DeepAI AI Chat
Log In Sign Up

Partial Inference in Structured Prediction

by   Chuyang Ke, et al.
Purdue University

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.


page 1

page 2

page 3

page 4


Exact inference in structured prediction

Structured prediction can be thought of as a simultaneous prediction of ...

Exact Inference in High-order Structured Prediction

In this paper, we study the problem of inference in high-order structure...

Fairness constraints can help exact inference in structured prediction

Many inference problems in structured prediction can be modeled as maxim...

Minimax bounds for structured prediction

Structured prediction can be considered as a generalization of many stan...

Tight Error Bounds for Structured Prediction

Structured prediction tasks in machine learning involve the simultaneous...

A Primal Condition for Approachability with Partial Monitoring

In approachability with full monitoring there are two types of condition...

Multi-Person Tracking by Multicut and Deep Matching

In [1], we proposed a graph-based formulation that links and clusters pe...