Neural Networks (NN), the backbones of Deep Learning, create field theories through their output ensembles at initialization. Certain limits of NN architecture give rise to free field theories via Central Limit Theorem (CLT), whereas other regimes give rise to weakly coupled, and non-perturbative field theories, via small, and large deviations from CLT. I will present a systematic construction...
Recognizing symmetries in data allows for significant boosts in neural network training. In many cases, however, the underlying symmetry is present only in an idealized dataset, and is broken in the training data, due to effects such as arbitrary and/or non-uniform detector bin edges. Standard approaches, such as data augmentation or equivariant networks fail to represent the nature of the...
We have developed an end-to-end data analysis framework, HEP ML Lab (HML), based on Python for signal-background analysis in high-energy physics research. It offers essential interfaces and shortcuts for event generation, dataset creation, and method application.
With the HML API, a large volume of collision events can be generated in sequence under different settings. The representations...
We present a class of Neural Networks which extends the notion of Energy Flow Networks (EFNs) to higher-order particle correlations. The structure of these networks is inspired by the Energy-Energy Correlators of QFT, which are particularly robust against non-perturbative corrections. By studying the response of our models to the presence and absence of non-perturbative hadronization, we can...
Neural network models that rely on jet substructure are commonly trained assuming jet constituents at truth level or smeared by parameterized detector response. However, the performance in such simplified circumstances may translate poorly to actual collider experiments. We investigate the impact by comparing large-R jet tagging using smeared particle-level jets versus jets built using...
Machine learning algorithms have the capacity to discern intricate features directly from raw data. We demonstrated the performance of top taggers built upon three machine learning architectures: a BDT that uses jet-level variables (high-level features, HLF) as input, while a CNN (ResNet) trained on the jet image, and a GNN (LorentzNet) trained on the particle cloud representation of a jet...
