Adaptive security

I would like to know if there are any effective methods to choose a cryptographic algorithm from a pool of algorithms depending on a certain situation.

Let's say we know the performances of these algorithms when encrypting or signing messages of different sizes for example (there are too many metrics other than msg size) and we want the best algorithm to do the job. Are there any machine learning methods to do this?

Thank you

There certainly are mechanisms for choosing cryptographic algorithms from a pool. The obvious example is the TLS handshake to agree on a cipher suite for a connection between two computers. The two endpoints will have a list of the ciphers that it is willing/able to support. This will be set by the policy of the device owner and may be determined by believed bit-level of security, forward security, or performance, or other factors.

The decision mechanism is essentially an "I cut you choose" method, where the client lists its supported suites in order of preference and the server selects one suite from the list.

More complex negotiations would be possible, taking more information about the performance and preferences of the endpoint, but in practice, the speed of the decision process is deemed sufficiently important to keep with the "I cut you choose" version.

I expect that companies such as Google measure the performance of their data centres and handsets in order to choose the default preferences of Chrome and Google websites to optimise performance for both. How they perform the optimisation however I do not know.