This Increasing privacy concerns and unrestricted access to data communication overhead slows down the convergence of lead to the development of a novel machine learning the Machine Learning algorithms. For example, the client paradigm called Federated Learning (FL). FL borrows many devices could be self-driving cars in which the goal might be of the ideas from distributed machine learning, however, the to create a driver sleep prevention face recognition machine challenges associated with federated learning makes it an learning system preventing road accidents or making use of interesting engineering problem since the models are trained large volumes of traffic training data from cameras in the on edge devices. It was introduced in 2016 by Google, and vehicles to improve the vehicle AI agent's driving since then active research is being carried out in different capability. Because in both cases, due to the possibility of areas within FL such as federated optimization algorithms, collecting large number of samples by increasing the client model and update compression, differential privacy, devices, the data used to train models will have a large robustness, and attacks, federated GANs and privacy variance (carries more Information) and will be more robust preserved personalization. There are many open challenges to bias (race of the driver, different types of roads, and in the development of such federated machine learning pedestrian scenarios) and thus underrepresentation of systems and this project will be focusing on the samples is minimized. The slower client connections might communication bottleneck and data Non IID-ness, and its also cause stragglers.

In this report, we describe our systems in which the objective is to determine whether a given news article could be considered as hyperpartisan. Hyperpartisan news is news that takes an extremely polarized political standpoint with an intention of creating political divide among the public. We attempted several approaches, including n-grams, sentiment analysis, as well as sentence and document representation using pre-tained ELMo. Our best system using pre-trained ELMo with Bidirectional LSTM achieved an accuracy of around 83% through 10-fold cross-validation without much hyperparameter tuning.

We consider the problem of learning a high-dimensional graphical model in which certain hub nodes are highly-connected to many other nodes. Many authors have studied the use of an l1 penalty in order to learn a sparse graph in high-dimensional setting. However, the l1 penalty implicitly assumes that each edge is equally likely and independent of all other edges. We propose a general framework to accommodate more realistic networks with hub nodes, using a convex formulation that involves a row-column overlap norm penalty. We apply this general framework to three widely-used probabilistic graphical models: the Gaussian graphical model, the covariance graph model, and the binary Ising model. An alternating direction method of multipliers algorithm is used to solve the corresponding convex optimization problems. On synthetic data, we demonstrate that our proposed framework outperforms competitors that do not explicitly model hub nodes. We illustrate our proposal on a webpage data set and a gene expression data set.

We consider the problem of Graphical lasso with an additional $\ell_{\infty}$ element-wise norm constraint on the precision matrix. This problem has applications in high-dimensional covariance decomposition such as in \citep{Janzamin-12}. We propose an ADMM algorithm to solve this problem. We also use a continuation strategy on the penalty parameter to have a fast implemenation of the algorithm.

We consider estimation of multiple high-dimensional Gaussian graphical models corresponding to a single set of nodes under several distinct conditions. We assume that most aspects of the networks are shared, but that there are some structured differences between them. Specifically, the network differences are generated from node perturbations: a few nodes are perturbed across networks, and most or all edges stemming from such nodes differ between networks. This corresponds to a simple model for the mechanism underlying many cancers, in which the gene regulatory network is disrupted due to the aberrant activity of a few specific genes. We propose to solve this problem using the structured joint graphical lasso, a convex optimization problem that is based upon the use of a novel symmetric overlap norm penalty, which we solve using an alternating directions method of multipliers algorithm. Our proposal is illustrated on synthetic data and on an application to brain cancer gene expression data.