Metric Learning via Cross-Validation

DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer

We have witnessed rapid evolution of deep neural network architecture design in the past years. These latest progresses greatly facilitate the developments in various areas such as computer vision and natural language processing. However, along with the extraordinary performance, these state-of-theart models also bring in expensive computational cost. Directly deploying these models into applic...

Error rate estimation via cross-validation and learning curve theory

Critical Points in Assessing Learning Performance via Cross-validation

Quality assessment of learning methods is essential when adapting them to different tasks, introducing new algorithms, developing the existing ones, or tracking the learning improvements over time. Obtaining realistic results is, however, complicated. In this paper, we clarify this by addressing performance evaluation measure and method selection, with a main focus on combining the AUC measure ...

Learning dynamic Bayesian network models via cross-validation

We study cross-validation as a scoring criterion for learning dynamic Bayesian network models that generalize well. We argue that cross-validation is more suitable than the Bayesian scoring criterion for one of the most common interpretations of generalization. We confirm this by carrying out an experimental comparison of cross-validation and the Bayesian scoring criterion, as implemented by th...

Metric Learning via Normal Mixtures

Natural learners rarely have access to perfectly labeled data { motivating the study of unsupervised learning in an attempt to assign labels. An alternative viewpoint, which avoids the issue of labels entirely , has as the learner's goal the discovery of an eeective metric with which similarity judgments can be made. We refer to this paradigm as metric learning. EEective classiication, for exam...