Matrix completion is the study of recovering an underlying matrix from a sparse subset of noisy observations. Traditionally, it is assumed that the entries of the matrix are "missing completely at random" (MCAR), i.e., each entry is revealed at random, independent of everything else, with uniform probability. This is likely unrealistic due to the presence of "latent confounders", i.e., unobserved factors that determine both the entries of the underlying matrix and the missingness pattern in the observed matrix. For example, in the context of movie recommender systems -- a canonical application for matrix completion -- a user who vehemently dislikes horror films is unlikely to ever watch horror films. In general, these confounders yield "missing not at random" (MNAR) data, which can severely impact any inference procedure that does not correct for this bias. We develop a formal causal model for matrix completion through the language of potential outcomes, and provide novel identification arguments for a variety of causal estimands of interest. We design a procedure, which we call "synthetic nearest neighbors" (SNN), to estimate these causal estimands. We prove finite-sample consistency and asymptotic normality of our estimator. Our analysis also leads to new theoretical results for the matrix completion literature. In particular, we establish entry-wise, i.e., max-norm, finite-sample consistency and asymptotic normality results for matrix completion with MNAR data. As a special case, this also provides entry-wise bounds for matrix completion with MCAR data. Across simulated and real data, we demonstrate the efficacy of our proposed estimator.

Variational inference for state space models (SSMs) is known to be hard in general. Recent works focus on deriving variational objectives for SSMs from unbiased sequential Monte Carlo estimators. We reveal that the marginal particle filter is obtained from sequential Monte Carlo by applying Rao-Blackwellization operations, which sacrifices the trajectory information for reduced variance and differentiability. We propose the variational marginal particle filter (VMPF), which is a differentiable and reparameterizable variational filtering objective for SSMs based on an unbiased estimator. We find that VMPF with biased gradients gives tighter bounds than previous objectives, and the unbiased reparameterization gradients are sometimes beneficial.

As an important problem of causal inference, we discuss the estimation of treatment effects (TEs) under unobserved confounding. Representing the confounder as a latent variable, we propose Intact-VAE, a new variant of variational autoencoder (VAE), motivated by the prognostic score that is sufficient for identifying TEs. Our VAE also naturally gives representation balanced for treatment groups, using its prior. Experiments on (semi-)synthetic datasets show state-of-the-art performance under diverse settings. Based on the identifiability of our model, further theoretical developments on identification and consistent estimation are also discussed. This paves the way towards principled causal effect estimation by deep neural networks.

Link prediction is a fundamental problem in graph data analysis. While most of the literature focuses on transductive link prediction that requires all the graph nodes and majority of links in training, inductive link prediction, which only uses a proportion of the nodes and their links in training, is a more challenging problem in various real-world applications. In this paper, we propose a meta-learning approach with graph neural networks for link prediction: Neural Processes for Graph Neural Networks (NPGNN), which can perform both transductive and inductive learning tasks and adapt to patterns in a large new graph after training with a small subgraph. Experiments on real-world graphs are conducted to validate our model, where the results suggest that the proposed method achieves stronger performance compared to other state-of-the-art models, and meanwhile generalizes well when training on a small subgraph.

Many machine learning tasks that involve predicting an output response can be solved by training a weighted regression model. Unfortunately, the predictive power of this type of models may severely deteriorate under low sample sizes or under covariate perturbations. Reweighting the training samples has aroused as an effective mitigation strategy to these problems. In this paper, we propose a novel and coherent scheme for kernel-reweighted regression by reparametrizing the sample weights using a doubly non-negative matrix. When the weighting matrix is confined in an uncertainty set using either the log-determinant divergence or the Bures-Wasserstein distance, we show that the adversarially reweighted estimate can be solved efficiently using first-order methods. Numerical experiments show that our reweighting strategy delivers promising results on numerous datasets.

It is of importance to develop statistical techniques to analyze high-dimensional data in the presence of both complex dependence and possible outliers in real-world applications such as imaging data analyses. We propose a new robust high-dimensional regression with coefficient thresholding, in which an efficient nonconvex estimation procedure is proposed through a thresholding function and the robust Huber loss. The proposed regularization method accounts for complex dependence structures in predictors and is robust against outliers in outcomes. Theoretically, we analyze rigorously the landscape of the population and empirical risk functions for the proposed method. The fine landscape enables us to establish both {statistical consistency and computational convergence} under the high-dimensional setting. The finite-sample properties of the proposed method are examined by extensive simulation studies. An illustration of real-world application concerns a scalar-on-image regression analysis for an association of psychiatric disorder measured by the general factor of psychopathology with features extracted from the task functional magnetic resonance imaging data in the Adolescent Brain Cognitive Development study.

The industry as a whole is beginning to realize the intimate connection between Artificial Intelligence and its less heralded, yet equally viable, knowledge foundation. The increasing prominence of knowledge graphs in almost any form of analytics--from conventional Business Intelligence solutions to data science tools--suggests this fact, as does the growing interest in Neuro-Symbolic AI. In most of these use cases, graphs are the framework for intelligently reasoning about business concepts with a comprehension exceeding that of mere machine learning. However, what many organizations still don't realize is there's an equally vital movement gaining traction around AI's knowledge base that drastically improves its statistical learning prowess, making the latter far more effectual. In these applications graphs aren't simply providing an alternative form of AI to machine learning that naturally complements it.

While being part of a team working on designing and developing a lead scoring system prototype, I faced the challenge of integrating machine learning models into the target environment built around the Microsoft .NET ecosystem. Technically, I implemented the lead scoring predictive model using the Scikit-learn machine learning built-in algorithm for regression, more precisely Logistic Regression. Considering the phases of initial data analysis, data preprocessing, exploratory data analysis (EDA), and the data preparation for the model building itself, I used the Jupyter Notebook environment powered by Anaconda distribution for Python scientific computing. Previously, I have investigated and touched Python within Flask as a micro web framework written in this programming language. However, I aimed to integrate or deploy the machine learning model written in Python into the .NET ecosystem, using the C# programming language and Visual Studio IDE.

In the era of Big Data, businesses are faced with a deluge of time series data. This data is not just available in high volumes, but is also highly nuanced. Amazon Forecast Deep Learning algorithms such as DeepAR and CNN-QR build representations that effectively capture common trends and patterns across these numerous time series. These algorithms produce forecasts that perform better than traditional forecasting methods. In some cases, it may be possible to further improve Amazon Forecast accuracy by training the models with similarly behaving subsets of the time series dataset.

Machine Learning is a new buzzword that is a subpart of Artificial Intelligence. Everyone seems to be wanting to go into this field. But mostly are thinking of how to start and where to proceed. This article has got you covered. Machine Learning enables systems to learn and enhance the experience without begging explicitly programmed.