Robuta

https://openreview.net/forum?id=1SvVuUNN5I Bi-directional Masks for Efficient N:M Sparse Training | OpenReview We focus on addressing the dense backward propagation issue for training efficiency of N:M fine-grained sparsity that preserves at most N out of M consecutive... n m sparse training bi directional masks https://collaborate.princeton.edu/en/publications/pixelated-butterfly-simple-and-efficient-sparse-training-for-neur/ PIXELATED BUTTERFLY: SIMPLE AND EFFICIENT SPARSE TRAINING FOR NEURAL NETWORK MODELS - Princeton... sparse training neural network pixelated butterfly simple https://scienceportal.tecnalia.com/en/publications/collaborative-training-of-heterogeneous-reinforcement-learning-ag/ Collaborative training of heterogeneous reinforcement learning agents in environments with sparse... reinforcement learning collaborative training agents environments