Gaussian graphical models [27] are a popular approach to describing networks, and are directly related to variable prediction via linear regression [20]. The focus is often on graphical model edges described by partial correlations which are zero, identifying pairs of nodes which are conditionally independent [2]. For example, the graphical LASSO [10] imposes a sparse regularization penalty on the precision matrix estimate, seeking a network which trades off predictive accuracy for sparsity. This provides a network which more interpretable and efficient to use, however it is not clear that sparse solutions actually generalize better to new data than dense solutions do [28]. Meanwhile, a different research direction is based on forming edges via some simple relationship such as affinity or univariate correlation. This limited network is used as a starting point for computing sophisticated dense estimates of relatedness between nodes, providing a deeper analysis of network structure. In such research, sparsity is usually imposed on the simple network, however the subsequent analysis is often based on methods which inherently presume Gaussian statistics and l penalties in some sense.

Cancer analysis and prediction is the utmost important research field for well-being of humankind. The Cancer data are analyzed and predicted using machine learning algorithms. Most of the researcher claims the accuracy of the predicted results within 99%. However, we show that machine learning algorithms can easily predict with an accuracy of 100% on Wisconsin Diagnostic Breast Cancer dataset. We show that the method of gaining accuracy is an unethical approach that we can easily mislead the algorithms. In this paper, we exploit the weakness of Machine Learning algorithms. We perform extensive experiments for the correctness of our results to exploit the weakness of machine learning algorithms. The methods are rigorously evaluated to validate our claim. In addition, this paper focuses on correctness of accuracy. This paper report three key outcomes of the experiments, namely, correctness of accuracies, significance of minimum accuracy, and correctness of machine learning algorithms.

High-dimensional data in many machine learning applications leads to computational and analytical complexities. Feature selection provides an effective way for solving these problems by removing irrelevant and redundant features, thus reducing model complexity and improving accuracy and generalization capability of the model. In this paper, we present a novel teacher-student feature selection (TSFS) method in which a 'teacher' (a deep neural network or a complicated dimension reduction method) is first employed to learn the best representation of data in low dimension. Then a 'student' network (a simple neural network) is used to perform feature selection by minimizing the reconstruction error of low dimensional representation. Although the teacher-student scheme is not new, to the best of our knowledge, it is the first time that this scheme is employed for feature selection. The proposed TSFS can be used for both supervised and unsupervised feature selection. This method is evaluated on different datasets and is compared with state-of-the-art existing feature selection methods. The results show that TSFS performs better in terms of classification and clustering accuracies and reconstruction error. Moreover, experimental evaluations demonstrate a low degree of sensitivity to parameter selection in the proposed method.

In distributed statistical learning, $N$ samples are split across $m$ machines and a learner wishes to use minimal communication to learn as well as if the examples were on a single machine. This model has received substantial interest in machine learning due to its scalability and potential for parallel speedup. However, in high-dimensional settings, where the number examples is smaller than the number of features ("dimension"), the speedup afforded by distributed learning may be overshadowed by the cost of communicating a single example. This paper investigates the following question: When is it possible to learn a $d$-dimensional model in the distributed setting with total communication sublinear in $d$? Starting with a negative result, we show that for learning $\ell_1$-bounded or sparse linear models, no algorithm can obtain optimal error until communication is linear in dimension. Our main result is that that by slightly relaxing the standard boundedness assumptions for linear models, we can obtain distributed algorithms that enjoy optimal error with communication logarithmic in dimension. This result is based on a family of algorithms that combine mirror descent with randomized sparsification/quantization of iterates, and extends to the general stochastic convex optimization model.

We propose a data-driven framework to enable the modeling and optimization of human-machine interaction processes, e.g., systems aimed at assisting humans in decision-making or learning, work-load allocation, and interactive advertising. This is a challenging problem for several reasons. First, humans' behavior is hard to model or infer, as it may reflect biases, long term memory, and sensitivity to sequencing, i.e., transience and exponential complexity in the length of the interaction. Second, due to the interactive nature of such processes, the machine policy used to engage with a human may bias possible data-driven inferences. Finally, in choosing machine policies that optimize interaction rewards, one must, on the one hand, avoid being overly sensitive to error/variability in the estimated human model, and on the other, being overly deterministic/predictable which may result in poor human 'engagement' in the interaction. To meet these challenges, we propose a robust approach, based on the maximum entropy principle, which iteratively estimates human behavior and optimizes the machine policy--Alternating Entropy-Reward Ascent (AREA) algorithm. We characterize AREA, in terms of its space and time complexity and convergence. We also provide an initial validation based on synthetic data generated by an established noisy nonlinear model for human decision-making.

As a recent graduate of the Flatiron School's Data Science Bootcamp, I've been inundated with advice on how to ace technical interviews. A soft skill that keeps coming to the forefront is the ability to explain complex machine learning algorithms to a non-technical person. This series of posts is me sharing with the world how I would explain all the machine learning topics I come across on a regular basis...to my grandma. Some get a bit in-depth, others less so, but all I believe are useful to a non-Data Scientist. In the upcoming parts of this series, I'll be going over: To summarize, an algorithm is the mathematical life force behind a model.

Daniel D. Gutierrez is a practicing data scientist who's been working with data long before the field came in vogue. As a technology journalist, he enjoys keeping a pulse on this fast-paced industry. Daniel is also an educator having taught data science, machine learning and R classes at the university level. He has authored four computer industry books on database and data science technology, including his most recent title, "Machine Learning and Data Science: An Introduction to Statistical Learning Methods with R." Daniel holds a BS in Mathematics and Computer Science from UCLA.

In many real-world applications such as text categorization and face recognition, the dimensions of data are usually very high. Dealing with high-dimensional data is computationally expensive while noise or outliers in the data can increase dramatically as the dimension increases. Dimension reduction is one of the most important and effective methods to handle high dimensional data [4, 17, 20]. Among the dimension reduction methods, Principal Component Analysis (PCA) is one of the most widely used methods due to its simplicity and effectiveness. PCA is a statistical procedure that uses an orthogonal transformation to convert a set of correlated variables into a set of linearly uncorrelated principal directions. Usually the number of principal directions is less than or equal to the number of original variables. This transformation is defined in such a way that the first principal direction has the largest possible variance (that is, accounts for as much of the variability in the data as possible), and each succeeding direction has the highest variance under the constraint that it is orthogonal to the preceding directions. The resulting vectors are an uncorrelated orthogonal basis set. When data points lie in a low-dimensional manifold and the manifold is linear or nearly-linear, the low-dimensional structure of data can be effectively captured by a linear subspace spanned by the principal PCA directions.

We propose Zeno++, a new robust asynchronous synchronous Stochastic Gradient Descent~(SGD) under a general Byzantine failure model with unbounded number of Byzantine workers.

Determining the number of clusters when performing unsupervised clustering is a tricky problem. Many data sets don't exhibit well separated clusters, and two human beings asked to visually tell the number of clusters by looking at a chart, are likely to provide two different answers. Sometimes clusters overlap with each other, and large clusters contain sub-clusters, making a decision not easy. For instance, how many clusters do you see in the picture below? What is the optimum number of clusters?