Efficient programmable learning to search.
Year: 2014
Type: preprint
Abstract: We improve “learning to search ” approaches to structured prediction in two ways. First, we show that the search space can be defined by an arbitrary imperative program, reducing the number of lines of code required to develop new structured prediction tasks by orders of magnitude. Second, we make structured prediction orders of magnitude faster through various algorithmic improvements. 1
Source: arXiv (Cornell University)
Authors: Hal Daumé, John Langford, Stéphane Ross
Institutions: Microsoft (United States), Google (United States)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1931054966
