Jerry Ma
Jerry joined the FAIR lab after a machine learning internship at Facebook. His research interests include economic theory, security, and AI, specifically in reinforcement learning and optimization. Jerry earned an A.B. in economics and the classics from Harvard University.
Jerry's Work
Jerry's Publications
January 05, 2021
RESEARCH
Order-Aware Generative Modeling Using the 3D-Craft Dataset
Research on 2D and 3D generative models typically focuses on the final artifact being created, e.g., an image or a 3D structure. Unlike 2D image generation, the generation of 3D objects in the real world is commonly constrained by the process…
Zhuoyuan Chen, Demi Guo, Tong Xiao, Saining Xie, Xinlei Chen, Haonan Yu, Jonathan Gray, Kavya Srinet, Haoqi Fan, Jerry Ma, Charles R. Qi, Shubham Tulsiani, Arthur Szlam, Larry Zitnick,
January 05, 2021
January 05, 2021
RESEARCH
COMPUTER VISION
ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero
The AlphaGo, AlphaGo Zero, and AlphaZero series of algorithms are remarkable demonstrations of deep reinforcement learning’s capabilities, achieving superhuman performance in the complex game of Go with progressively increasing autonomy.…
Yuandong Tian, Jerry Ma, Qucheng Gong, Shubho Sengupta, Zhuoyuan Chen, James Pinkerton, Larry Zitnick,
January 05, 2021
January 05, 2021
RESEARCH
COMPUTER VISION
Quasi-Hyperbolic Momentum and Adam for Deep Learning
Momentum-based acceleration of stochastic gradient descent (SGD) is widely used in deep learning. We propose the quasi-hyperbolic momentum algorithm (QHM) as an extremely simple alteration of momentum SGD, averaging a plain SGD step with a…
January 05, 2021
