Adaptive Sampled Softmax with Kernel Based Sampling
international conference on machine learning, 2018.
Softmax is the most commonly used output function for multiclass problems and is widely used in areas such as vision, natural language processing, and recommendation. A softmax model has linear costs in the number of classes which makes it too expensive for many real-world problems. A common approach to speed up training involves sampling...More
PPT (Upload PPT)