When dense matrix computations are too large to fit in cache, previous research proposes tiling to reduce or eliminate capacity misses. This paper presents a new algorithm for ch...
Abstract Most ranking algorithms are based on the optimization of some loss functions, such as the pairwise loss. However, these loss functions are often different from the criter...
algorithms as networks of modules. The data flow architecture is popular because of the flexibility of mixing calculation modules with display modules, and because of its easy grap...
William L. Hibbard, Charles R. Dyer, Brian E. Paul
Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...
Michael Collins, Amir Globerson, Terry Koo, Xavier...
The most expensive geometric operation in image synthesis is visibility determination. Classically this is solved with hidden surface removal algorithms that render only the parts...