Distance plays a fundamental role in measuring similarity between objects. Various visualization techniques and learning tasks in statistics and machine learning such as shape matching, classification, dimension reduction and clustering often rely on some distance or similarity measure. It is of tremendous importance to have a distance that can incorporate the underlying structure of the object. In this paper, we focus on proposing such a distance between network objects. Our key insight is to define a distance based on the long term diffusion behavior of the whole network. We first introduce a dynamic system on graphs called Laplacian flow. Based on this Laplacian flow, a new version of diffusion distance between networks is proposed. We will demonstrate the utility of the distance and its advantage over various existing distances through explicit examples. The distance is also applied to subsequent learning tasks such as clustering network objects.

The reparameterization trick is widely used in variational inference as it yields more accurate estimates of the gradient of the variational objective than alternative approaches such as the score function method. Although there is overwhelming empirical evidence in the literature showing its success, there is relatively little research exploring why the reparameterization trick is so effective. We explore this under the idealized assumptions that the variational approximation is a mean-field Gaussian density and that the log of the joint density of the model parameters and the data is a quadratic function that depends on the variational mean. From this, we show that the marginal variances of the reparameterization gradient estimator are smaller than those of the score function gradient estimator. We apply the result of our idealized analysis to real-world examples.

By balancing margin-quantity maximization and margin-quality maximization, the proposed IMMIGRATE algorithm considers both local and global information when using margin-based frameworks. We here derive a new mathematical interpretation of margin-based cost function by using the quadratic form distance (QFD) and applying both the large-margin and max-min entropy principles. We also design a new principle for classifying new samples and propose a Bayesian framework to iteratively minimize the cost function. We demonstrate the power of our new method by comparing it with 16 widely used classifiers (e.g. Support Vector Machine, k-nearest neighbors, RELIEF, etc.) including some classifiers that are capable of identifying interaction terms (e.g. SODA, hierNet, etc.) on synthetic dataset, five gene expression datasets, and twenty UCI machine learning datasets. Our method is able to outperform other methods in most cases.

Person identification is critical for sensitive applications such as system login/unlock, access control and payment. In this paper, we present an operation-free person identification system, namely WiPIN, that identifies biometric features of users using Wi-Fi signals. Our approach is based on an entirely new insight that different persons have distinct effects, including the absorption and reflection, on the Wi-Fi signals. We show that through effective signal processing and feature extraction/matching designs, the Channel State Information (CSI) used in recent Wi-Fi protocols can be utilized for person identification without requiring any collaborative operations, such as wiping, walking, or speaking. We theoretically analyzed the interaction between the human body and Wi-Fi Signals via an interactive model. We proposed a mapping rule between variation patterns of Wi-Fi signals and human biologic features, and demonstrated the feasibility of establishing CSI based person identifiers. We conducted extensive experiments over commodity off-the-shelf Wi-Fi devices. The results show WiPIN achieves 92% accuracy in person identification over a group of 30 users, with sufficient robustness to environment noises.

Ensemble learning is a statistical paradigm built on the premise that many weak learners can perform exceptionally well when deployed collectively. The BART method of Chipman et al. (2010) is a prominent example of Bayesian ensemble learning, where each learner is a tree. Due to its impressive performance, BART has received a lot of attention from practitioners. Despite its wide popularity, however, theoretical studies of BART have begun emerging only very recently. Laying the foundations for the theoretical analysis of Bayesian forests, Rockova and van der Pas (2017) showed optimal posterior concentration under conditionally uniform tree priors. These priors deviate from the actual priors implemented in BART. Here, we study the exact BART prior and propose a simple modification so that it also enjoys optimality properties. To this end, we dive into branching process theory. We obtain tail bounds for the distribution of total progeny under heterogeneous Galton-Watson (GW) processes exploiting their connection to random walks. We conclude with a result stating the optimal rate of posterior convergence for BART.

Graphical Lasso (GL) is a popular method for learning the structure of an undirected graphical model, which is based on an $l_1$ regularization technique. The objective of this paper is to compare the computationally-heavy GL technique with a numerically-cheap heuristic method that is based on simply thresholding the sample covariance matrix. To this end, two notions of sign-consistent and inverse-consistent matrices are developed, and then it is shown that the thresholding and GL methods are equivalent if: (i) the thresholded sample covariance matrix is both sign-consistent and inverse-consistent, and (ii) the gap between the largest thresholded and the smallest un-thresholded entries of the sample covariance matrix is not too small. By building upon this result, it is proved that the GL method--as a conic optimization problem--has an explicit closed-form solution if the thresholded sample covariance matrix has an acyclic structure. This result is then generalized to arbitrary sparse support graphs, where a formula is found to obtain an approximate solution of GL. Furthermore, it is shown that the approximation error of the derived explicit formula decreases exponentially fast with respect to the length of the minimum-length cycle of the sparsity graph. The developed results are demonstrated on synthetic data, functional MRI data, traffic flows for transportation networks, and massive randomly generated datasets. We show that the proposed method can obtain an accurate approximation of the GL for instances with the sizes as large as $80,000\times 80,000$ (more than 3.2 billion variables) in less than 30 minutes on a standard laptop computer running MATLAB, while other state-of-the-art methods do not converge within 4 hours.

Recent analyses of certain gradient descent optimization methods have shown that performance can degrade in some settings - such as with stochasticity or implicit momentum. In deep reinforcement learning (Deep RL), such optimization methods are often used for training neural networks via the temporal difference error or policy gradient. As an agent improves over time, the optimization target changes and thus the loss landscape (and local optima) change. Due to the failure modes of those methods, the ideal choice of optimizer for Deep RL remains unclear. As such, we provide an empirical analysis of the effects that a wide range of gradient descent optimizers and their hyperparameters have on policy gradient methods, a subset of Deep RL algorithms, for benchmark continuous control tasks. We find that adaptive optimizers have a narrow window of effective learning rates, diverging in other cases, and that the effectiveness of momentum varies depending on the properties of the environment. Our analysis suggests that there is significant interplay between the dynamics of the environment and Deep RL algorithm properties which aren't necessarily accounted for by traditional adaptive gradient methods. We provide suggestions for optimal settings of current methods and further lines of research based on our findings.

One of the definitional debates that bedevils the artificial intelligence (AI) field is whether machine learning is an AI-based method or technology. Or is it just an analytics-based activity? After all, it is statistical in nature, and attempts--as virtually analytical methods do--to fit a line or curve to a set of data points. And what difference does it make? Basic machine learning is practically indistinguishable from predictive analytics.

To summarize epochs, we either computed the 80% trimmed mean, or the standard deviation (SD). The sensor dimension was then summarized using a mean or the standard deviation, yielding four combinations in total (Figure 1A).

The difference between regression machine learning algorithms and classification machine learning algorithms sometimes confuse most data scientists, which make them to implement wrong methodologies in solving their prediction problems. Andreybu, who is from Germany and has more than 5 years of machine learning experience, says that "understanding whether the machine learning task is a regression or classification problem is key for selecting the right algorithm to use." Let's start by talking about the similarities between the two techniques. Regression and classification are categorized under the same umbrella of supervised machine learning. Both share the same concept of utilizing known datasets (referred to as training datasets) to make predictions. In supervised learning, an algorithm is employed to learn the mapping function from the input variable (x) to the output variable (y); that is y f(X).