Practical Batch Bayesian Sampling Algorithms for Online Adaptive Traffic Experimentation
원문 초록
Online controlled experiments have emerged as industry gold standard for assessing new web features. As new web algorithms proliferate, experimentation platform faces an increasing demand on the velocity of online experiments, which encourages adaptive traffic testing methods to speed up identifying best variant by efficiently allocating traffic. This paper proposed four Bayesian batch bandit algorithms (NB-TS, WB-TS, NB-TTTS, WB-TTTS) for eBay's experimentation platform, using summary batch statistics of a goal metric without incurring new engineering technical debts. The novel WB-TTTS, in particular, demonstrates as an efficient, trustworthy and robust alternative to fixed horizon A/B testing. Another novel contribution is to bring trustworthiness of best arm identification algorithms into evaluation criterion and highlight the existence of severe false positive inflation with equivalent best arms. To gain the trust of experimenters, experimentation platform must consider both efficiency and trustworthiness; However, to the best of authors' knowledge, trustworthiness as an important topic is rarely discussed. This paper shows that Bayesian bandits without neutral posterior reshaping, particularly naive Thompson sampling (NB-TS), are untrustworthy because they can always identify an arm as the best from equivalent best arms. To restore trustworthiness, a novel finding uncovers connections between convergence distribution of posterior optimal probabilities of equivalent best arms and neutral posterior reshaping, which controls false positives. Lastly, this paper presents lessons learned from eBay's experience, as well as thorough evaluations. We hope this work is useful to other industrial practitioners and inspires academic researchers interested in the trustworthiness of adaptive traffic experimentation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Representative Action Selection for Large Action-Space Meta-Bandits
Steering Generative Models with Experimental Data for Protein Fitness Optimization
Addressing Missing Data Issue for Diffusion-based Recommendation
Dynamic Assortment Selection and Pricing with Censored Preference Feedback
Bandit-Based Prompt Design Strategy Selection Improves Prompt Optimizers
Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.