Finite Sample Bounds for Learning with Score Matching

ArXi:2605.14168v1 Announce Type: new Learning of continuous exponential family distributions with unbounded remains an important area of research for both theory and applications in high-dimensional statistics. In recent years, score matching has become a widely used method for learning exponential families with continuous variables due to its computational ease when compared against maximum likelihood estimation. However, theoretical understanding of the statistical properties of score matching is still lacking.