Leadership, entrepreneurship, and AI insights

  • LinkedIn Social Icon
  • YouTube Social  Icon
  • Twitter Social Icon
  • Facebook Social Icon
  • Instagram Social Icon
  • SoundCloud Social Icon
  • Spotify Social Icon

© 2018 by Robin.ly. Provided by CrossCircles Inc.

[NeurIPS 2019 Highlight] Jingwei Liang @ Cambridge : Multipliers and Adaptive Acceleration

Updated: Jan 30


This episode is an interview with Jingwei Liang from University of Cambridge, discussing highlights from his paper, "Trajectory of Alternating Direction Method of Multipliers and Adaptive Acceleration," accepted as an oral presentation at NeurIPS 2019 Conference.


Jingwei is currently a Leverhulme Early Career Fellowship at Department of Applied Mathematics and Theoretical Physics University of Cambridge. He's also a member of the group Cambridge Image Analysis. Jingwei received my Ph.D. from ENSICAEN and University of Caen Normandy advised by Jalal Fadili and Gabriel Peyré. Prior to that, he obtained my bachlor degree in Electrical & Information Engineering from Nanjing University of Posts and Telecommunications.



Interview with Robin.ly:




Robin.ly is a content platform dedicated to helping engineers and researchers develop leadership, entrepreneurship, and AI insights to scale their impacts in the new tech era.


Subscribe to our newsletter to stay updated for more NeurIPS interviews and inspiring AI talks:


Paper At A Glance


The alternating direction method of multipliers (ADMM) is one of the most widely used first-order optimisation methods in the literature owing to its simplicity, flexibility and efficiency. Over the years, numerous efforts are made to improve the performance of the method, such as the inertial technique. By studying the geometric properties of ADMM, we discuss the limitations of current inertial accelerated ADMM and then present and analyze an adaptive acceleration scheme for the method. Numerical experiments on problems arising from image processing, statistics and machine learning demonstrate the advantages of the proposed acceleration approach.


[Poster]

[Full Paper]