A Step Toward Interpretability: Smearing the Likelihood
This work addresses interpretability for particle physics researchers, but it is incremental as it presents a first modest step without broad validation.
The authors tackled the lack of a clear definition and method for interpretability in particle physics machine learning by proposing a definition and practical approach using smeared likelihoods to identify relevant physical energy scales. They demonstrated that discrimination power in quark vs. gluon jet identification increases as resolution decreases, indicating sensitivity to emissions at all scales.
The problem of interpretability of machine learning architecture in particle physics has no agreed-upon definition, much less any proposed solution. We present a first modest step toward these goals by proposing a definition and corresponding practical method for isolation and identification of relevant physical energy scales exploited by the machine. This is accomplished by smearing or averaging over all input events that lie within a prescribed metric energy distance of one another and correspondingly renders any quantity measured on a finite, discrete dataset continuous over the dataspace. Within this approach, we are able to explicitly demonstrate that (approximate) scaling laws are a consequence of extreme value theory applied to analysis of the distribution of the irreducible minimal distance over which a machine must extrapolate given a finite dataset. As an example, we study quark versus gluon jet identification, construct the smeared likelihood, and show that discrimination power steadily increases as resolution decreases, indicating that the true likelihood for the problem is sensitive to emissions at all scales.