These notes aim to shed light on the recently proposed structured projected intermediate gradient optimization technique (SPIGOT, Peng et al., 2018). SPIGOT is a variant of the straight-through estimator (Bengio et al., 2013) which bypasses gradients of the argmax function by back-propagating a surrogate "gradient." We provide a new interpretation to the proposed gradient and put this technique into perspective, linking it to other methods for training neural networks with discrete latent variables. As a by-product, we suggest alternate variants of SPIGOT which will be further explored in future work.

Conversion prediction plays an important role in online advertising since Cost-Per-Action (CPA) has become one of the primary campaign performance objectives in the industry. Unlike click prediction, conversions have different types in nature, and each type may be associated with different decisive factors. In this paper, we formulate conversion prediction as a multi-task learning problem, so that the prediction models for different types of conversions can be learned together. These models share feature representations, but have their specific parameters, providing the benefit of information-sharing across all tasks. We then propose Multi-Task Field-weighted Factorization Machine (MT-FwFM) to solve these tasks jointly. Our experiment results show that, compared with two state-of-the-art models, MT-FwFM improve the AUC by 0.74% and 0.84% on two conversion types, and the weighted AUC across all conversion types is also improved by 0.50%.

K-Nearest Neighbors, or KNN for short, is one of the simplest machine learning algorithms and is used in a wide array of institutions. KNN is a non-parametric, lazy learning algorithm. When we say a technique is non-parametric, it means that it does not make any assumptions about the underlying data. In other words, it makes its selection based off of the proximity to other data points regardless of what feature the numerical values represent. Being a lazy learning algorithm implies that there is little to no training phase.

Federated learning systems enable the collaborative training of machine learning models among different organizations under the privacy restrictions. As researchers try to support more machine learning models with different privacy-preserving approaches, current federated learning systems face challenges from various issues such as unpractical system assumptions, scalability and efficiency. Inspired by federated systems in other fields such as databases and cloud computing, we investigate the characteristics of federated learning systems. We find that two important features for other federated systems, i.e., heterogeneity and autonomy, are rarely considered in the existing federated learning systems. Moreover, we provide a thorough categorization for federated learning systems according to four different aspects, including data partition, model, privacy level, and communication architecture. Lastly, we take a systematic comparison among the existing federated learning systems and present future research opportunities and directions.

Machine learning techniques for Recommendation System (RS) and Classification has become a prime focus of research to tackle the problem of information overload. RS are software tools that aim at making informed decisions about the services that a user may like. On the other hand, classification technique deals with the categorization of a data object into one of the several predefined classes. In the multi-label classification problem, unlike the traditional multi-class classification setting, each instance can be simultaneously associated with a subset of labels. The focus of thesis is on the development of novel techniques for collaborative filtering and multi-label classification. We propose a novel method of constructing a hierarchical bi-level maximum margin matrix factorization to handle matrix completion of ordinal rating matrix. Taking the cue from the alternative formulation of support vector machines, a novel loss function is derived by considering proximity as an alternative criterion instead of margin maximization criterion for matrix factorization framework. We extended the concept of matrix factorization for yet another important problem of machine learning namely multi-label classification which deals with the classification of data with multiple labels. We propose a novel piecewise-linear embedding method with a low-rank constraint on parametrization to capture nonlinear intrinsic relationships that exist in the original feature and label space. We also study the embedding of labels together with the group information with an objective to build an efficient multi-label classifier. We assume the existence of a low-dimensional space onto which the feature vectors and label vectors can be embedded. We ensure that labels belonging to the same group share the same sparsity pattern in their low-rank representations.

Classical Principal Component Analysis (PCA) approximates data in terms of projections on a small number of orthogonal vectors. There are simple procedures to efficiently compute various functions of the data from the PCA approximation. The most important function is arguably the Euclidean distance between data items, This can be used, for example, to solve the approximate nearest neighbor problem. We use random variables to model the inherent uncertainty in such approximations, and apply the Maximum Entropy Method to infer the underlying probability distribution. We propose using the expected values of distances between these random variables as improved estimates of the distance. We show by analysis and experimentally that in most cases results obtained by our method are more accurate than what is obtained by the classical approach. This improves the accuracy of a classical technique that have been used with little change for over 100 years.

We implement machine learning algorithms to nuclear data. These algorithms are purely data driven and generate models that are capable to capture intricate trends. Gradient boosted trees algorithm is employed to generate a trained model from existing nuclear data, which is used for prediction for data of damping parameter, shell correction energies, quadrupole deformation, pairing gaps, level densities and giant dipole resonance for large number of nuclei. We, in particular, predict level density parameter for superheavy elements which is of great current interest. The predictions made by the machine learning algorithm is found to have standard deviation from 0.00035 to 0.73.

Nonconvex optimization algorithms with random initialization have attracted increasing attention recently. It has been showed that many first-order methods always avoid saddle points with random starting points. In this paper, we answer a question: can the nonconvex heavy-ball algorithms with random initialization avoid saddle points? The answer is yes! Direct using the existing proof technique for the heavy-ball algorithms is hard due to that each iteration of the heavy-ball algorithm consists of current and last points. It is impossible to formulate the algorithms as iteration like xk+1= g(xk) under some mapping g. To this end, we design a new mapping on a new space. With some transfers, the heavy-ball algorithm can be interpreted as iterations after this mapping. Theoretically, we prove that heavy-ball gradient descent enjoys larger stepsize than the gradient descent to escape saddle points to escape the saddle point. And the heavy-ball proximal point algorithm is also considered; we also proved that the algorithm can always escape the saddle point.

Variational autoencoders (VAE) have quickly become a central tool in machine learning, applicable to a broad range of data types and latent variable models. By far the most common first step, taken by seminal papers and by core software libraries alike, is to model MNIST data using a deep network parameterizing a Bernoulli likelihood. This practice contains what appears to be and what is often set aside as a minor inconvenience: the pixel data is [0, 1] valued, not {0, 1} as supported by the Bernoulli likelihood. Here we show that, far from being a triviality or nuisance that is convenient to ignore, this error has profound importance to VAE, both qualitative and quantitative. We introduce and fully characterize a new [0, 1]-supported, single parameter distribution: the continuous Bernoulli, which patches this pervasive bug in VAE. This distribution is not nitpicking; it produces meaningful performance improvements across a range of metrics and datasets, including sharper image samples, and suggests a broader class of performant VAE.

In the last decade, there has been a great technological advance in the infrastructure of mobile technologies. The increase in the use of wireless local area networks and the use of satellite services are also noticed. The high utilization rate of mobile devices for various purposes makes clear the need to track wireless networks to ensure the integrity and confidentiality of the information transmitted. Therefore, it is necessary to quickly and efficiently identify the normal and abnormal traffic of such networks, so that administrators can take action. This work aims to analyze classification techniques in relation to data from Wireless Networks, using some classes of anomalies pre-established according to some defined criteria of the MAC layer. For data analysis, WEKA Data Mining software (Waikato Environment for Knowledge Analysis) is used. The classification algorithms present a success rate in the classification of viable data, being indicated in the use of intrusion detection systems for wireless networks.