Setting of the learning problem consistency of learning processes bounds on the rate of convergence of learning processes controlling the generalization ability of learning processes constructing learning algorithms what is important in learning theory?.

The Nature of Statistical Learning Theory

In this tutorial we give an overview of the basic ideas underlying Support Vector (SV) machines for function estimation. Furthermore, we include a summary of currently used algorithms for training SV machines, covering both the quadratic (or convex) programming part and advanced methods for dealing with large datasets. Finally, we mention some modifications and extensions that have been applied to the standard SV algorithm, and discuss the aspect of regularization from a SV perspective.

/pdf/a-tutorial-on-support-vector-regression-10mfvogjkf.pdf

A tutorial on support vector regression

The use of randomness is now an accepted tool in Theoretical Computer Science but not everyone is aware of the underpinnings of this methodology in Combinatorics - particularly, in what is now called the probabilistic Method as developed primarily by Paul Erdoős over the past half century. Here I will explore a particular set of problems - all dealing with “good” colorings of an underlying set of points relative to a given family of sets. A central point will be the evolution of these problems from the purely existential proofs of Erdős to the algorithmic aspects of much interest to this audience.

/pdf/the-probabilistic-method-5g63k0itke.pdf

The Probabilistic Method

Machine learning is one of the fastest growing areas of computer science, with far-reaching applications. The aim of this textbook is to introduce machine learning, and the algorithmic paradigms it offers, in a principled way. The book provides an extensive theoretical account of the fundamental ideas underlying machine learning and the mathematical derivations that transform these principles into practical algorithms. Following a presentation of the basics of the field, the book covers a wide array of central topics that have not been addressed by previous textbooks. These include a discussion of the computational complexity of learning and the concepts of convexity and stability; important algorithmic paradigms including stochastic gradient descent, neural networks, and structured output learning; and emerging theoretical concepts such as the PAC-Bayes approach and compression-based bounds. Designed for an advanced undergraduate or beginning graduate course, the text makes the fundamentals and algorithms of machine learning accessible to students and non-expert readers in statistics, computer science, mathematics, and engineering.

/pdf/understanding-machine-learning-from-theory-to-algorithms-5aeszqx33g.pdf

Understanding Machine Learning: From Theory To Algorithms

This important text and reference for researchers and students in machine learning, game theory, statistics and information theory offers a comprehensive treatment of the problem of predicting individual sequences. Unlike standard statistical approaches to forecasting, prediction of individual sequences does not impose any probabilistic assumption on the data-generating mechanism. Yet, prediction algorithms can be constructed that work well for all possible sequences, in the sense that their performance is always nearly as good as the best forecasting strategy in a given reference class. The central theme is the model of prediction using expert advice, a general framework within which many related problems can be cast and discussed. Repeated game playing, adaptive data compression, sequential investment in the stock market, sequential pattern analysis, and several other problems are viewed as instances of the experts' framework and analyzed from a common nonstochastic standpoint that often reveals new and intriguing connections.

/pdf/prediction-learning-and-games-31z1lqjpec.pdf

Prediction, learning, and games

A tree is scattered if no subdivision of the complete binary tree is a subtree. Building on results of Halin, Polat and Sabidussi, we identify four types of subtrees of a scattered tree and a function of the tree into the integers at least one of which is preserved by every embedding. 
With this result and a result of Tyomkyn, we prove that the tree alternative property conjecture of Bonato and Tardif holds for scattered trees and a conjecture of Tyomkin holds for locally finite scattered trees.

Invariant subsets of scattered trees. An application to the tree alternative property of Bonato and Tardif

The \textit{age} of a relational structure $\mathfrak A$ of signature $\mu$ is the set $age(\mathfrak A)$ of its finite induced substructures, considered up to isomorphism. This is an ideal in the poset $\Omega_\mu$ consisting of finite structures of signature $\mu$ and ordered by embeddability. If the structures are made of infinitely many relations and if, among those, infinitely many are at least binary then there are ideals which do not come from an age. We provide many examples. We particularly look at metric spaces and offer several problems. We also provide an example of an ideal $I$ of isomorphism types of at most countable structures whose signature consists of a single ternary relation symbol. This ideal does not come from the set $\age_{\mathfrak I}(\mathfrak A)$ of isomorphism types of substructures of $\mathfrak A$ induced on the members of an ideal $\mathfrak I$ of sets. This answers a question due to R. Cusin and J.F. Pabion (1970).

Representation of ideals of relational structures

Two orders on the same set are orthogonal if the constant maps and the identity map are the only maps preserving both orders. We construct linear orders orthogonal to the order on the rationals.

The Order on the Rationals has an Orthogonal Order with the Same Order Type

https://contacts.ucalgary.ca/info/math/files/info/unitis/courses/PMAT60351/F2006/LEC1/age27-07-06.%2004.30PM.pdf

We investigate infinite versions of vector and affine space partition results, and thus obtain examples and a counterexample for a partition problem for relational structures. In particular we provide two (related) examples of an age indivisible relational structure which is not weakly indivisible.

Norbert Sauer

Papers

Invariant subsets of scattered trees. An application to the tree alternative property of Bonato and Tardif

Representation of ideals of relational structures

The Order on the Rationals has an Orthogonal Order with the Same Order Type

Representation of ideals of relational structures

Partitions and Indivisibility Properties of Countable Dimensional Vector Spaces