Bøger i Foundations and Trends (R) in Machine Learning serien

Variational autoencoders (VAEs) are powerful deep generative models widely used to represent high-dimensional complex data through a low-dimensional latent space learned in an unsupervised manner. In this volume, the authors introduce and discuss a general class of models, called dynamical variational autoencoders.

Tensor Regression is the first thorough overview of the fundamentals, motivations, popular algorithms, strategies for efficient implementation, related applications, available datasets, and software resources for tensor-based regression analysis.

Minimum-Distortion Embedding describes the theory behind and practical use of a cutting-edge artificial intelligence technique. Accompanied by an open-source software package, PyMDE, it illustrates applying these AI techniques in areas such as images, co- networks, demographics, genetics, and biology.

The term Federated Learning was coined as recently as 2016 to describe a machine learning setting where multiple entities collaborate in solving a machine learning problem, under the coordination of a central server or service provider. This book describes the latest state-of-the art.

Provides a comprehensive introduction to generating advanced data analytics on graphs that allows us to move beyond the standard regular sampling in time and space to facilitate modelling in many important areas.

Provides a review of existing graph kernels, their applications, software plus data resources, and an empirical comparison of state-of-the-art graph kernels. The book focuses on the theoretical description of common graph kernels, and on a large-scale empirical evaluation of graph kernels.

Surveys recent progress in using spectral methods, including matrix and tensor decomposition techniques, to learn many popular latent variable models. The focus is on a special type of tensor decomposition called CP decomposition. The authors cover a wide range of algorithms to find the components of such tensor decomposition.

Presents an introduction to the framework of variational autoencoders (VAEs) that provides a principled method for jointly learning deep latent-variable models and corresponding inference models using stochastic gradient descent.

Sequential Monte Carlo is a technique for solving statistical inference problems recursively. This book shows how this powerful technique can be applied to machine learning problems such as probabilistic programming, variational inference and inference evaluation.

Provides a textbook like treatment of multi-armed bandits. The work on multi-armed bandits can be partitioned into a dozen or so directions. Each chapter tackles one line of work, providing a self-contained introduction and pointers for further reading.

Presents an overview of the main theoretical insights that support the practical effectiveness of OT before explaining how to turn these insights into fast computational schemes. This book will be a valuable reference for researchers and students wishing to get a thorough understanding of computational optimal transport.

Provides a starting point for understanding deep reinforcement learning. Although written at a research level it provides a comprehensive and accessible introduction to deep reinforcement learning models, algorithms and techniques.

Reviews and extends some important results in random matrix theory in the specific context of real random Wishart matrices. To overcome the complexity of the subject matter, the authors use a lecture note style to make the material accessible to a wide audience. This results in a comprehensive and self-contained introduction.

Covers the Thompson sampling algorithm and its application, illustrating concepts through a range of examples, including Bernoulli bandit problems, shortest path problems, product recommendation, assortment, active learning with neural networks, and reinforcement learning in Markov decision processes.

Many modern methods for prediction leverage nearest neighbour search to find past training examples most similar to a test example, an idea that dates back in text to at least the 11th century and has stood the test of time. This monograph explains the success of these methods, both in theory and in practice.

Provides a systematic and example-rich guide to the basic properties and applications of tensor network methodologies, and demonstrates their promise as a tool for the analysis of extreme-scale multidimensional data. The book demonstrates the ability of tensor networks to provide linearly or even super-linearly, scalable solutions.

Principal components analysis (PCA) is a well-known technique for approximating a tabular data set by a low rank matrix. In this volume, the authors extend the idea of PCA to handle arbitrary data sets consisting of numerical, Boolean, categorical, ordinal, and other data types.

Identifies unifying principles, patterns, and intuitions for scaling Bayesian inference. This book examines how these techniques can be scaled up to larger problems and scaled out across parallel computational resources, and reviews existing work on utilizing computing resources with both MCMC and variational approximation techniques.

Discusses models and methods for Bayesian inference in the simple single-step Bandit model. The book then reviews the extensive recent literature on Bayesian methods for model-based RL, where prior information can be expressed on the parameters of the Markov model.

Takes the learning-theory point of view of property testing and focuses on results for testing properties of functions that are of interest to the learning theory community. In particular the book covers results for testing algebraic properties of functions such as linearity.

Presents the main complexity theorems in convex optimization and their corresponding algorithms. The book begins with the fundamental theory of black-box optimization and proceeds to guide the reader through recent advances in structural optimization and stochastic optimization.

Offers an invitation to the field of matrix concentration inequalities. The book begins with some history of random matrix theory; describes a flexible model for random matrices that is suitable for many problems; and discusses the most important matrix concentration results.

Provides a simple and clear description of explicit-duration modelling by categorizing the different approaches into three main groups, which differ in encoding in the explicit-duration variables different information about regime switching/reset boundaries.

Describes recent advances in our understanding of the theoretical benefits of active learning, and implications for the design of effective active learning algorithms. Much of the book focuses on a particular technique - disagreement-based active learning. It also briefly surveys several alternative approaches from the literature.

Examines the topic of information processing over graphs. The presentation is largely self-contained and covers results that relate to the analysis and design of multi-agent networks for the distributed solution of optimization, adaptation, and learning problems from streaming data through localized interactions among agents.

Covers several aspects of the "optimism in the face of uncertainty" principle for large scale optimization problems under finite numerical budget. The book lays out the theoretical foundations of the field by characterizing the complexity of the optimization problems and designing efficient algorithms with performance guarantees.

A Markov Decision Process (MDP) is a natural framework for formulating sequential decision-making problems under uncertainty. In recent years, researchers have greatly advanced algorithms for learning and acting in MDPs. This book reviews such algorithms.

Presents the theory of submodular functions in a self-contained way from a convex analysis perspective, presenting tight links between certain polyhedra, combinatorial optimization and convex optimization problems. In particular, it describes how submodular function minimization is equivalent to solving a variety of convex optimization problems.

Presents an overview of existing research in this topic, including recent progress on scaling to high-dimensional feature spaces and to data sets with an extremely large number of data points. The book presents as unified a framework as possible under which existing research on metric learning can be cast.

Reviews a branch of Monte Carlo methods that are based on the forward-backward idea, and that are referred to as backward simulators. In recent years, the theory and practice of backward simulation algorithms have undergone a significant development, and the algorithms keep finding new applications.