fbpx

IT Blog

Uncategorized

Chung-Ang University researchers develop algorithm for optimal decision making under heavy-tailed noisy rewards – EurekAlert

Researchers propose methods that theoretically guarantee minimal loss for worst case scenarios with minimal prior information for heavy-tailed reward distributions
Chung Ang University
image: The problem of sequential decision-making for noisy rewards in data science usually assumes a light-tailed noise distribution. However, many real-world datasets actually show a heavy-tailed noise. To address this, researchers from Korea proposed a minimax optimal robust upper confidence bound (MR-UCB) method and tested its validity with cryptocurrency datasets. Their method could identify the most profitable cryptocurrency with the least time-averaged cumulative regret. view more 
Credit: Marco Verch from flickr (https://www.flickr.com/photos/149561324@N03/32889807948)
In data science, researchers typically deal with data that contain noisy observations. An important problem explored by data scientists in this context is the problem of sequential decision making. This is commonly known as a “stochastic multi-armed bandit”(stochastic MAB). Here, an intelligent agent sequentially explores and selects actions based on noisy rewards under an uncertain environment. Its goal is to minimize the cumulative regret–the difference between the maximum reward and the expected reward of selected actions. A smaller regret implies a more efficient decision making.
Most existing studies on stochastic MABs have performed regret analysis under the assumption that the reward noise follows a light-tailed distribution. However, many real-world datasets, in fact, show a heavy-tailed noise distribution. These include user behavioral pattern data used for developing personalized recommendation systems, stock price data for automatic transaction development, and sensor data for autonomous driving.
In a recent study, Assistant Professor Kyungjae Lee of Chung-Ang University and Assistant Professor Sungbin Lim of the Ulsan Institute of Science and Technology, both in Korea, addressed this issue. In their theoretical analysis, they proved that the existing algorithms for stochastic MABs were sub-optimal for heavy-tailed rewards. More specifically, the methods employed in these algorithms–robust upper confidence bound (UCB) and adaptively perturbed exploration (APE) with unbounded perturbation–do not guarantee a minimax (minimization of maximum possible loss) optimality.
“Based on this analysis, minimax optimal robust (MR) UCB and APE methods have been proposed. MR-UCB utilizes a tighter confidence bound of robust mean estimators, and MR-APE is its randomized version. It employs bounded perturbation whose scale follows the modified confidence bound in MR-UCB,” explains Dr. Lee, speaking of their work, which was published in the IEEE Transactions on Neural Networks and Learning Systems on 14 September 2022.
The researchers next derived gap-dependent and independent upper bounds of the cumulative regret. For both the proposed methods, the latter value matches the lower bound under the heavy-tailed noise assumption, thereby achieving minimax optimality. Further, the new methods require minimal prior information and depend only on the maximum order of the bounded moment of rewards. In contrast, the existing algorithms require the upper bound of this moment a priori–information that may not be accessible in many real-world problems.
Having established their theoretical framework, the researchers tested their methods by performing simulations under Pareto and Fréchet noises. They found that MR-UCB consistently outperformed other exploration methods and was more robust with an increase in the number of actions under heavy-tailed noise.
Further, the duo verified their approach for real-world data using a cryptocurrency dataset, showing that MR-UCB and MR-APE were beneficial–minimax optimal regret bounds and minimal prior knowledge–in tackling heavy-tailed synthetic and real-world stochastic MAB problems.
“Being vulnerable to heavy-tailed noise, the existing MAB algorithms show poor performance in modeling stock data. They fail to predict big hikes or sudden drops in stock prices, causing huge losses. In contrast, MR-APE can be used in autonomous trading systems with stable expected returns through stock investment,” comments Dr. Lee, discussing the potential applications of the present work. “Additionally, it can be applied to personalized recommendation systems since behavioral data shows heavy-tailed noise. With better predictions of individual behavior, it is possible to provide better recommendations than conventional methods, which can maximize the advertising revenue,” he concludes.
 
***
 
Reference
DOI: https://doi.org/10.1109/TNNLS.2022.3203035
 
Authors: Kyungjae Lee1, Sungbin Lim2
 
Affiliations:
1Department of Artificial Intelligence, Chung-Ang University, Seoul, South Korea
2Artificial Intelligence Graduate School and the Department of Industrial Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan, South Korea
 
About Chung-Ang University
Chung-Ang University is a private comprehensive research university located in Seoul, South Korea. It was started as a kindergarten in 1916 and attained university status in 1953. It is fully accredited by the Ministry of Education of Korea. Chung-Ang University conducts research activities under the slogan of “Justice and Truth.” Its new vision for completing 100 years is “The Global Creative Leader.” Chung-Ang University offers undergraduate, postgraduate, and doctoral programs, which encompass a law school, management program, and medical school; it has 16 undergraduate and graduate schools each. Chung-Ang University’s culture and arts programs are considered the best in Korea.
Website: https://neweng.cau.ac.kr/index.do
 
About Assistant Professor Kyungjae Lee
Professor Kyungjae Lee received his B.S. and Ph.D. degrees in Electrical Engineering and Computer Engineering, respectively, from Seoul National University, Korea in 2015 and 2020, respectively. He is currently an Assistant Professor with the Department of Artificial Intelligence at Chung-Ang University, Seoul, Korea. His current research interests include multi-armed bandits, combinatorial bandits, reinforcement learning, and their applications.
IEEE Transactions on Neural Networks and Learning Systems
10.1109/TNNLS.2022.3203035
Computational simulation/modeling
Not applicable
Minimax Optimal Bandits for Heavy Tail Rewards
14-Sep-2022
Kyungjae Lee has received a research grant from Chung-Ang University Research Grants and Sungbin Lim has received a research grant from the Institute for Information & communication Technology Planning & evaluation (IITP)
Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.
Media Contact
Se-Jin Oh
Chung Ang University
shinn0015@cau.ac.kr
Office: 02-820-6614

Chung Ang University
EurekAlert! The Global Source for Science News
AAAS - American Association for the Advancement of Science
Copyright © 2022 by the American Association for the Advancement of Science (AAAS)
Copyright © 2022 by the American Association for the Advancement of Science (AAAS)

source