Partial Inference in Structured Prediction
Machine Learning
2023-06-08 v1 Machine Learning
Abstract
In this paper, we examine the problem of partial inference in the context of structured prediction. Using a generative model approach, we consider the task of maximizing a score function with unary and pairwise potentials in the space of labels on graphs. Employing a two-stage convex optimization algorithm for label recovery, we analyze the conditions under which a majority of the labels can be recovered. We introduce a novel perspective on the Karush-Kuhn-Tucker (KKT) conditions and primal and dual construction, and provide statistical and topological requirements for partial recovery with provable guarantees.
Cite
@article{arxiv.2306.03949,
title = {Partial Inference in Structured Prediction},
author = {Chuyang Ke and Jean Honorio},
journal= {arXiv preprint arXiv:2306.03949},
year = {2023}
}