Learning from Ambiguous and Misspecified Models

Active Learning for Misspecified Models

Active learning is the problem in supervised learning to design the locations of training input points so that the generalization error is minimized. Existing active learning methods often assume that the model used for learning is correctly specified, i.e., the learning target function can be expressed by the model at hand. In many practical situations, however, this assumption may not be fulf...

Active learning for misspecified generalized linear models

Active learning refers to algorithmic frameworks aimed at selecting training data points in order to reduce the number of required training data points and/or improve the generalization performance of a learning method. In this paper, we present an asymptotic analysis of active learning for generalized linear models. Our analysis holds under the common practical situation of model misspecificat...

Socratic Learning: Correcting Misspecified Generative Models using Discriminative Models

A challenge in training discriminative models like neural networks is obtaining enough labeled training data. Recent approaches use generative models to combine weak supervision sources, like user-defined heuristics or knowledge bases, to label training data. Prior work has explored learning accuracies for these sources even without ground truth labels, but they assume that a single accuracy pa...

Learning from Ambiguous Examples

Learning From Ambiguous Examples

Current inductive learning systems are not well suited to learning from ambiguous examples. We say that an example is ambiguous if it has multiple interpretations, only one of which may be valid. Some domains in which ambiguous learning problems can be found are natural language processing (NLP) and computer vision. An example of an ambiguous training instance with two interpretations is shown ...