Conveners
Session: Machine Learning: Machine Learning
- Florencia Canelli (Universitaet Zuerich (CH))
Session: Machine Learning: Machine Learning
- Matthew Schwartz
How to represent a jet is at the core of machine learning on jet physics. Inspired by the notion of point cloud, we propose a new approach that considers a jet as an unordered set of its constituent particles, effectively a "particle cloud". Such particle cloud representation of jets is efficient in incorporating raw information of jets and also explicitly respects the permutation symmetry....
Classification of jets with deep learning has gained significant attention in recent times. However, the performance of deep neural networks is often achieved at the cost of interpretability. Here we propose an interpretable network trained on the jet spectrum $S_{2}(R)$ which is a two-point correlation function of the jet constituents. The spectrum can be derived from a functional Taylor...
Despite the successful application of deep learning to many problems involving jet substructure, typical approaches involve representing jets either as lists of four-vectors or as 2D images. This is mainly due to the compatibility of these structures with existing architectures, such as recurrent or convolutional networks. However, these networks fail to exhibit equivariance with respect to...
Based on the established task of identifying boosted, hadronically decaying top quarks, we compare a wide range of modern machine learning approaches. We find that they are extremely powerful and great fun.
We apply techniques from Bayesian generative statistical modeling to uncover hidden features in jet substructure observables that discriminate between different a priori unknown underlying short distance physical processes in multi-jet events. In particular, we use a mixed membership model known as Latent Dirichlet Allocation to build a data-driven unsupervised top-quark tagger and ttbar event...
We introduce a novel implementation of a reinforcement learning algorithm which is adapted to the problem of jet grooming, a crucial component of jet physics at hadron colliders. We show that the grooming policies trained using a Deep Q-Network model outperform state-of-the-art tools used at the LHC such as Recursive Soft Drop, allowing for improved resolution of the mass of boosted objects....
Machine learning methods are being increasingly and successfully applied to many different physics problems. However, current machine learning approaches do not model uncertainties well - if at all. In this talk I will discuss how using Bayesian neural networks can give us a handle on uncertainties in machine learning. I will use tagging top quark vs. light quark and gluon jets as an example...
Parton shower Monte Carlo programs are a key tool for all aspects of analysis using jet substructure. These programs have many tunable parameters that control aspects of both perturbative and non-perturbative models. Finding the best parameters is non-trivial, and parton showers are typically run both for some optimized parameters as well as variations for uncertainty...
We present an innovative end-to-end deep learning approach for jet identification at the LHC. The method combines deep neural networks with low-level detector information, such as calorimeter energy deposits and tracking information, to build a discriminator to identify different particles. Using two physics examples as references: electron and photon discrimination and quark and gluon...