Maximum entropy approach to massive graph spectrum learning with applications
We propose an alternative maximum entropy approach to learning the spectra of massive graphs. In contrast to state-of-the-art Lanczos algorithm for spectral density estimation and applications thereof, our approach does not require kernel smoothing. As the choice of kernel function and associated ba...
Main Authors: | Granziol, D, Ru, B, Dong, X, Zohren, S, Osborne, M, Roberts, S |
---|---|
Format: | Journal article |
Language: | English |
Published: |
MDPI
2022
|
Similar Items
-
Maximum Entropy Approach to Massive Graph Spectrum Learning with Applications
by: Diego Granziol, et al.
Published: (2022-06-01) -
MEMe: An accurate maximum entropy method for efficient approximations in large-scale machine learning
by: Granziol, D, et al.
Published: (2019) -
MEMe: An Accurate Maximum Entropy Method for Efficient Approximations in Large-Scale Machine Learning
by: Diego Granziol, et al.
Published: (2019-05-01) -
Learning rates as a function of batch size: a random matrix theory approach to neural network training
by: Granziol, D, et al.
Published: (2022) -
From Maximum Entropy to Maximum Entropy Production: A New Approach
by: Nathaniel Virgo
Published: (2010-01-01)