A Survey of Machine Learning-Based Physics Event Generation

Event generators in high-energy nuclear and particle physics play an important role in facilitating studies of particle reactions. We survey the state of the art of machine learning (ML) efforts at building physics event generators. We review ML generative models used in ML-based event generators and their specific challenges, and discuss various approaches of incorporating physics into the ML model designs to overcome these challenges. Finally, we explore some open questions related to super-resolution, fidelity, and extrapolation for physics event generation based on ML technology.

GANplifying event samples

A critical question concerning generative networks applied to event generation in particle physics is if the generated events add statistical precision beyond the training sample. We show for a simple example with increasing dimensionality how generative networks indeed amplify the training statistics. We quantify their impact through an amplification factor or equivalent numbers of sampled events.

Event generation and statistical sampling for physics with deep generative models and a density information buffer

Simulating nature and in particular processes in particle physics require expensive computations and sometimes would take much longer than scientists can afford. Here, we explore ways to a solution for this problem by investigating recent advances in generative modeling and present a study for the generation of events from a physical process with deep generative models. The simulation of physical processes requires not only the production of physical events, but to also ensure that these events occur with the correct frequencies. We investigate the feasibility of learning the event generation and the frequency of occurrence with several generative machine learning models to produce events like Monte Carlo generators. We study three processes: a simple two-body decay, the processes e+e− → Z → l+l− and $$pp\to t\bar{t}$$ p p → t t ¯ including the decay of the top quarks and a simulation of the detector response. By buffering density information of encoded Monte Carlo events given the encoder of a Variational Autoencoder we are able to construct a prior for the sampling of new events from the decoder that yields distributions that are in very good agreement with real Monte Carlo events and are generated several orders of magnitude faster. Applications of this work include generic density estimation and sampling, targeted event generation via a principal component analysis of encoded ground truth data, anomaly detection and more efficient importance sampling, e.g., for the phase space integration of matrix elements in quantum field theories.

How to GAN Event Unweighting

Event generation with neural networks has seen significant progress recently. The big open question is still how such new methods will accelerate LHC simulations to the level required by upcoming LHC runs. We target a known bottleneck of standard simulations and show how their unweighting procedure can be improved by generative networks. This can, potentially, lead to a very significant gain in simulation speed.

Thalamocortical mechanisms regulating the relationship between transient beta events and human tactile perception

Transient neocortical events with high spectral power in the 15-29Hz beta band are among the most reliable predictors of sensory perception. Prestimulus beta event rates in primary somatosensory cortex correlate with sensory suppression, most effectively 100-300ms before stimulus onset. However, the neural mechanisms underlying this perceptual association are unknown. We combined human magnetoencephalography (MEG) measurements with biophysical neural modeling to test potential cellular and circuit mechanisms that underlie observed correlations between prestimulus beta events and tactile detection. Extending prior studies, we found that simulated bursts from higher-order, non-lemniscal thalamus were sufficient to drive beta event generation and to recruit slow supragranular inhibition acting on a 300ms time scale to suppress sensory information. Further analysis showed that the same beta generating mechanism can lead to facilitated perception for a brief period when beta events occur simultaneously with tactile stimulation before inhibition is recruited. These findings were supported by close agreement between model-derived predictions and empirical MEG data. The post-event suppressive mechanism explains an array of studies that associate beta with decreased processing, while the during-event faciliatory mechanism may demand a reinterpretation of the role of beta events in the context of coincident timing.