A Correction of Pseudo Log-Likelihood Method

arXiv:2403.18127v1 Announce Type: new
Abstract: Pseudo log-likelihood is a type of maximum likelihood estimation (MLE) method used in various fields including contextual bandits, influence maximization of social networks, and causal bandits. However, in previous literature \citep{li2017provably, zhang2022online, xiong2022combinatorial, feng2023combinatorial1, feng2023combinatorial2}, the log-likelihood function may not be bounded, which may result in the algorithm they proposed not well-defined. In this paper, we give a counterexample that the maximum pseudo log-likelihood estimation fails and then provide a solution to correct the algorithms …

abstract algorithm arxiv causal cs.lg fields function however influence likelihood literature math.st maximum likelihood estimation mle networks social social networks stat.ml stat.th the algorithm type