SYSTEMS AND METHODS FOR ROBUST LARGE-SCALE MACHINE LEARNING

The present disclosure provides a new scalable coordinate descent (SCD) algorithm and associated system for generalized linear models whose convergence behavior is always the same, regardless of how much SCD is scaled out and regardless of the computing environment. This makes SCD highly robust and enables it to scale to massive datasets on low-cost commodity servers. According to one aspect, by using a natural partitioning of parameters into blocks, updates can be performed in parallel a block at a time without compromising convergence. Experimental results on a real advertising dataset are used to demonstrate SCD's cost effectiveness and scalability. 本公开提供了用于广义线性模型的新的可缩放坐标下降(SCD)算法和关联系统，不管SCD被横向扩展多少并且不管计算环境如何，其收敛行为始终相同。这使得SCD高度稳健并且使得其能够缩放到低成本商用服务器上的大规模数据集。根据个方面，通过使用将参数自然分区成块，可以在不折中收敛的情况下次块地并行执行更新。对实际广告数据集的实验结果用于证明SCD的成本效益和可缩放性。