Behaviorally consistent optimal stopping rules

Optimal Stopping Rules for Directionally Reinforced Processes

Optimal Stopping Rules for Sequential Hypothesis Testing

Suppose that we are given sample access to an unknown distribution p over n elements and an explicit distribution q over the same n elements. We would like to reject the null hypothesis “p = q” after seeing as few samples as possible, when p 6= q, while we never want to reject the null, when p = q. Well-known results show that Θ( √ n/ 2) samples are necessary and sufficient for distinguishing w...

Optimal stopping rules for active learning

Active learning algorithms aim to minimise the amount of labelled data used to learn a target concept. However, there is no formal framework for expressing the trade-off between needed accuracy and the cost of label acquisition, rendering the objective evaluation of algorithms problematic and the development of criteria for deciding when to terminate data acquisition impossible. This paper aims...

Constructing Time-Homogeneous Generalised Diffusions Consistent with Optimal Stopping Values

Consider a set of discounted optimal stopping problems for a one-parameter family of objective functions and a fixed diffusion process, started at a fixed point. A standard problem in stochastic control/optimal stopping is to solve for the problem value in this setting. In this article we consider an inverse problem; given the set of problem values for a family of objective functions, we aim to...

Efficient Stopping Rules

The importance of sampling methods in machine learning is growing due to an ever-increasing number of datasets containing millions of records of biological, medical, or other types of data. Such datasets are often beyond the reach of many standard machine learning techniques because of high computational or space complexity of the algorithms. When making even a single pass through the data is p...