Modular Machine Learning (Ben Recht)

In machine learning theory, we study problems with very simple descriptions.  We analyze how to fit a mixture of gaussians, or train an SVM, or compute principal components.  But in the wild, machine learning is a much more involved process.  A data scientist (heheh) is never just presented with data and told to fit an SVM.  One must first decide how to represent the data as a vector or discrete code, then how to normalize features, then how to prune features, and then, maybe, can begin fitting an SVM.

What can we say about the theoretical properties of such “end-to-end” machine learning?  What do the risk bounds look like?  Is this simply a matter of studying the “stability” properties of the end-to-end pipeline.  If so, how does one evaluate the stability of connecting together a series of components which have their individual, well-understood, stability properties.  Can we derive generalization bounds for general DAGs of heterogenous machine learning components?

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s