A Practical and Provable Algorithm for Subspace Clustering

1. Introduction Traditional distance based clustering algorithms such as K-Means perform poorly on high dimensional data because of curse of dimensionality[1]. A common approach to cluster such data is to assume that even though their ambient dimensionality is high, their intrinsic dimensionality is much lower. As an example, consider the dataset of images of faces… Continue reading A Practical and Provable Algorithm for Subspace Clustering

A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics

1. Introduction The purpose of this blog post is to try and understand the paper by the same name as the title, by Yuchen Zhang, Percy Liang, and Moses Charikar [2]. The setting is that of minimization of a (not necessarily convex) real valued function . Where is a compact set in . The algorithm… Continue reading A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics