Approximate algorithm for categorical structured inference with noisy observations achieves Hamming error logarithmic in the number of categories, generalizing prior binary-label results.
We assume that k is such that one can obtain a labeling for G that is edge-compatible with X by traversing G
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Approximate Inference in Structured Instances with Noisy Categorical Observations
Approximate algorithm for categorical structured inference with noisy observations achieves Hamming error logarithmic in the number of categories, generalizing prior binary-label results.