DeepAI AI Chat
Log In Sign Up

Resource Constrained Structured Prediction

by   Tolga Bolukbasi, et al.

We study the problem of structured prediction under test-time budget constraints. We propose a novel approach applicable to a wide range of structured prediction problems in computer vision and natural language processing. Our approach seeks to adaptively generate computationally costly features during test-time in order to reduce the computational cost of prediction while maintaining prediction performance. We show that training the adaptive feature generation system can be reduced to a series of structured learning problems, resulting in efficient training using existing structured learning algorithms. This framework provides theoretical justification for several existing heuristic approaches found in literature. We evaluate our proposed adaptive system on two structured prediction tasks, optical character recognition (OCR) and dependency parsing and show strong performance in reduction of the feature costs without degrading accuracy.


page 1

page 2

page 3

page 4


Adaptive Classification for Prediction Under a Budget

We propose a novel adaptive approximation approach for test-time resourc...

Localized Structured Prediction

Key to structured prediction is exploiting the problem structure to simp...

Efficient Learning by Directed Acyclic Graph For Resource Constrained Prediction

We study the problem of reducing test-time acquisition costs in classifi...

Peri-Diagnostic Decision Support Through Cost-Efficient Feature Acquisition at Test-Time

Computer-aided diagnosis (CADx) algorithms in medicine provide patient-s...

Learning Constraints for Structured Prediction Using Rectifier Networks

Various natural language processing tasks are structured prediction prob...

Adaptive Learning for the Resource-Constrained Classification Problem

Resource-constrained classification tasks are common in real-world appli...

Graph Structured Prediction Energy Networks

For joint inference over multiple variables, a variety of structured pre...