# What is the definition of the robustness of a machine learning algorithm?

What is the definition of the robustness of a machine learning algorithm? Is it different from the definition of the performance?

What is the definition of the robustness of a machine learning algorithm? Is it different from the definition of the performance?

## All Answers (2)

Alexander V Lebedev· Karolinska InstitutetThe robustness is the property that characterizes how effective your algorithm is while being tested on the new independent (but similar) dataset. In the other words, the robust algorithm is the one, the testing error of which is close to the training error.

For details see the following presentation:

( http://www.colt2010.org/presentation/rob_colt.pdf )

There you can find the references to the original papers as well.

P.S.:

To my best knowledge, "robustness to noise" (or "noise robustness") is a slightly different term, that describe the stability of the algorithm performance after adding some noise to your data (sorry for a bit self-evident definition=))

Evaldas Vaiciukynas· Kaunas University of Technologyhttp://users.ece.utexas.edu/~cmcaram/pubs/XuCaramanisMannor.NFL.pdf

Can you help by adding an answer?