Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.
Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.
Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.
Author ORCID Identifier
AccessType
Open Access Dissertation
Document Type
dissertation
Degree Name
Doctor of Philosophy (PhD)
Degree Program
Computer Science
Year Degree Awarded
2019
Month Degree Awarded
May
First Advisor
Sridhar Mahadevan
Second Advisor
Phil Thomas
Third Advisor
Daniel Sheldon
Fourth Advisor
Mario Parente
Subject Categories
Artificial Intelligence and Robotics | Dynamical Systems
Abstract
Many existing machine learning (ML) algorithms cannot be viewed as gradient descent on some single objective. The solution trajectories taken by these algorithms naturally exhibit rotation, sometimes forming cycles, a behavior that is not expected with (full-batch) gradient descent. However, these algorithms can be viewed more generally as solving for the equilibrium of a game with possibly multiple competing objectives. Moreover, some recent ML models, specifically generative adversarial networks (GANs) and its variants, are now explicitly formulated as equilibrium problems. Equilibrium problems present challenges beyond those encountered in optimization such as limit-cycles and chaotic attractors and are able to abstract away some of the difficulties encountered when training models like GANs.
In this thesis, I aim to advance our understanding of equilibrium problems so as to improve state-of-the-art in GANs and related domains. In the following chapters, I will present work on
- designing a no-regret framework for solving monotone equilibrium problems in online or streaming settings (with applications to Reinforcement Learning),
- ensuring convergence when training a GAN to fit a normal distribution to data by Crossing-the-Curl,
- improving state-of-the-art image generation with techniques derived from theory,
- and borrowing tools from dynamical systems theory for analyzing the complex dynamics of GAN training.
DOI
https://doi.org/10.7275/13780178
Recommended Citation
Gemp, Ian, "FROM OPTIMIZATION TO EQUILIBRATION: UNDERSTANDING AN EMERGING PARADIGM IN ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING" (2019). Doctoral Dissertations. 1548.
https://doi.org/10.7275/13780178
https://scholarworks.umass.edu/dissertations_2/1548