Jiyan Yang

Jiyan is a research scientist at Facebook AI Research (FAIR), working on machine learning problems in the ranking and recommendation domain. His focus includes large-scale distributed training algorithms, quantization algorithms, and deep learning modeling. Jiyan earned his Ph.D. from Stanford University, where his thesis used randomized linear algebra as a tool to develop optimization and machine learning algorithms for large-scale data applications.

Jiyan's Publications

April 07, 2020

RESEARCH

NLP

Training with Low-precision Embedding Tables

Starting from the success of Glove and Word2Vec in natural language processing, continuous representations are widely deployed in many other domain of applications. These applications span over encoding textual information to modeling user and…

Jian Zhang, Jiyan Yang, Hector Yuen,

April 07, 2020