Learn More
Active machine learning algorithms are used when large numbers of unlabeled examples are available and getting labels for them is costly (e.g. requiring consulting a human expert). Many conventional active learning algorithms focus on refining the decision boundary, at the expense of exploring new regions that the current hypothesis misclassifies. We(More)
This paper is concerned with model reduction for complex Markov chain models. The Kullback–Leibler divergence rate is employed as a metric to measure the difference between the Markov model and its approximation. For a certain relaxation of the bi-partition model reduction problem, the solution is shown to be characterized by an associated eigenvalue(More)
In active learning, a machine learning algorithm is given an unlabeled set of examples U, and is allowed to request labels for a relatively small subset of U to use for training. The goal is then to judiciously choose which examples in U to have labeled in order to optimize some performance criterion, e.g. classification accuracy. We study how active(More)
Significant changes in the instance distribution or associated cost function of a learning problem require one to reoptimize a previously-learned classifier to work under new conditions. We study the problem of reoptimizing a multi-class classifier based on its ROC hypersurface and a matrix describing the costs of each type of prediction error. For a binary(More)
This paper is concerned with an informationtheoretic framework to aggregate a large-scale Markov chain to obtain a reduced order Markov model. The KullbackLeibler (K-L) divergence rate is employed as a metric to measure the distance between two stationary Markov chains. Model reduction is obtained by considering an optimization problem with respect to this(More)
The increasing evidences have revealed that microRNAs (miRNAs) play significant role in nutrient stress response. Previously, miR399 was documented to be induced by phosphorus (P) starvation and involved in regulating P starvation responses. To further investigate the function of miR399 in rice (Oryza sativa L.), we performed GeneChip analysis with OsmiR399(More)
We explore the problem of budgeted machine learning, in which the learning algorithm has free access to the training examples' labels but has to pay for each attribute that is specified. This learning model is appropriate in many areas, including medical applications. We present new algorithms for choosing which attributes to purchase of which examples in(More)
This paper is concerned with model reduction for a complex Markov chain using state aggregation. The work is motivated in part by the need for reduced order estimation of occupancy in a building during evacuation. We propose and compare two distinct model reduction techniques, each of which is based on the potential matrix for the Markov semigroup. The(More)
The personalization of treatment via biomarkers and other risk categories has drawn increasing interest among clinical scientists. Personalized treatment strategies can be learned using data from clinical trials, but such trials are very costly to run. This paper explores the use of active learning techniques to design more efficient trials, addressing(More)