Zishen Wan (@ZishenW) profile picture

PhD student @GeorgiaTech | Master @Harvard | Working on VLSI, Computer Architecture and AI

Cambridge, MA
Joined December 2018
If you are interested in speeding up RL training, welcome to check out our recent paper at #TMLR. Title: QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learning Paper: lnkd.in/gRsvjgix Code: lnkd.in/gNne5ftG
Very excited to share this work that with a simple idea reduces carbon footprint of training RL model by up to 3.8x w/ @Srivatsan91 , @profvjreddi, and other collaborators from @hseas and @DeepMind.
2
Thanks @Aleksandra, @profvjreddi, @gbarthmaron for your guidance. Very excited to share our work on applying quantization to speed up RL and reducing carbon footprint. Thanks to my co-authors Max Lam, @sharad24sc,@ZishenW.
Very excited to share this work that with a simple idea reduces carbon footprint of training RL model by up to 3.8x w/ @Srivatsan91 , @profvjreddi, and other collaborators from @hseas and @DeepMind.
2
4
Welcome to attend and look forward to seeing you all!
C-BRIC researchers and partners can join Zishen Wan for a talk on "Analyzing and Improving Fault Tolerance of Autonomous Navigation Systems" Thurs., Aug. 26 at 11:00am ET/8:00am PT.
1
Glad to announce my new (first) book 'Robotic Computing on FPGAs'! It's published as Computer Architecture Series by @MorganClaypool. Thanks my collaborators Dr. Shaoshan Liu (PerceptIn), Dr. Bo Yu (PerceptIn), and Prof. Yu Wang (Tsinghua). sigarch.org/other-announceme…
1
5
Please join Session-10a (Best of CAL @IEEECAL) at HPCA'21 @HpcaArchConf starting at 12:30 ET Today! Our paper 'The Sky Is Not the Limit: A Visual Performance Model for Cyber-Physical Co-Design in Autonomous Machines' will be presented! zishenwan.github.io/publicat…
5