Saher Esmeir

IJCAI Conference 2007 Conference Paper

• Saher Esmeir
• Shaul Markovitch

Occam's razor is the principle that, given two hypotheses consistent with the observed data, the simpler one should be preferred. Many machine learning algorithms follow this principle and search for a small hypothesis within the version space. The principle has been the subject of a heated debate with theoretical and empirical arguments both for and against it. Earlier empirical studies lacked sufficient coverage to resolve the debate. In this work we provide convincing empirical evidence for Occam's razor in the context of decision tree induction. By applying a variety of sophisticated sampling techniques, our methodology samples the version space for many real-world domains and tests the correlation between the size of a tree and its accuracy. We show that indeed a smaller tree is likely to be more accurate, and that this correlation is statistically significant across most domains.

NeurIPS Conference 2007 Conference Paper

Anytime Induction of Cost-sensitive Trees

• Saher Esmeir
• Shaul Markovitch

Machine learning techniques are increasingly being used to produce a wide-range of classifiers for complex real-world applications that involve nonuniform testing costs and misclassification costs. As the complexity of these applications grows, the management of resources during the learning and classification processes be- comes a challenging task. In this work we introduce ACT (Anytime Cost-sensitive Trees), a novel framework for operating in such environments. ACT is an anytime algorithm that allows trading computation time for lower classification costs. It builds a tree top-down and exploits additional time resources to obtain better esti- mations for the utility of the different candidate splits. Using sampling techniques ACT approximates for each candidate split the cost of the subtree under it and fa- vors the one with a minimal cost. Due to its stochastic nature ACT is expected to be able to escape local minima, into which greedy methods may be trapped. Ex- periments with a variety of datasets were conducted to compare the performance of ACT to that of the state of the art cost-sensitive tree learners. The results show that for most domains ACT produces trees of significantly lower costs. ACT is also shown to exhibit good anytime behavior with diminishing returns.

JMLR Journal 2007 Journal Article

Anytime Learning of Decision Trees

• Saher Esmeir
• Shaul Markovitch

The majority of existing algorithms for learning decision trees are greedy---a tree is induced top-down, making locally optimal decisions at each node. In most cases, however, the constructed tree is not globally optimal. Even the few non-greedy learners cannot learn good trees when the concept is difficult. Furthermore, they require a fixed amount of time and are not able to generate a better tree if additional time is available. We introduce a framework for anytime induction of decision trees that overcomes these problems by trading computation speed for better tree quality. Our proposed family of algorithms employs a novel strategy for evaluating candidate splits. A biased sampling of the space of consistent trees rooted at an attribute is used to estimate the size of the minimal tree under that attribute, and an attribute with the smallest expected tree is selected. We present two types of anytime induction algorithms: a contract algorithm that determines the sample size on the basis of a pre-given allocation of time, and an interruptible algorithm that starts with a greedy tree and continuously improves subtrees by additional sampling. Experimental results indicate that, for several hard concepts, our proposed approach exhibits good anytime behavior and yields significantly better decision trees when more time is available. [abs] [ pdf ][ bib ] &copy JMLR 2007. ( edit, beta )

AAAI Conference 2006 Conference Paper

Anytime Induction of Decision Trees: An Iterative Improvement Approach

• Saher Esmeir

Most existing decision tree inducers are very fast due to their greedy approach. In many real-life applications, however, we are willing to allocate more time to get better decision trees. Our recently introduced LSID3 contract anytime algorithm allows computation speed to be traded for better tree quality. As a contract algorithm, LSID3 must be allocated its resources a priori, which is not always possible. In this work, we present IIDT, a general framework for interruptible induction of decision trees that need not be allocated resources a priori. The core of our proposed framework is an iterative improvement algorithm that repeatedly selects a subtree whose reconstruction is expected to yield the highest marginal utility. The algorithm then rebuilds the subtree with a higher allocation of resources. IIDT can also be configured to receive training examples as they become available, and is thus appropriate for incremental learning tasks. Empirical evaluation with several hard concepts shows that IIDT exhibits good anytime behavior and significantly outperforms greedy inducers when more time is available. A comparison of IIDT to several modern decision tree learners showed it to be superior.

AAAI Conference 2006 Conference Paper

When a Decision Tree Learner Has Plenty of Time

• Saher Esmeir

The majority of the existing algorithms for learning decision trees are greedy—a tree is induced top-down, making locally optimal decisions at each node. In most cases, however, the constructed tree is not globally optimal. Furthermore, the greedy algorithms require a fixed amount of time and are not able to generate a better tree if additional time is available. To overcome this problem, we present a lookahead-based algorithm for anytime induction of decision trees which allows trading computational speed for tree quality. The algorithm uses a novel strategy for evaluating candidate splits; a stochastic version of ID3 is repeatedly invoked to estimate the size of the tree in which each split results, and the split that minimizes the expected size is preferred. Experimental results indicate that for several hard concepts, our proposed approach exhibits good anytime behavior and yields significantly better decision trees when more time is available.

ICML Conference 2004 Conference Paper

Lookahead-based algorithms for anytime induction of decision trees

• Saher Esmeir
• Shaul Markovitch