Boosting is one of the most successful ideas in machine learning, achieving great practical performance with little fine-tuning. The success of boosted classifiers is most often attributed to improvements in margins. The focus on margin explanations was pioneered in the seminal work by Schaphire et al. (1998) and has culminated in the $k$'th margin generalization bound by Gao and Zhou (2013), which was recently proved to be near-tight for some data distributions (Gr\o nlund et al. 2019). In this work, we first demonstrate that the $k$'th margin bound is inadequate in explaining the performance of state-of-the-art gradient boosters. We then explain the short comings of the $k$'th margin bound and prove a stronger and more refined margin-based generalization bound that indeed succeeds in explaining the performance of modern gradient boosters. Finally, we improve upon the recent generalization lower bound by Gr\o nlund et al. (2019).

We use surrogate losses to obtain several new regret bounds and new algorithms for contextual bandit learning. Using the ramp loss, we derive a new margin-based regret bound in terms of standard sequential complexity measures of a benchmark class of real-valued regression functions. Using the hinge loss, we derive an efficient algorithm with a $\sqrt{dT}$-type mistake bound against benchmark policies induced by $d$-dimensional regressors. Under realizability assumptions, our results also yield classical regret bounds.

Parametric tests are only valid if the data satisfy certain assumptions. If these assumptions hold, they will, however, typically give more accurate results. The analysis of statistical learning theory has very much the flavor of a nonparametric statistical test. The weakness of pac, therefore, is that its results must hold true even in worst-case distributions. There is, however, a new twist to this story in that the more recent pacstyle results are able to take account of observed attributes of the function that has been chosen by the learner, for example, its margin on the training set.

Kernel methods, a new generation of learning algorithms, utilize techniques from optimization, statistics, and functional analysis to achieve maximal generality, flexibility, and performance. These algorithms are different from earlier techniques used in machine learning in many respects: For example, they are explicitly based on a theoretical model of learning rather than on loose analogies with natural learning systems or other heuristics. They come with theoretical guarantees about their performance and have a modular design that makes it possible to separately implement and analyze their components. They are not affected by the problem of local minima because their training amounts to convex optimization. In the last decade, a sizable community of theoreticians and practitioners has formed around these methods, and a number of practical applications have been realized.

This manuscript shows that AdaBoost and its immediate variants can produce approximate maximum margin classifiers simply by scaling step size choices with a fixed small constant. In this way, when the unscaled step size is an optimal choice, these results provide guarantees for Friedman's empirically successful "shrinkage" procedure for gradient boosting (Friedman, 2000). Guarantees are also provided for a variety of other step sizes, affirming the intuition that increasingly regularized line searches provide improved margin guarantees. The results hold for the exponential loss and similar losses, most notably the logistic loss.

Aiming towards the development of a general clustering theory, we discuss abstract axiomatization for clustering. In this respect, we follow up on the work of Kelinberg, (Kleinberg) that showed an impossibility result for such axiomatization. We argue that an impossibility result is not an inherent feature of clustering, but rather, to a large extent, it is an artifact of the specific formalism used in Kleinberg. As opposed to previous work focusing on clustering functions, we propose to address clustering quality measures as the primitive object to be axiomatized. We show that principles like those formulated in Kleinberg's axioms can be readily expressed in the latter framework without leading to inconsistency. A clustering-quality measure is a function that, given a data set and its partition into clusters, returns a non-negative real number representing how `strong' or `conclusive' the clustering is. We analyze what clustering-quality measures should look like and introduce a set of requirements (`axioms') that express these requirement and extend the translation of Kleinberg's axioms to our framework. We propose several natural clustering quality measures, all satisfying the proposed axioms. In addition, we show that the proposed clustering quality can be computed in polynomial time.

There are two mathematical flavors of margin bound dependent upon the weights Wi of the vote and the features Xi that the vote is taken over. The results here are of the "bll2" form. We improve on Shawe-Taylor et al. [12] and Bartlett [1] by a log(m)2 sample complexity factor and much tighter constants (1000 or unstated versus 9 or 18 as suggested by Section 2.2). In addition, the bound here covers margin errors without weakening the error-free case. Herbrich and Graepel [3] moved significantly towards the approach adopted in our paper, but the methodology adopted meant that their result does not scale well to high dimensional feature spaces as the bound here (and earlier results) do.

There are two mathematical flavors of margin bound dependent upon the weights Wi of the vote and the features Xi that the vote is taken over. The results here are of the "bll2" form. We improve on Shawe-Taylor et al. [12] and Bartlett [1] by a log(m)2 sample complexity factor and much tighter constants (1000 or unstated versus 9 or 18 as suggested by Section 2.2). In addition, the bound here covers margin errors without weakening the error-free case. Herbrich and Graepel [3] moved significantly towards the approach adopted in our paper, but the methodology adopted meant that their result does not scale well to high dimensional feature spaces as the bound here (and earlier results) do.

There are two mathematical flavors of margin bound dependent upon the weights Wi of the vote and the features Xi that the vote is taken over. Those ([12], [1]) with a bound on Li w and Li x ("bib" bounds). The results here are of the "bll2" form. We improve on Shawe-Taylor et al. [12] and Bartlett [1] by a log(m)2 sample complexity factor and much tighter constants (1000 or unstated versus 9 or 18 as suggested by Section 2.2). In addition, the bound here covers margin errors without weakening the error-free case.

We present an improvement of Novikoff's perceptron convergence theorem. Reinterpreting this mistake bound as a margin dependent sparsity guarantee allows us to give a PACstyle generalisation error bound for the classifier learned by the perceptron learning algorithm. The bound value crucially depends on the margin a support vector machine would achieve on the same data set using the same kernel. Ironically, the bound yields better guarantees than are currently available for the support vector solution itself.