IEEE ICASSP 2022

2022 IEEE International Conference on Acoustics, Speech and Signal Processing

7-13 May 2022
  • Virtual (all paper presentations)
22-27 May 2022
  • Main Venue: Marina Bay Sands Expo & Convention Center, Singapore
27-28 October 2022
  • Satellite Venue: Crowne Plaza Shenzhen Longgang City Centre, Shenzhen, China

ICASSP 2022
MLSP-29.6

AdaPID: An Adaptive PID Optimizer for Training Deep Neural Networks

Boxi Weng, Jian Sun, Gang Wang, School of Automation, Beijing Institute of Technology, China; Alireza Sadeghi, Dept. of Electrical and Computer Engineering, University of Minnesota, United States of America

Session:
Signal Processing Theory and Methods

Track:
Machine Learning for Signal Processing

Location:
Gather Area H

Presentation Time:
Tue, 10 May, 22:00 - 22:45 China Time (UTC +8)
Tue, 10 May, 14:00 - 14:45 UTC

Session Chair:
Yang Liu, Meta, Reality Lab
Presentation
Discussion
Resources
Session MLSP-29
MLSP-29.1: APPLYING DIFFERENTIAL PRIVACY TO TENSOR COMPLETION
Zheng Wei, Zhengpin Li, Jian Wang, Fudan University, China; Xiaojun Mao, Shanghai Jiao Tong University, China
MLSP-29.2: LOW-COMPLEXITY ATTENTION MODELLING VIA GRAPH TENSOR NETWORKS
Yao Lei Xu, Kriton Konstantinidis, Shengxi Li, Danilo P. Mandic, Imperial College London, United Kingdom of Great Britain and Northern Ireland; Ljubiša Stanković, University of Montenegro, Montenegro
MLSP-29.3: AN ACCELERATED RANK-(L,L,1,1) BLOCK TERM DECOMPOSITION OF MULTI-SUBJECT FMRI DATA UNDER SPATIAL ORTHONORMALITY CONSTRAINT
Li-Dan Kuang, Biao Wang, Hao-Peng Zhang, Jianming Zhang, Wenjun Li, Feng Li, Changsha University of Science and Technology, China; Qiu-Hua Lin, Dalian University of Technology, China; Vince D. Calhoun, Georgia State University, China
MLSP-29.4: KRYLOV-LEVENBERG-MARQUARDT ALGORITHM FOR STRUCTURED TUCKER TENSOR DECOMPOSITIONS
Petr Tichavsky, Institute of Information Theory and Automation of the CAS, Czechia; Anh-Huy Phan, Andrzej Cichocki, Skolkovo Institute of Science and Technology, Russian Federation
MLSP-29.5: IMPROVING DYNAMIC GRAPH CONVOLUTIONAL NETWORK WITH FINE-GRAINED ATTENTION MECHANISM
Bo Wu, Xun Liang, Xiangping Zheng, Yuhui Guo, Hui Tang, Renmin University of China, China
MLSP-29.6: AdaPID: An Adaptive PID Optimizer for Training Deep Neural Networks
Boxi Weng, Jian Sun, Gang Wang, School of Automation, Beijing Institute of Technology, China; Alireza Sadeghi, Dept. of Electrical and Computer Engineering, University of Minnesota, United States of America