ML4Jets2020

Session

Anomaly detection (LHCO)

16 Jan 2020, 14:20

KC 802 (Kimmel Center for University Life)

Conveners

Anomaly detection (LHCO)

• Gregor Kasieczka (Hamburg University (DE))
• David Shih (Rutgers University)

65. LHCO Introduction and overview

David Shih (Rutgers University), Gregor Kasieczka (Hamburg University (DE))

16/01/2020, 14:30

5. Unsupervised new physics searches with data-driven inference

Dr Dillon Barry (Jozef Stefan Institute)

16/01/2020, 14:50

We have developed a framework for performing unsupervised new physics searches using jet substructure in di-jet events, where the likelihood functions are inferred in a data-driven manner. This framework is based on a machine learning algorithm called Latent Dirichlet Allocation, a statistical model initially used for describing the topical structure of documents. In this talk I will present...

13. Tag N’ Train : Combining Autoencoders and CWoLa for Better Unsupervised Searches

Oz Amram (Johns Hopkins University (US))

16/01/2020, 15:10

As our jet classifiers grow in complexity, limitations in simulating QCD will start to bottleneck our ability to train classifiers that perform as well on data as they do in simulation. One proposed approach to avoid this problem is the CWoLa method, in which the classifier is trained directly on data to distinguish between statistical mixtures of classes. The main challenge when applying...

19. Variational Autoencoders for Anomalous Jet Tagging

Taoli Cheng (University of Montreal)

16/01/2020, 15:30

We present a detailed study on Variational Autoencoders (VAEs) performing in anomalous jet tagging. By taking in low-level jet constituents' information, and only training with background jets in an unsupervised manner, the VAE is able to encode important information for reconstructing jets, while learning an expressive posterior distribution in the latent space. The encoder (inference) and...

71. Comparing weak and unsupervised anomaly detection

Pablo Martín

16/01/2020, 16:20

A comparison of CWoLa hunting and autoencoders.

40. LHC Olympics 2020: Columbia University

Alan Mathew Kahn (Columbia University (US))

16/01/2020, 16:40

We present results of an anomaly detection method via sequence modeling.

27. LHC Olympics 2020: MIT

Nilai Sarda (MIT)

16/01/2020, 17:00

<empty>

73. LHC Olympics 2020: Berkeley Cosmology

George Stein

16/01/2020, 17:20

75. LHCO2020: Outcome of the Challenge

Ben Nachman (Lawrence Berkeley National Lab. (US)), Gregor Kasieczka (Hamburg University (DE)), David Shih (Rutgers University)

16/01/2020, 17:40

We will unveil the answer to Black Box 1 and discuss the outcomes of the challenge. Note that there are two talks here - one that was hurriedly prepared for the unveiling of the results at the time of the challenge and a second, polished set of slides that we have prepared without time pressure after the workshop.

32. LHC Olympics 2020: Team UERJ Physics

Clemencia Mora Herrera (Universidade do Estado do Rio de Janeiro (BR))

Implementation is still in progress. In principle Deep Neural Networks with Keras.

57. LHC Olympics 2020: Berkeley Cosmo

Uros Seljak

LHCO

44. LHC Olympics 2020: DA

Huilin Qu (Univ. of California Santa Barbara (US))

In progress.

54. LHC Olympics 2020: HKUST

Ying-Ying Li

LHCO

37. LHC Olympics 2020: pWolk

Ferdinand Schenck (Humboldt University of Berlin (DE))

Empty until strategy is solidified

67. LHCO

Julien Noce Donini (Université Clermont Auvergne (FR))

LHCO

68. LHCO

Sang Eon Park (Massachusetts Inst. of Technology (US))

MIT LHCO hep-ex group

38. Outlier Exposure for the BSM searches at LHC

Charanjit Kaur

In this talk, I will discuss the application of the Outlier Exposure technique for searching the physics beyond the standard model at LHC. Outlier exposure is an efficient technique to detect and generalize the hidden anomalies in the data. The method has been tested on multi-class data and has proven capable of detecting anomalies which were not part of the original training data. I will...