Deep zero-inflated negative binomial model and its application in scRNA-seq data integration

Abstract

Many real applications of bandits have sparse non-zero rewards, leading to slow learning rates. A careful distribution modeling that utilizes problem-specific structures is known as critical to estimation efficiency in the statistics literature, yet is under-explored in bandits. To fill the gap, we initiate the study of zero-inflated bandits, where the reward is modeled as a classic semiparametric distribution called zero-inflated distribution. We carefully design Upper Confidence Bound (UCB) and Thompson Sampling (TS) algorithms for this specific structure. Our algorithms are suitable for a very general class of reward distributions, operating under tail assumptions that are considerably less stringent than the typical sub-Gaussian requirements. Theoretically, we derive the regret bounds for both the UCB and TS algorithms for multi-armed bandit, showing that they can achieve rate-optimal regret when the reward distribution is sub-Gaussian. The superior empirical performance of the proposed methods is shown via extensive numerical studies.

A review of machine learning methods for cancer characterization from microbiome data

“…Thus, the next steps in ML for cancer-related applications using microbiome data likely include the development and application of models that are more robust under zeroinflated data with high variability. Several models have already been proposed for this kind of data [145][146][147] , some specifically designed for microbial count data 148 . Such models should find microbial signatures associated with cancer characteristics while filtering out sporadic associations resulting from technical variations.…”