Automated Discovery of Jet Substructure Analyses
Explore this paper's citation graph
Summary
In a demonstration how algorithms can produce original research in direct competition to human experts, the resulting jet substructure variables and analyses are capable of determining the initial temperature of the plasma medium from analyzing 1200--2500 jets, a performance not seen in existing, manually designed analyses.
- Type
- preprint
- Published
- 2018-10-01
- Cited by
- 9
- References
- 16
- Access
- Open access
- OpenAlex
- https://openalex.org/W2892980436
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:119529001
Keywords
Substructure, Jet (fluid), Physics, Quark–gluon plasma, Large Hadron Collider
References
- Global Optimality in Tensor Factorization, Deep Learning, and Beyond
- cuDNN: Efficient Primitives for Deep Learning
- Deep vs. shallow networks : An approximation theory perspective
- Why Deep Neural Networks for Function Approximation?
- Regularisation of neural networks by enforcing Lipschitz continuity
- Adam: A Method for Stochastic Optimization
- Parseval Networks: Improving Robustness to Adversarial Examples
- Proceedings of the 22nd international conference on Machine learning
- FFX: Fast, Scalable, Deterministic Symbolic Regression Technology
- (2018). Many-body chaos and energy dynamics in holography. Journal of High Energy Physics, (2018),
Cited by
- Energy flow networks: deep sets for particle jets
- Report from the A.I. For Nuclear Physics Workshop.
- Recent development of hydrodynamic modeling in heavy-ion collisions
- Machine learning for high energy heavy ion collisions
- Explainable machine learning of the underlying physics of high-energy particle collisions
- Learning from many collider events at once
- A.I. for nuclear physics
- Deep Learning for the classification of quenched jets
- The information content of jet quenching and machine learning assisted observable design
Related papers
- Jet substructure templates: data-driven QCD backgrounds for fat jet searches
- Jet substructure with analytical methods
- Computing N -subjettiness for boosted jets
- Deep learning jet substructure from two-particle correlations
- Identifying the quantum properties of hadronic resonances using machine learning