Co-adaptive learning over a countable space
This addresses a foundational gap in co-adaptive learning, which has applications in areas like brain-computer interfacing, by offering theoretical guarantees for improved performance.
The paper tackles the co-adaptive learning problem in an online, closed-loop setting by providing a general analysis, proving that it outperforms learning with a fixed decoder with high probability under a specific condition.
Co-adaptation is a special form of on-line learning where an algorithm $\mathcal{A}$ must assist an unknown algorithm $\mathcal{B}$ to perform some task. This is a general framework and has applications in recommendation systems, search, education, and much more. Today, the most common use of co-adaptive algorithms is in brain-computer interfacing (BCI), where algorithms help patients gain and maintain control over prosthetic devices. While previous studies have shown strong empirical results Kowalski et al. (2013); Orsborn et al. (2014) or have been studied in specific examples Merel et al. (2013, 2015), there is no general analysis of the co-adaptive learning problem. Here we will study the co-adaptive learning problem in the online, closed-loop setting. We will prove that, with high probability, co-adaptive learning is guaranteed to outperform learning with a fixed decoder as long as a particular condition is met.