Approximate inference in structured instances with noisy categorical observations
We study the problem of recovering the latent ground truth labeling of a structured instance
with categorical random variables in the presence of noisy observations. We present a new
approximate algorithm for graphs with categorical variables that achieves low Hamming
error in the presence of noisy vertex and edge observations. Our main result shows a
logarithmic dependency of the Hamming error to the number of categories of the random
variables. Our approach draws connections to correlation clustering with a fixed number of …
with categorical random variables in the presence of noisy observations. We present a new
approximate algorithm for graphs with categorical variables that achieves low Hamming
error in the presence of noisy vertex and edge observations. Our main result shows a
logarithmic dependency of the Hamming error to the number of categories of the random
variables. Our approach draws connections to correlation clustering with a fixed number of …
[PDF][PDF] Approximate Inference in Structured Instances with Noisy Categorical Observations–Supplementary Material
To apply the Bernstein inequality, we must consider Lu, v− p. We have E [Lu, v− p]= 0 and σ2
(Lu, v− p)= p (1− p). We must also have that the random variables are constrained. We know
that| Lu, v− p|≤ max {1− p, p} and p< 1/2 so| Lu, v− p|≤ 1− p. Now, we apply the Bernstein
inequality:
(Lu, v− p)= p (1− p). We must also have that the random variables are constrained. We know
that| Lu, v− p|≤ max {1− p, p} and p< 1/2 so| Lu, v− p|≤ 1− p. Now, we apply the Bernstein
inequality:
以上显示的是最相近的搜索结果。 查看全部搜索结果