Glossary term
Glossary term
Training and Fine-Tuning
The process of using mathematical techniques such as gradient descent to find the minimum of a convex function. A great deal of research in machine learning has focused on formulating various problems as convex optimization problems and in solving those problems more efficiently.
For complete details, see Boyd and Vandenberghe, Convex Optimization.
Created for this library
A pricing team trains its linear demand model with convex optimization so it can guarantee the solution is the global minimum on the training set.
A risk modeling team uses convex optimization for its production scorecard because reproducible global optima ease regulatory review.
A logistics planner solves a convex optimization problem to allocate vehicles across routes given soft constraints on cost and service level.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License