activity
20172026
most citedExtracting Global Dynamics of Loss Landscape in Deep Learning Models

1 citations · 1 across the 7 of their papers we have counts for

collaborators
Showing math.DSShow all

10 papers · 1 filter

math.DS2026

Characterizing High-dimensional Dynamics by Combinatorial-Topological Methods on a Latent Space

Patrick Bailon, Marcio Gameiro, Brittany Gelb +5

Combinatorial-topological methods for characterizing dynamics are rigorous, generalizable, computable, and they only require approximations, but the dimension of the phase space is…

math.DS2026

Compositionality of Global Dynamics in Product and Skew-Product Systems

William D. Kalies, Tony Wehbe

We study the compositionality of global dynamics through attractor lattices and order structures of recurrent dynamics in product and skew-product systems using Conley theory. For…

math.DS2026

Conley Index Theory for Hybrid Systems

Bernardo Rivas, William Kalies

We define a homological Conley index for a class of hybrid dynamical systems. This is achieved by factoring through the hybrid suspension semiflow, which views a class of hybrid dy…

math.DS2025

Topological Dynamics via Learned Hybrid Systems

Bernardo Rivas, Kaito Iwasaki, William Kalies +2

The analysis of global dynamics, particularly the identification and characterization of attractors and their regions of attraction, is essential for complex nonlinear and hybrid s…

math.DS2025

Data-driven Identification of Attractors Using Machine Learning

Marcio Gameiro, Brittany Gelb, William Kalies +3

In this paper we explore challenges in developing a topological framework in which machine learning can be used to robustly characterize global dynamics. Specifically, we focus on…

math.DS2024

Priestley duality and representations of recurrent dynamics

William Kalies, Robert Vandervorst

For an arbitrary dynamical system there is a strong relationship between global dynamics and the order structure of an appropriately constructed Priestley space. This connection pr…