Princeton University Users: If you would like to view a senior thesis while you are away from campus, you will need to connect to the campus network remotely via the Global Protect virtual private network (VPN). If you are not part of the University requesting a copy of a thesis, please note, all requests are processed manually by staff and will require additional time to process.
 

Publication:

The Pseudo Adiabatic Regime

Loading...
Thumbnail Image

Files

The Pseudo Adiabatic Regime.pdf (3.25 MB)

Date

2025-04-28

Journal Title

Journal ISSN

Volume Title

Publisher

Research Projects

Organizational Units

Journal Issue

Abstract

Score-Based Generative Models (SGMs) generate data by evolving samples under a Stochastic Differential Equation (SDE) that may include an auxiliary momentum variable. In this thesis, we investigate the probability density functions describing the evolution of such systems with momentum when the governing SDE slowly changes. For a simple moving Gaussian potential, we show the existence of an intermediate Pseudo-Adiabatic Regime (PAR) in which the momentum variables equilibrate while the position variables continue to evolve. In this regime, we show that the forward and reverse-time SDEs are the same, potentially simplifying the generative process. Using perturbative analysis and numerical experiments, we characterize the conditions under which the PAR emerges, demonstrating that a large damping-to-mass ratio suffices. Our results offer new perspectives on SGMs, and motivate further research into a more efficient generative process for SGMs.

Description

Keywords

Citation