Natural Gradient for Combined Loss Using Wavelets
Journal of Scientific Computing, ISSN: 1573-7691, Vol: 86, Issue: 2
2021
- 1Citations
- 3Captures
Metric Options: CountsSelecting the 1-year or 3-year option will change the metrics count to percentiles, illustrating how an article or review compares to other articles or reviews within the selected time period in the same journal. Selecting the 1-year option compares the metrics against other articles/reviews that were also published in the same calendar year. Selecting the 3-year option compares the metrics against other articles/reviews that were also published in the same calendar year plus the two years prior.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Article Description
Natural gradients have been widely used in the optimization of loss functionals over probability space, with important examples such as Fisher–Rao gradient descent for Kullback–Leibler divergence, Wasserstein gradient descent for transport-related functionals, and Mahalanobis gradient descent for quadratic loss functionals. This note considers the situation in which the loss is a convex linear combination of these examples. We propose a new natural gradient algorithm by utilizing compactly supported wavelets to diagonalize approximately the Hessian of the combined loss. Numerical results are included to demonstrate the efficiency of the proposed algorithm.
Bibliographic Details
http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=85099001505&origin=inward; http://dx.doi.org/10.1007/s10915-020-01367-x; http://link.springer.com/10.1007/s10915-020-01367-x; http://link.springer.com/content/pdf/10.1007/s10915-020-01367-x.pdf; http://link.springer.com/article/10.1007/s10915-020-01367-x/fulltext.html; https://dx.doi.org/10.1007/s10915-020-01367-x; https://link.springer.com/article/10.1007/s10915-020-01367-x
Springer Science and Business Media LLC
Provide Feedback
Have ideas for a new metric? Would you like to see something else here?Let us know