Topics in Random Matrices and Statistical Machine Learning
It addresses theoretical issues in random matrix theory and statistical machine learning, but appears incremental as it builds on existing frameworks like Laguerre matrices and Stone's theorem.
This thesis tackles two problems: establishing conditions for finite inverse moments of certain random matrices, and proving consistency of the k-nearest neighbor rule in specific metric spaces, with results including necessary and sufficient conditions and universal weak and strong consistency proofs.
This thesis consists of two independent parts: random matrices, which form the first one-third of this thesis, and machine learning, which constitutes the remaining part. The main results of this thesis are as follows: a necessary and sufficient condition for the inverse moments of $(m,n,β)$-Laguerre matrices and compound Wishart matrices to be finite; the universal weak consistency and the strong consistency of the $k$-nearest neighbor rule in metrically sigma-finite dimensional spaces and metrically finite dimensional spaces respectively. In Part I, the Chapter 1 introduces the $(m,n,β)$-Laguerre matrix, Wishart and compound Wishart matrix and their joint eigenvalue distribution. While in Chapter 2, a necessary and sufficient condition to have finite inverse moments has been derived. In Part II, the Chapter 1 introduces the various notions of metric dimension and differentiation property followed by our proof for the necessary part of Preiss' result. Further, Chapter 2 gives an introduction to the mathematical concepts in statistical machine learning and then the $k$-nearest neighbor rule is presented in Chapter 3 with a proof of Stone's theorem. In chapters 4 and 5, we present our main results and some possible future directions based on it.