First-Exit Time Analysis for Truncated Heavy-Tailed Dynamical Systems
Xingyu Wang, Chang-Han Rhee

TL;DR
This paper analyzes the first-exit times of truncated heavy-tailed stochastic systems, revealing phase transitions and metastable behaviors, and extends classical Freidlin-Wentzell theory to heavy-tailed contexts.
Contribution
It develops a framework connecting large deviations with metastability for truncated heavy-tailed systems, providing a detailed characterization of exit times and locations.
Findings
Identifies a hierarchy of phase transitions in exit times as truncation varies.
Unveils the catastrophe principle where key events are driven by few components.
Extends Freidlin-Wentzell theory to heavy-tailed stochastic systems.
Abstract
In this paper, we study the first-exit time of stochastic difference equation and its truncated variant , where and the law of the noise is multivariate regularly varying. The truncation operator is often introduced as a modulation mechanism in heavy-tailed systems, such as stochastic gradient descent algorithms in deep learning. By developing a framework that connects large deviations with metastability, we leverage the locally uniform sample-path large deviations for both processes in Wang and Rhee (2024) to obtain precise characterizations of the joint…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
Topicsstochastic dynamics and bifurcation · Markov Chains and Monte Carlo Methods · Quantum many-body systems
