Date of Award
2019
Degree Type
Dissertation
Degree Name
Doctor of Philosophy (PhD)
Graduate Group
Mathematics
First Advisor
Robin Pemantle
Abstract
Stochastic approximations is a rich branch of probability theory and has a wide range of application. Here we study stochastic approximations from the perspective of gradient descent. An important question is what is the asymptotic limit of a stochastic approximation. In that spirit we will provide a detailed description for the limiting behavior of certain one dimensional stochastic approximations.
Recommended Citation
Karatapanis, Konstantinos, "Certain Systems Arising In Stochastic Gradient Descent" (2019). Publicly Accessible Penn Dissertations. 3532.
https://repository.upenn.edu/edissertations/3532
Files over 3MB may be slow to open. For best results, right-click and select "save as..."