Network Horizon Dynamics I: Qualitative Aspects
March 25, 2019 Β· Declared Dead Β· π arXiv.org
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
B. Dribus, A. Sumner, K. Bist, N. Regmi, J. Sircar, S. Upreti
arXiv ID
1903.10268
Category
physics.soc-ph
Cross-listed
cs.SI
Citations
0
Venue
arXiv.org
Last Checked
4 months ago
Abstract
Mostly acyclic directed networks, treated mathematically as directed graphs, arise in machine learning, biology, social science, physics, and other applications. Newman [1] has noted the mathematical challenges of such networks. In this series of papers, we study their connectivity properties, focusing on three types of phase transitions that affect horizon sizes for typical nodes. The first two types involve the familiar emergence of giant components as average local connectivity increases, while the third type involves small-world horizon growth at variable distance from a typical node. In this first paper, we focus on qualitative behavior, simulations, and applications, leaving formal considerations for subsequent papers. We explain how such phase transitions distinguish deep neural networks from shallow machine learning architectures, and propose hybrid local/random network designs with surprising connectivity advantages. We also propose a small-world approach to the horizon problem in the cosmology of the early universe as a novel alternative to the inflationary hypothesis of Guth and Linde.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β physics.soc-ph
π
π
The Cartographer
R.I.P.
π»
Ghosted
Networks beyond pairwise interactions: structure and dynamics
R.I.P.
π»
Ghosted
Statistical physics of human cooperation
R.I.P.
π»
Ghosted
Vital nodes identification in complex networks
R.I.P.
π»
Ghosted
Influence maximization in complex networks through optimal percolation
R.I.P.
π»
Ghosted
Scale-free networks are rare
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted