of this network is well-known. However, for more involved algorithms such as the Alternating Direction Methods of Multipliers (ADMM) much less is known. At the heart of many distributed optimization algorithms there exists a gossip subroutine which averages local information over the network, and whose efficiency is crucial for the overall performance of the method. In this paper we review recent research in this area and, with the goal of isolating such a communication exchange behaviour, we compare different algorithms when applied to a canonical distributed averaging consensus problem. We also show interesting connections between ADMM and lifted Markov chains besides providing an explicitly characterization of its convergence and optimal parameter tuning in terms of spectral properties of the network. Finally, we empirically study the connection between network topology and convergence rates for different algorithms on a real world problem of sensor localization.

Motivated by the pressing need for suicide prevention through improving behavioral healthcare, we use medical claims data to study the risk of subsequent suicide attempts for patients who were hospitalized due to suicide attempts and later discharged. Understanding the risk behaviors of such patients at elevated suicide risk is an important step towards the goal of "Zero Suicide". An immediate and unconventional challenge is that the identification of suicide attempts from medical claims contains substantial uncertainty: almost 20\% of "suspected" suicide attempts are identified from diagnostic codes indicating external causes of injury and poisoning with undermined intent. It is thus of great interest to learn which of these undetermined events are more likely actual suicide attempts and how to properly utilize them in survival analysis with severe censoring. To tackle these interrelated problems, we develop an integrative Cox cure model with regularization to perform survival regression with uncertain events and a latent cure fraction. We apply the proposed approach to study the risk of subsequent suicide attempt after suicide-related hospitalization for adolescent and young adult population, using medical claims data from Connecticut. The identified risk factors are highly interpretable; more intriguingly, our method distinguishes the risk factors that are most helpful in assessing either susceptibility or timing of subsequent attempt. The predicted statuses of the uncertain attempts are further investigated, leading to several new insights on suicide event identification.

The increased computerization in recent years has resulted in the production of a variety of different software, however measures need to be taken to ensure that the produced software isn't defective. Many researchers have worked in this area and have developed different Machine Learning-based approaches that predict whether the software is defective or not. This issue can't be resolved simply by using different conventional classifiers because the dataset is highly imbalanced i.e the number of defective samples detected is extremely less as compared to the number of non-defective samples. Therefore, to address this issue, certain sophisticated methods are required. The different methods developed by the researchers can be broadly classified into Resampling based methods, Cost-sensitive learning-based methods, and Ensemble Learning. Among these methods. This report analyses the performance of the Online Sequential Extreme Learning Machine (OS-ELM) proposed by Liang et.al. against several classifiers such as Logistic Regression, Support Vector Machine, Random Forest, and Na\"ive Bayes after oversampling the data. OS-ELM trains faster than conventional deep neural networks and it always converges to the globally optimal solution. A comparison is performed on the original dataset as well as the over-sampled data set. The oversampling technique used is Cluster-based Over-Sampling with Noise Filtering. This technique is better than several state-of-the-art techniques for oversampling. The analysis is carried out on 3 projects KC1, PC4 and PC3 carried out by the NASA group. The metrics used for measurement are recall and balanced accuracy. The results are higher for OS-ELM as compared to other classifiers in both scenarios.

The stochastic gradient descent (SGD) method is most widely used for deep neural network (DNN) training. However, the method does not always converge to a flat minimum of the loss surface that can demonstrate high generalization capability. Weight noise injection has been extensively studied for finding flat minima using the SGD method. We devise a new weight-noise injection-based SGD method that adds symmetrical noises to the DNN weights. The training with symmetrical noise evaluates the loss surface at two adjacent points, by which convergence to sharp minima can be avoided. Fixed-magnitude symmetric noises are added to minimize training instability. The proposed method is compared with the conventional SGD method and previous weight-noise injection algorithms using convolutional neural networks for image classification. Particularly, performance improvements in large batch training are demonstrated. This method shows superior performance compared with conventional SGD and weight-noise injection methods regardless of the batch-size and learning rate scheduling algorithms.

Tensor rank learning for canonical polyadic decomposition (CPD) has long been deemed as an essential but challenging problem. In particular, since the tensor rank controls the complexity of the CPD model, its inaccurate learning would cause overfitting to noise or underfitting to the signal sources, and even destroy the interpretability of model parameters. However, the optimal determination of a tensor rank is known to be a non-deterministic polynomial-time hard (NP-hard) task. Rather than exhaustively searching for the best tensor rank via trial-and-error experiments, Bayesian inference under the Gaussian-gamma prior was introduced in the context of probabilistic CPD modeling and it was shown to be an effective strategy for automatic tensor rank determination. This triggered flourishing research on other structured tensor CPDs with automatic tensor rank learning. As the other side of the coin, these research works also reveal that the Gaussian-gamma model does not perform well for high-rank tensors or/and low signal-to-noise ratios (SNRs). To overcome these drawbacks, in this paper, we introduce a more advanced generalized hyperbolic (GH) prior to the probabilistic CPD model, which not only includes the Gaussian-gamma model as a special case, but also provides more flexibilities to adapt to different levels of sparsity. Based on this novel probabilistic model, an algorithm is developed under the framework of variational inference, where each update is obtained in a closed-form. Extensive numerical results, using synthetic data and real-world datasets, demonstrate the excellent performance of the proposed method in learning both low as well as high tensor ranks even for low SNR cases.

Non-stationary bandits and online clustering of bandits lift the restrictive assumptions in contextual bandits and provide solutions to many important real-world scenarios. Though the essence in solving these two problems overlaps considerably, they have been studied independently. In this paper, we connect these two strands of bandit research under the notion of test of homogeneity, which seamlessly addresses change detection for non-stationary bandit and cluster identification for online clustering of bandit in a unified solution framework. Rigorous regret analysis and extensive empirical evaluations demonstrate the value of our proposed solution, especially its flexibility in handling various environment assumptions.

Attributed networks nowadays are ubiquitous in a myriad of high-impact applications, such as social network analysis, financial fraud detection, and drug discovery. As a central analytical task on attributed networks, node classification has received much attention in the research community. In real-world attributed networks, a large portion of node classes only contain limited labeled instances, rendering a long-tail node class distribution. Existing node classification algorithms are unequipped to handle the \textit{few-shot} node classes. As a remedy, few-shot learning has attracted a surge of attention in the research community. Yet, few-shot node classification remains a challenging problem as we need to address the following questions: (i) How to extract meta-knowledge from an attributed network for few-shot node classification? (ii) How to identify the informativeness of each labeled instance for building a robust and effective model? To answer these questions, in this paper, we propose a graph meta-learning framework -- Graph Prototypical Networks (GPN). By constructing a pool of semi-supervised node classification tasks to mimic the real test environment, GPN is able to perform \textit{meta-learning} on an attributed network and derive a highly generalizable model for handling the target classification task. Extensive experiments demonstrate the superior capability of GPN in few-shot node classification.

Machine Learning Tutorial - Expectation-Maximization (EM) Algorithm In Machine Learning, covers the EM algorithm along with the problem of latent variables in maximum likelihood and Gaussian mixture model. You'll learn: What is EM Algorithm In Machine Learning? This Edureka video on'EM Algorithm In Machine Learning' covers the EM algorithm along with the problem of latent variables in maximum likelihood and Gaussian mixture model.