Having access to massive amounts of data does not necessarily imply that induction algorithms must use them all. Samples often provide the same accuracy with far less computational cost. However, the correct sample size rarely is obvious. We analyze methods for progressive sampling--- using progressively larger samples as long as model accuracy improves. We explore several notions of efficient progressive sampling. We analyze efficiency relative to induction with all instances; we show that a simple, geometric sampling schedule is asymptotically optimal, and we describe how best to take into account prior expectations of accuracy convergence. We then describe the issues involved in instantiating an efficient progressive sampler, including how to detect convergence. Finally, we provide empirical results comparing a variety of progressive sampling methods. We conclude that progressive sampling can be remarkably efficient. 1 Introduction Induction algorithms face competing requiremen...

This paper extends the currently accepted model of inductive bias by identifying six categories of bias and separates inductive bias from the policy for its selection (the inductive policy). We analyze existing "blas selection " systems, examining the similarities and differences in their inductive policies, and idemify three techniques useful for building inductive policies. We then present a framework for representing and automaticaIly selecting a wide variety of biases and describe experiments with an instantiation of the framework addressing various pragmatic tradeoffs of time, space, accuracy, and the cost oferrors. The experiments show that a common framework can be used to implement policies for a variety of different types of blas selection, such as parameter selection, term selection, and example selection, using similar techniques. The experiments also show that different tradeoffs can be made by the implementation of different policies; for example, from the same data different rule sets can be learned based on different tradeoffs of accuracy versus the cost of erroneous predictions.

: Each year, one of the explicit challenges for the KDD research community is to develop methods that facilitate the use of inductive learning algorithms for mining very large databases. By collecting, categorizing, and summarizing past work on scaling up inductive learning algorithms, this paper serves to establish a common ground for researchers addressing the challenge. We begin with a discussion of important, but often tacit, issues related to scaling up learning algorithms. We highlight similarities among methods by categorizing them into three main approaches. For each approach, we then describe, compare, and contrast the different constituent methods, drawing on specific examples from the published literature. Finally, we use the preceding analysis to suggest how one should proceed when dealing with a large problem, and where future research efforts should be focused. Primary contact: Foster Provost NYNEX Science and Technology, 400 Westchester Avenue, White Plains, NY 10604 em...

We present a new efficient algorithm for obtaining utilitarian optimal solutions to Disjunctive Temporal Problems with Preferences (DTPPs). The previous state-of-the-art system achieves temporal preference optimization using a SAT formulation, with its creators attributing its performance to advances in SAT solving techniques. We depart from the SAT encoding and instead introduce the Valued DTP (VDTP). In contrast to the traditional semiring-based formalism that annotates legal tuples of a constraint with preferences, our framework instead assigns elementary costs to the constraints themselves. After proving that the VDTP can express the same set of utilitarian optimal solutions as the DTPP with piecewise-constant preference functions, we develop a method for achieving weighted constraint satisfaction within a meta-CSP search space that has traditionally been used to solve DTPs without preferences. This allows us to directly incorporate several powerful techniques developed in previous decision-based DTP literature. Finally, we present empirical results demonstrating that an implementation of our approach consistently outperforms the SAT-based solver by orders of magnitude.

Flexible computation is a general framework for decision making under limited computational resources. It enables an agent to allocate limited computational resources to maximize its overall performance or utility. In this paper, we present a strategy for flexible computation, which we call iterative state-space reduction. The main ideas are to reduce a problem space that is difficult to search to one that is relatively easy to explore, to use the optimal solution from the reduced space as an approximate solution to the original problem, and to iteratively apply multiple reductions to progressively find better solutions.

Abstract not found