Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time
This work addresses the challenge of efficient and robust parameter learning in structured prediction, though it appears incremental as it builds on existing MAP perturbation frameworks.
The paper tackles the problem of learning parameters for MAP perturbation models in structured prediction, proposing a polynomial-time randomized algorithm that guarantees generalization under certain conditions.
MAP perturbation models have emerged as a powerful framework for inference in structured prediction. Such models provide a way to efficiently sample from the Gibbs distribution and facilitate predictions that are robust to random noise. In this paper, we propose a provably polynomial time randomized algorithm for learning the parameters of perturbed MAP predictors. Our approach is based on minimizing a novel Rademacher-based generalization bound on the expected loss of a perturbed MAP predictor, which can be computed in polynomial time. We obtain conditions under which our randomized learning algorithm can guarantee generalization to unseen examples.