Weakly Supervised Classification For High Energy Physics

Dery, Lucio M.; Nachman, B. P.; Rubbo, F.; Schwartzman, A.

doi:10.1088/1742-6596/1085/4/042006

Cited by 4 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…using boosted decision trees (BDTs) on calculated features for doing ID classification and energy regression. Indeed, ML has long been applied to various tasks in HEP [1][2][3], but has recently seen much wider application [4][5][6][7][8][9], including the 2012 discovery of the Higgs boson [10,11] at the ATLAS [12] and CMS [13] experiments at the Large Hadron Collider (LHC).…”

Section: Overviewmentioning

confidence: 99%

Calorimetry with deep learning: particle simulation and reconstruction for collider physics

et al. 2020

View full text Add to dashboard Cite

Using detailed simulations of calorimeter showers as training data, we investigate the use of deep learning algorithms for the simulation and reconstruction of single isolated particles produced in high-energy physics collisions. We train neural networks on single-particle shower data at the calorimeter-cell level, and show significant improvements for simulation and reconstruction when using these networks compared to methods which rely on currently-used state-of-the-art algorithms. We define two models: an end-to-end reconstruction network which performs simultaneous particle identification and energy regression of particles when given calorimeter shower data, and a generative network which can provide reasonable modeling of calorimeter showers for different particle types at specified angles and energies. We investigate the optimization of our models with hyperparameter scans. Furthermore, we demonstrate the applicability of the reconstruction model to shower inputs from other detector geometries, specifically ATLAS-like and CMS-like geometries. These networks can serve as fast and computationally light methods for particle shower simulation and reconstruction for current and future experiments at particle colliders.

show abstract

Section: Overviewmentioning

confidence: 99%

Calorimetry with deep learning: particle simulation and reconstruction for collider physics

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In the collider physics context many studies have been published in recent years that attempt to parametrize the concept of anomalousness in data using unsupervised machine learning -see refs. [20][21][22][23][24][25][26][27][28][29][30][31][32][33]. These…”

Section: Introductionmentioning

confidence: 98%

A semi-supervised approach to dark matter searches in direct detection data with machine learning

Herrero-García

Patrick

Scaffidi

2022

J. Cosmol. Astropart. Phys.

View full text Add to dashboard Cite

The dark matter sector remains completely unknown. It is therefore crucial to keep an open mind regarding its nature and possible interactions. Focusing on the case of Weakly Interacting Massive Particles, in this work we make this general philosophy more concrete by applying modern machine learning techniques to dark matter direct detection. We do this by encoding and decoding the graphical representation of background events in the XENONnT experiment with a convolutional variational autoencoder. We describe a methodology that utilizes the `anomaly score' derived from the reconstruction loss of the convolutional variational autoencoder as well as a pre-trained standard convolutional neural network, in a semi-supervised fashion. Indeed, we observe that optimum results are obtained only when both unsupervised and supervised anomaly scores are considered together. A data set that has a higher proportion of anomaly score is deemed anomalous and deserves further investigation. Contrary to classical analyses, in principle all information about the events is used, preventing unnecessary information loss. Lastly, we demonstrate the reach of learning-focused anomaly detection in this context by comparing results with classical inference, observing that, if tuned properly, these techniques have the potential to outperform likelihood-based methods.

show abstract

“…The LLP problem is motivated by a number of applications where access to individual examples is too expensive or impossible to achieve, or available at aggregate level for privacy-preserving reasons. Examples include ecommerce, fraud detection, medical databases (Patrini et al, 2014), high energy physics (Dery et al, 2018), election prediction (Sun et al, 2017), medical image analysis (Bortsova et al, 2018), remote sensing (Ding et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Easy Learning from Label Proportions

Busa-Fekete¹,

Choi²,

Dick³

et al. 2023

Preprint

View full text Add to dashboard Cite

We consider the problem of Learning from Label Proportions (LLP), a weakly supervised classification setup where instances are grouped into "bags", and only the frequency of class labels at each bag is available. Albeit, the objective of the learner is to achieve low task loss at an individual instance level. Here we propose EASYLLP: a flexible and simple-to-implement debiasing approach based on aggregate labels, which operates on arbitrary loss functions. Our technique allows us to accurately estimate the expected loss of an arbitrary model at an individual level. We showcase the flexibility of our approach by applying it to popular learning frameworks, like Empirical Risk Minimization (ERM) and Stochastic Gradient Descent (SGD) with provable guarantees on instance level performance. More concretely, we exhibit a variance reduction technique that makes the quality of LLP learning deteriorate only by a factor of k (k being bag size) in both ERM and SGD setups, as compared to full supervision. Finally, we validate our theoretical results on multiple datasets demonstrating our algorithm performs as well or better than previous LLP approaches in spite of its simplicity.

show abstract

Weakly Supervised Classification For High Energy Physics

Cited by 4 publications

References 9 publications

Calorimetry with deep learning: particle simulation and reconstruction for collider physics

Calorimetry with deep learning: particle simulation and reconstruction for collider physics

A semi-supervised approach to dark matter searches in direct detection data with machine learning

Easy Learning from Label Proportions

Contact Info

Product

Resources

About