DeepAI AI Chat
Log In Sign Up

Exact Inference in High-order Structured Prediction

by   Chuyang Ke, et al.
Purdue University

In this paper, we study the problem of inference in high-order structured prediction tasks. In the context of Markov random fields, the goal of a high-order inference task is to maximize a score function on the space of labels, and the score function can be decomposed into sum of unary and high-order potentials. We apply a generative model approach to study the problem of high-order inference, and provide a two-stage convex optimization algorithm for exact label recovery. We also provide a new class of hypergraph structural properties related to hyperedge expansion that drives the success in general high-order inference problems. Finally, we connect the performance of our algorithm and the hyperedge expansion property using a novel hypergraph Cheeger-type inequality.


page 1

page 2

page 3

page 4


Partial Inference in Structured Prediction

In this paper, we examine the problem of partial inference in the contex...

Efficient optimization for Hierarchically-structured Interacting Segments (HINTS)

We propose an effective optimization algorithm for a general hierarchica...

Exact Partitioning of High-order Planted Models with a Tensor Nuclear Norm Constraint

We study the problem of efficient exact partitioning of the hypergraphs ...

Truncated Max-of-Convex Models

Truncated convex models (TCM) are a special case of pairwise random fiel...

Joint Information Extraction with Cross-Task and Cross-Instance High-Order Modeling

Prior works on Information Extraction (IE) typically predict different t...

Texture Modelling with Nested High-order Markov-Gibbs Random Fields

Currently, Markov-Gibbs random field (MGRF) image models which include h...

A Deep Learning Model for Structured Outputs with High-order Interaction

Many real-world applications are associated with structured data, where ...