Co-adaptive learning over a countable space
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.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderRecommendation SystemsSimilar Papers 제목 키워드 기반
Thiele's Differential Equation Based on Markov Jump Processes with Non-countable State Space
In modern life insurance, Markov processes in continuous time on a finite or at least countable state space have been over the years an important tool for the modelling of the states of an insured. Motivated by applicati…
Reproducing Kernel Hilbert Spaces Cannot Contain all Continuous Functions on a Compact Metric Space
Given an uncountable, compact metric space, we show that there exists no reproducing kernel Hilbert space that contains the space of all continuous functions on this compact space.
AllExpected utility theory on mixture spaces without the completeness axiom
A mixture preorder is a preorder on a mixture space (such as a convex set) that is compatible with the mixing operation. In decision theoretic terms, it satisfies the central expected utility axiom of strong independence…
Open-Ended Question AnsweringBayesian Optimization with a Finite Budget: An Approximate Dynamic Programming Approach
We consider the problem of optimizing an expensive objective function when a finite budget of total evaluations is prescribed. In that context, the optimal solution strategy for Bayesian optimization can be formulated as…
Bayesian OptimizationCan AI be Accountable?
The AI we use is powerful, and its power is increasing rapidly. If this powerful AI is to serve the needs of consumers, voters, and decision makers, then it is imperative that the AI is accountable. In general, an agent …