Timezone: »

 
Quantization based Optimization : Alternative Stochastic Approximation of Global Optimization
Jinwuk Seok · Changsik Cho
Event URL: https://openreview.net/forum?id=0vaWgel-qz »

In this study, we propose a global optimization algorithm based on quantizing the energy level of an objective function in an NP-hard problem.According to the white noise hypothesis for a quantization error with a dense and uniform distribution, we can regard the quantization error as i.i.d. white noise. According to stochastic analysis, the proposed algorithm converges weakly only under conditions satisfying Lipschitz continuity, instead of local convergence properties such as the Hessian constraint of the objective function. This shows that the proposed algorithm ensures global optimization by Laplace's condition. Numerical experiments show that the proposed algorithm outperforms conventional learning methods in solving NP-hard optimization problems such as the traveling salesman problem.

Author Information

Jinwuk Seok (Electronics and Telecommunications Research Institute)

Jinwuk Seok received his BS and MS degrees in Electrical Control Engineering from Hong-Ik University, Seoul, Republic of Korea, in 1993 and 1995, respectively. Additionally, he received his Ph.D. degree in Electrical Engineering from Hong-Ik University, Seoul, Republic of Korea, in 1998. He has been a principal member of engineering staff at Electronics and Telecommunications Research Institute in Korea since 2000, and an adjunct professor of the Computer Software Engineering Department at the University of Science and Technology in Korea since 2009. His research interests include artificial intelligence, machine learning, and stochastic nonlinear control.

Changsik Cho (ETRI)

Changsik Cho is currently a Director at the Electronics and Telecommunications Research Institute (ETRI), Korea. He received his B.S. and M.S. degree from KyungPook National University, Korea, in 1993 and 1995 and received his Ph.D degree from ChungNam National University, Korea, in 2011. His research interests are AutoML, MLOps, AI Compiler, and Neural Network Computing System.

More from the Same Authors

  • 2021 : Stochastic Learning Equation using Monotone Increasing Resolution of Quantization »
    Jinwuk Seok ·
  • 2022 : Poster Session 2 »
    Jinwuk Seok · Bo Liu · Ryotaro Mitsuboshi · David Martinez-Rubio · Weiqiang Zheng · Ilgee Hong · Chen Fan · Kazusato Oko · Bo Tang · Miao Cheng · Aaron Defazio · Tim G. J. Rudner · Gabriele Farina · Vishwak Srinivasan · Ruichen Jiang · Peng Wang · Jane Lee · Nathan Wycoff · Nikhil Ghosh · Yinbin Han · David Mueller · Liu Yang · Amrutha Varshini Ramesh · Siqi Zhang · Kaifeng Lyu · David Yunis · Kumar Kshitij Patel · Fangshuo Liao · Dmitrii Avdiukhin · Xiang Li · Sattar Vakili · Jiaxin Shi
  • 2021 : Poster Session 2 (gather.town) »
    Wenjie Li · Akhilesh Soni · Jinwuk Seok · Jianhao Ma · Jeffery Kline · Mathieu Tuli · Miaolan Xie · Robert Gower · Quanqi Hu · Matteo Cacciola · Yuanlu Bai · Boyue Li · Wenhao Zhan · Shentong Mo · Junhyung Lyle Kim · Sajad Fathi Hafshejani · Chris Junchi Li · Zhishuai Guo · Harshvardhan Harshvardhan · Neha Wadia · Tatjana Chavdarova · Difan Zou · Zixiang Chen · Aman Gupta · Jacques Chen · Betty Shea · Benoit Dherin · Aleksandr Beznosikov