H
Hao-Jun Michael Shi
Researcher at Northwestern University
Publications - 17
Citations - 758
Hao-Jun Michael Shi is an academic researcher from Northwestern University. The author has contributed to research in topics: Compressed sensing & Broyden–Fletcher–Goldfarb–Shanno algorithm. The author has an hindex of 7, co-authored 15 publications receiving 420 citations. Previous affiliations of Hao-Jun Michael Shi include University of California, Los Angeles.
Papers
More filters
Posted Content
Deep Learning Recommendation Model for Personalization and Recommendation Systems
Maxim Naumov,Dheevatsa Mudigere,Hao-Jun Michael Shi,Jianyu Huang,Narayanan Sundaraman,Jongsoo Park,Xiaodong Wang,Udit Gupta,Carole-Jean Wu,Alisson Gusatti Azzolini,Dmytro Dzhulgakov,Andrey Mallevich,Ilia Cherniavskii,Yinghai Lu,Raghuraman Krishnamoorthi,Ansha Yu,Volodymyr Kondratenko,Stephanie Pereira,Xianjie Chen,Wenlin Chen,Vijay Rao,Bill Jia,Liang Xiong,Misha Smelyanskiy +23 more
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.
Proceedings Article
A Progressive Batching L-BFGS Method for Machine Learning
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.
Proceedings ArticleDOI
Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems
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.
Posted Content
A Primer on Coordinate Descent Algorithms
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.
Posted Content
A Progressive Batching L-BFGS Method for Machine Learning
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.