Log-linear parsing models are often trained by optimizing likelihood, but we would prefer to optimise for a task-specific metric like Fmeasure. Softmax-margin is a convex objecti...
We are using bandit-based adaptive operator selection while autotuning parallel computer programs. The autotuning, which uses evolutionary algorithm-based stochastic sampling, take...
Maciej Pacula, Jason Ansel, Saman P. Amarasinghe, ...
Workload, platform, and available resources constitute a parallel program’s execution environment. Most parallelization efforts statically target an anticipated range of environ...
Arun Raman, Ayal Zaks, Jae W. Lee, David I. August
We propose a scheme for congestion avoidance in networks using a connectionless protocol at the network layer. The scheme uses a minimal amount of feedback from the network to the ...
One of the major challenges in stereo matching is to handle partial occlusions. In this paper, we introduce the Outlier Confidence (OC) which dynamically measures how likely one pi...