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...
In previous work, we have introduced functional strategies, that is, first-class generic functions that can traverse into terms of any type while mixing uniform and type-specific ...
Existing methods place data or code in scratchpad memory, i.e., SPM by either relying on heuristics or resorting to integer programming or mapping it to a graph coloring problem. ...
The running time of many applications is dominated by the cost of memory operations. To optimize such applications for a given platform, it is necessary to have a detailed knowled...
Most data-mining techniques seek a single model that optimizes an objective function with respect to the data. In many real-world applications several models will equally optimize...