Sequential Best-Arm Identification with Application to Brain-Computer Interface
This work addresses the lengthy learning process in BCI speller systems for users, such as those in medical or rehabilitation settings, by improving sampling efficiency, though it appears incremental as it builds on existing bandit methods and LLM applications.
The paper tackles the inefficiency of conventional non-adaptive paradigms in brain-computer interface (BCI) speller systems by framing the problem as sequential best-arm identification tasks, using pre-trained large language models (LLMs) to leverage prior knowledge and proposing a sequential top-two Thompson sampling (STTS) algorithm, resulting in substantial empirical improvement demonstrated through synthetic data and a P300 BCI speller simulator.
A brain-computer interface (BCI) is a technology that enables direct communication between the brain and an external device or computer system. It allows individuals to interact with the device using only their thoughts, and holds immense potential for a wide range of applications in medicine, rehabilitation, and human augmentation. An electroencephalogram (EEG) and event-related potential (ERP)-based speller system is a type of BCI that allows users to spell words without using a physical keyboard, but instead by recording and interpreting brain signals under different stimulus presentation paradigms. Conventional non-adaptive paradigms treat each word selection independently, leading to a lengthy learning process. To improve the sampling efficiency, we cast the problem as a sequence of best-arm identification tasks in multi-armed bandits. Leveraging pre-trained large language models (LLMs), we utilize the prior knowledge learned from previous tasks to inform and facilitate subsequent tasks. To do so in a coherent way, we propose a sequential top-two Thompson sampling (STTS) algorithm under the fixed-confidence setting and the fixed-budget setting. We study the theoretical property of the proposed algorithm, and demonstrate its substantial empirical improvement through both synthetic data analysis as well as a P300 BCI speller simulator example.