Hao-Jun Michael Shi

TL;DR: A state-of-the-art deep learning recommendation model (DLRM) is developed and its implementation in both PyTorch and Caffe2 frameworks is provided and a specialized parallelization scheme utilizing model parallelism on the embedding tables to mitigate memory constraints while exploiting data parallelism to scale-out compute from the fully-connected layers is designed.

TL;DR: This article presented a new version of the L-BFGS algorithm that combines three basic components -progressive batching, a stochastic line search, and stable quasi-Newton updating -and performed well on training logistic regression and deep neural networks.

TL;DR: This work proposes a novel approach for reducing the embedding size in an end-to-end fashion by exploiting complementary partitions of the category set to produce a unique embedding vector for each category without explicit definition.

TL;DR: This monograph presents a class of algorithms called coordinate descent algorithms for mathematicians, statisticians, and engineers outside the field of optimization due to their effectiveness in solving large-scale optimization problems in machine learning, compressed sensing, image processing, and computational statistics.

TL;DR: This paper proposed a new version of the L-BFGS algorithm that combines three basic components -progressive batching, stochastic line search, and stable quasi-Newton updating -and performs well on training logistic regression and deep neural networks.