NeurIPS, the full name of the neural information processing system of the General Assembly (Conference and Workshop ON Neural Information Processing Systems) , since its birth in 1987 has been 32 years of history, has been much attention academia and industry. NeurIPS class A conference in the field of artificial intelligence, but also one of the most prestigious annual meeting of the artificial intelligence field.
According to official sources, this year NeurIPS Conference Paper Submission re-creation of a new high, received a total of 6743 Pian submission, eventually admitted 1428 papers, 36 Oral , admission rate of 21.2% .
The number of participants this year is also a new high, the total number of participants has exceeded 13,000 people, 9,000 people in attendance compared to last year increased by almost half. Due to excessive number of applicants. This year the conference organizers even changed the rules to grab votes, the "first come first served" principle change to "draw" principle.
Picture the scene:
NeurIPS officials announced the selection of the most interesting results of the award of outstanding papers.
It is noteworthy that , in addition to Outstanding Paper Award (Outstanding Paper Award) and classic Paper Award (Test of Time Award), this year the organizing committee also added a "new direction Outstanding Paper Award" in recognition of the "innovation-oriented future research way "aspects of outstanding researchers.
Outstanding Paper Award
论文名称：Distribution-Independent PAC Learning of Halfspaces with Massart Noise
Author: Ilias Diakonikolas, Themis Gouleakis, Christos Tzamos
institutions: Madison, the University of Wisconsin Max Planck
paper Address: https://papers.nips.cc/paper/8722-distribution-independent-pac-learning-of-halfspaces- with-massart-noise
Outstanding New Directions Paper Award
Thesis Title: Uniform convergence may be unable to explain
generalization in deep learning Author: Vaishnavh Nagarajan, J Zico Kolter.
Agency: Carnegie Mellon University, Center for Artificial Intelligence Bosch
Paper Address: https://papers.nips.cc/paper/8722 -distribution-independent-pac-learning- of-halfspaces-with-massart-noise
Outstanding Paper Award Honorable Mention
Thesis Title: Nonparametric density estimation & convergence of GANs
under Besov IPM losses Author: Ananya Uppal, Shashank Singh, Barnabás Póczos
institutions: Carnegie Mellon University
dissertation Address: https://papers.nips.cc/paper/9109-nonparametric-density -estimation-convergence-rates-for- gans-under-besov-ipm-losses
Reviewers think this paper for non-parametric estimates have far-reaching implications of GAN and research work.
Thesis Title: Fast and Accurate Least-Mean- Squares Solvers
Author: Alaa Maalouf, Ibrahim Jubran, Dan Feldman
institutions: the University of Haifa in Israel
dissertation addresses: https://papers.nips.cc/paper/9040-fast-and-accurate -least-mean-squares-solvers
Outstanding Paper Award honorable mention new direction
Thesis Title: Putting An End to End-to -End: Gradient-Isolated Learning of Representations
Author: Sindy Löwe, Peter O'Connor, Bastiaan Veeling
institutions: the University of Amsterdam
Papers Address: https://papers.nips.cc/paper/ 8568-putting-an-end- to-end-to-end-gradient-isolated-learning-of-representations
Thesis Title: Scene Representation Networks: Continuous 3D- Structure-Aware Neural Scene Representations
Author: Vincent Sitzmann, Michael Zollhöfer, Gordon Wetzstein
institutions: Stanford University
dissertation addresses: https://papers.nips.cc/paper/8396-scene-representation -networks-continuous-3d-structure- aware-neural-scene-representations
Classic Paper Award (Test of Time Award)
Last year, NeurIPS Assembly classic paper award issued to NEC and Google researchers. Research Paper Award granted to the classic principle is "an important contribution to the lasting impact and broad appeal," this session from 18 in 2009 NIPS of the most cited papers in the highest elected continuing influence, outstanding contributions to the field of study .
In the end, this year's award NIPS 2009 paper "Dual Averaging Method for Regularized Stochastic Learning and Online Optimization" and its author, Microsoft's chief researcher Lin Xiao. Lin Xiao studied at Beijing University of Aeronautics and Astronautics at Stanford University, since 2006, worked at Microsoft Research.
Papers Link: https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/xiao10JMLR.pdf
Finally, NeurIPS also announced the venue year after the General Assembly: After continue to be held next in Vancouver next year, NeurIPS 2021 will move to the Australian city of Sydney.
