No abstract

Often the best performing supervised learning models are ensembles of hundreds or thousands of base-level classifiers. Unfortunately, the space required to store this many classifiers, and the time required to execute them at run-time, prohibits their use in applications where test sets are large (e.g. Google), where storage space is at a premium (e.g. PDAs), and where computational power is limited (e.g. hearing aids). We present a method for "compressing" large, complex ensembles into smaller, faster models, usually without significant loss in performance.

A number of supervised learning methods have been introduced in the last decade. Unfortunately, the last comprehensive empirical evaluation of supervised learning was the Statlog Project in the early 90's. We present a large-scale empirical comparison between ten supervised learning methods: SVMs, neural nets, logistic regression, naive bayes, memory-based learning, random forests, decision trees, bagged trees, boosted trees, and boosted stumps. We also examine the effect that calibrating the models via Platt Scaling and Isotonic Regression has on their performance. An important aspect of our study is the use of a variety of performance criteria to evaluate the learning methods.

No abstract

Multitask Learning is an approach to inductive transfer that improves generalization by using the domain information contained in the training signals of related tasks as an inductive bias. It does this by learning tasks in parallel while using a shared representation; what is learned for each task can help other tasks be learned better. This paper reviews prior work on MTL, presents new evidence that MTL in backprop nets discovers task relatedness without the need of supervisory signals, and presents new results for MTL with k-nearest neighbor and kernel regression. In this paper we demonstrate multitask learning in three domains. We explain how multitask learning works, and show that there are many opportunities for multitask learning in real domains. We present an algorithm and results for multitask learning with case-based methods like k-nearest neighbor and kernel regression, and sketch an algorithm for multitask learning in decision trees. Because multitask learning works, can be applied to many different kinds of domains, and can be used with different learning algorithms, we conjecture there will be many opportunities for its use on real-world problems.

No abstract

We present an abstraction of the genetic algorithm (GA), termed population-based incremental learning (PBIL), that explicitly maintains the statistics contained in a GA's population, but which abstracts away the crossover operator and redefines the role of the population. This results in PBIL being simpler, both computationally and theoretically, than the GA. Empirical results reported elsewhere show that PBIL is faster and more effective than the GA on a large set of commonly used benchmark problems. Here we present results on a problem custom designed to benefit both from the GA's crossover operator and from its use of a population. The results show that PBIL performs as well as, or better than, GAs carefully tuned to do well on this problem. This suggests that even on problems custom designed for GAs, much of the power of the GA may derive from the statistics maintained implicitly in its population, and not from the population itself nor from the crossover operator.

Complex models for regression and classification have high accuracy, but are unfortunately no longer interpretable by users. We study the performance of generalized additive models (GAMs), which combine single-feature models called shape functions through a linear function. Since the shape functions can be arbitrarily complex, GAMs are more accurate than simple linear models. But since they do not contain any interactions between features, they can be easily interpreted by users.We present the first large-scale empirical comparison of existing methods for learning GAMs. Our study includes existing spline and tree-based methods for shape functions and penalized least squares, gradient boosting, and backfitting for learning GAMs. We also present a new method based on tree ensembles with an adaptive number of leaves that consistently outperforms previous work. We complement our experimental results with a bias-variance analysis that explains how different shape models influence the additive model. Our experiments show that shallow bagged trees with gradient boosting distinguish itself as the best method on low-to medium-dimensional datasets.