Sciweavers

397 search results - page 27 / 80
» An empirical study of optimizations in YOGI
Sort
View
INTERSPEECH
2010
13 years 2 months ago
Combining many alignments for speech to speech translation
Alignment combination (symmetrization) has been shown to be useful for improving Machine Translation (MT) models. Most existing alignment combination techniques are based on heuri...
Sameer Maskey, Steven J. Rennie, Bowen Zhou
JMLR
2010
164views more  JMLR 2010»
13 years 2 months ago
Solving the Uncapacitated Facility Location Problem Using Message Passing Algorithms
The Uncapacitated Facility Location Problem (UFLP) is one of the most widely studied discrete location problems, whose applications arise in a variety of settings. We tackle the U...
Nevena Lazic, Brendan J. Frey, Parham Aarabi
ICMLA
2010
13 years 5 months ago
Robust Learning for Adaptive Programs by Leveraging Program Structure
Abstract--We study how to effectively integrate reinforcement learning (RL) and programming languages via adaptation-based programming, where programs can include non-deterministic...
Jervis Pinto, Alan Fern, Tim Bauer, Martin Erwig
PE
2011
Springer
214views Optimization» more  PE 2011»
13 years 2 months ago
Time-bounded reachability in tree-structured QBDs by abstraction
Structured QBDs by Abstraction Daniel Klink, Anne Remke, Boudewijn R. Haverkort, Fellow, IEEE, and Joost-Pieter Katoen, Member, IEEE Computer Society —This paper studies quantita...
Daniel Klink, Anne Remke, Boudewijn R. Haverkort, ...
ISNN
2005
Springer
14 years 1 months ago
One-Bit-Matching ICA Theorem, Convex-Concave Programming, and Combinatorial Optimization
Recently, a mathematical proof is obtained in (Liu, Chiu, Xu, 2004) on the so called one-bit-matching conjecture that all the sources can be separated as long as there is an one-to...
Lei Xu