Slide 40
Slide 40 text
参考文献
• Hadad, Hirshberg, Zhan, Wager, and Athey (2019). Confidence Intervals for Policy Evaluation in Adaptive
Experiments, arXiv.
• Kato, Ishihara, Honda, and Narita (2020). Adaptive Experimental Design for Efficient Treatment Effect
Estimation: Randomized Allocation via Contextual Bandit Algorithm, arXiv.
• Delyon and Portier (2018). Asymptotic optimality of adaptive importance sampling, NeuIPS.
• Johari, R., Pekelis, L., and Walsh, D. J. Always valid inference: Bringing sequential analysis to a/b testing,
arXiv.
• Zhao, S., Zhou, E., Sabharwal, A., and Ermon, S. Adaptive concentration inequalities for sequential decision
problems, NeurIPS.
• Balsubramani, A. and Ramdas, A. Sequential nonparametric testing with the law of the iterated logarithm, UAI.
• Balsubramani, A. Sharp finite-time iterated-logarithm martingale concentration. arXiv
40