Model-Independent Online Learning for Influence Maximization

  title={Model-Independent Online Learning for Influence Maximization},
  author={Sharan Vaswani and Branislav Kveton and Zheng Wen and Mohammad Ghavamzadeh and Laks V. S. Lakshmanan and Mark Schmidt},
This proves the first part of Theorem 1. We now prove the second part of the theorem. First, note that from the first part, we have f( e S, p⇤)  F ( e S)  F (S⇤), where the first inequality follows from the first part of this theorem, and the second inequality follows from the definition of S⇤. Thus, we have ⇢  1. To prove that ⇢ 1/K, we assume that S… CONTINUE READING