Zhu, ZhenyuLocatello, FrancescoCevher, Volkan2024-03-142024-03-142024-03-142023https://infoscience.epfl.ch/handle/20.500.14299/206107https://arxiv.org/abs/2310.18123This paper provides statistical sample complexity bounds for score-matching and its applications in causal discovery. We demonstrate that accurate estimation of the score function is achievable by training a standard deep ReLU neural network using stochastic gradient descent. We establish bounds on the error rate of recovering causal relationships using the score-matching-based causal discovery method of Rolland et al. [2022], assuming a sufficiently good estimation of the score function. Finally, we analyze the upper bound of score-matching estimation within the scorebased generative modeling, which has been applied for causal discovery but is also of independent interest within the domain of generative models.AI-MLtext::conference output::conference paper not in proceedings