AdaBoost has attracted much attention in the machine learning community because of its
excellent performance in combining weak classifiers into strong classifiers. However …

Class imbalance, where there are great differences between the number of observations
associated with particular discrete outcomes, is common within transportation and other …

We present a systematic study of the bipartite ranking problem, with the aim of explicating its
connections to the class-probability estimation problem. Our study focuses on the properties …

A new family of boosting algorithms, denoted Taylor-Boost, is proposed. It supports any
combination of loss function and first or second order optimization, and includes classical …

We present a minimax framework for classification that considers stochastic adversarial
perturbations to the training data. We show that for binary classification it is equivalent to …

We introduce a novel bias-variance decomposition for a range of strictly convex margin
losses, including the logistic loss (minimized by the classic LogitBoost algorithm) as well as …

The problem of simultaneous feature extraction and selection, for classifier design, is
considered. A new framework is proposed, based on boosting algorithms that can either 1) …

Using discrete choice models to forecast travelers parking location choice has been a
branch of parking demand research for many years. The most used discrete choice models …

Structural models are shown to be highly effective tools in computer vision and image
processing. Conditional random fields (CRFs) are a powerful group of statistical graphical …

In this thesis the problem of designing a fast multiclass object detector based on cascade
architecture is considered. A classifier cascade is a sequence of simple to complex sub …