neos: End-to-End-Optimised Summary Statistics for High Energy Physics
This work addresses the challenge of enhancing sensitivity in high-energy physics experiments, though it is incremental as it applies an existing differentiable paradigm to a specific domain.
The authors tackled the problem of optimizing summary statistics for high-energy physics analyses by introducing neos, a fully differentiable workflow that optimizes learnable summary statistics with respect to expected sensitivity, resulting in improved analysis performance by incorporating systematic uncertainties.
The advent of deep learning has yielded powerful tools to automatically compute gradients of computations. This is because training a neural network equates to iteratively updating its parameters using gradient descent to find the minimum of a loss function. Deep learning is then a subset of a broader paradigm; a workflow with free parameters that is end-to-end optimisable, provided one can keep track of the gradients all the way through. This work introduces neos: an example implementation following this paradigm of a fully differentiable high-energy physics workflow, capable of optimising a learnable summary statistic with respect to the expected sensitivity of an analysis. Doing this results in an optimisation process that is aware of the modelling and treatment of systematic uncertainties.