For labels taking values in a finite metric space, we introduce techniques new to weak supervision based on pseudo-Euclidean embeddings andtensor decompositions, providing anearly-consistent noise rate estimator.

For labels taking values in a finite metric space, we introduce techniques new to weak supervision based on pseudo-Euclidean embeddings andtensor decompositions, providing anearly-consistent noise rate estimator.

Structured prediction is the task of predicting an output which itself contains internal structure. As an example, consider the problem of image segmentation.

However, in reality, this may not always be the case.

We begin by providing online mistake bounds and P AC sample complexity in these scenarios for ball manipulations.

Neural Information Processing Systems http://nips.cc/