Reinforcement learning for graph theory, Parallelizing Wagner's approach
By: Alix Bouffard, Jane Breen
Potential Business Impact:
Finds weaknesses in math rules for computer networks.
Our work applies reinforcement learning to construct counterexamples concerning conjectured bounds on the spectral radius of the Laplacian matrix of a graph. We expand upon the re-implementation of Wagner's approach by Stevanovic et al. with the ability to train numerous unique models simultaneously and a novel redefining of the action space to adjust the influence of the current local optimum on the learning process.
Similar Papers
Leveraging Low-rank Factorizations of Conditional Correlation Matrices in Graph Learning
Machine Learning (CS)
Finds hidden connections in data faster.
Distributed Optimization of Pairwise Polynomial Graph Spectral Functions via Subgraph Optimization
Optimization and Control
Helps computer networks share information more efficiently.
Re-imagining Spectral Graph Theory
Combinatorics
New math tool connects different kinds of networks.