DeepAI AI Chat
Log In Sign Up

Train and Test Tightness of LP Relaxations in Structured Prediction

by   Ofer Meshi, et al.

Structured prediction is used in areas such as computer vision and natural language processing to predict structured outputs such as segmentations or parse trees. In these settings, prediction is performed by MAP inference or, equivalently, by solving an integer linear program. Because of the complex scoring functions required to obtain accurate predictions, both learning and inference typically require the use of approximate solvers. We propose a theoretical explanation to the striking observation that approximations based on linear programming (LP) relaxations are often tight on real-world instances. In particular, we show that learning with LP relaxed inference encourages integrality of training instances, and that tightness generalizes from train to test data.


page 1

page 2

page 3

page 4


Beyond Perturbation Stability: LP Recovery Guarantees for MAP Inference on Noisy Stable Instances

Several works have shown that perturbation stable instances of the MAP i...

LP-SparseMAP: Differentiable Relaxed Optimization for Sparse Structured Prediction

Structured prediction requires manipulating a large number of combinator...

Learning to Reformulate for Linear Programming

It has been verified that the linear programming (LP) is able to formula...

Efficient Algorithms for Global Inference in Internet Marketplaces

Matching demand to supply in internet marketplaces (e-commerce, ride-sha...

Alpha-expansion is Exact on Stable Instances

Approximate algorithms for structured prediction problems---such as the ...

Compact Relaxations for MAP Inference in Pairwise MRFs with Piecewise Linear Priors

Label assignment problems with large state spaces are important tasks es...

Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers

Formal verification of neural networks (NNs) is a challenging and import...