arXiv subjects

Tobias Golling

Publications and source records attributed to Tobias Golling.

At least 55 records · Page 3Linked to original sources

arXiv2023

The Mass-ive Issue: Anomaly Detection in Jet Physics

In the hunt for new and unobserved phenomena in particle physics, attention has turned in recent years to using advanced machine learning techniques for model independent searches. In this paper we highlight the main challenge of applying anomaly detection to jet physics, where preserving an unbiased estimator of the jet mass remains a critical piece of any model independent search. Using Variational Autoencoders and multiple industry-standard anomaly detection metrics, we demonstrate the unavoidable nature of this problem.

hep-ph↗

arXiv2023

CURTAINs for your Sliding Window: Constructing Unobserved Regions by Transforming Adjacent Intervals

We propose a new model independent technique for constructing background data templates for use in searches for new physics processes at the LHC. This method, called CURTAINs, uses invertible neural networks to parametrise the distribution of side band data as a function of the resonant observable. The network learns a transformation to map any data point from its value of the resonant observable to another chosen value. Using CURTAINs, a template for the background data in the signal window is constructed by mapping the data from the side-bands into the signal region. We perform anomaly detection using the CURTAINs background template to enhance the sensitivity to new physics in a bump hunt. We demonstrate its performance in a sliding window search across a wide range of mass values. Using the LHC Olympics dataset, we demonstrate that CURTAINs matches the performance of other leading approaches which aim to improve the sensitivity of bump hunts, can be trained on a much smaller range of the invariant mass, and is fully data driven.

hep-ph↗

arXiv2023

Flowification: Everything is a Normalizing Flow

The two key characteristics of a normalizing flow is that it is invertible (in particular, dimension preserving) and that it monitors the amount by which it changes the likelihood of data points as samples are propagated along the network. Recently, multiple generalizations of normalizing flows have been introduced that relax these two conditions. On the other hand, neural networks only perform a forward pass on the input, there is neither a notion of an inverse of a neural network nor is there one of its likelihood contribution. In this paper we argue that certain neural network architectures can be enriched with a stochastic inverse pass and that their likelihood contribution can be monitored in a way that they fall under the generalized notion of a normalizing flow mentioned above. We term this enrichment flowification. We prove that neural networks only containing linear layers, convolutional layers and invertible activations such as LeakyReLU can be flowified and evaluate them in the generative setting on image datasets.

cs.LG↗

arXiv2022

Decorrelation with conditional normalizing flows

The sensitivity of many physics analyses can be enhanced by constructing discriminants that preferentially select signal events. Such discriminants become much more useful if they are uncorrelated with a set of protected attributes. In this paper we show that a normalizing flow conditioned on the protected attributes can be used to find a decorrelated representation for any discriminant. As a normalizing flow is invertible the separation power of the resulting discriminant will be unchanged at any fixed value of the protected attributes. We demonstrate the efficacy of our approach by building supervised jet taggers that produce almost no sculpting in the mass distribution of the background.

hep-ph↗

arXiv2022

Variational Autoencoders for Anomalous Jet Tagging

We present a detailed study on Variational Autoencoders (VAEs) for anomalous jet tagging at the Large Hadron Collider. By taking in low-level jet constituents' information, and training with background QCD 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. When using the VAE as an anomaly detector, we present different approaches to detect anomalies: directly comparing in the input space or, instead, working in the latent space. In order to facilitate general search approaches such as bump-hunt, mass-decorrelated VAEs based on distance correlation regularization are also studied. We find that the naive mass-decorrelated VAEs fail at maintaining proper detection performance, by assigning higher probabilities to some anomalous samples. To build a performant mass-decorrelated anomalous jet tagger, we propose the Outlier Exposed VAE (OE-VAE), for which some outlier samples are introduced in the training process to guide the learned information. OE-VAEs are employed to achieve two goals at the same time: increasing sensitivity of outlier detection and decorrelating jet mass from the anomaly score. We succeed in reaching excellent results from both aspects. Code implementation of this work can be found at https://github.com/taolicheng/VAE-Jet

hep-ph↗

arXiv2022

Flows for Flows: Training Normalizing Flows Between Arbitrary Distributions with Maximum Likelihood Estimation

Normalizing flows are constructed from a base distribution with a known density and a diffeomorphism with a tractable Jacobian. The base density of a normalizing flow can be parameterised by a different normalizing flow, thus allowing maps to be found between arbitrary distributions. We demonstrate and explore the utility of this approach and show it is particularly interesting in the case of conditional normalizing flows and for introducing optimal transport constraints on maps that are constructed using normalizing flows.

cs.LG↗

arXiv2022

SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics

Deep learning methods have gained popularity in high energy physics for fast modeling of particle showers in detectors. Detailed simulation frameworks such as the gold standard Geant4 are computationally intensive, and current deep generative architectures work on discretized, lower resolution versions of the detailed simulation. The development of models that work at higher spatial resolutions is currently hindered by the complexity of the full simulation data, and by the lack of simpler, more interpretable benchmarks. Our contribution is SUPA, the SUrrogate PArticle propagation simulator, an algorithm and software package for generating data by simulating simplified particle propagation, scattering and shower development in matter. The generation is extremely fast and easy to use compared to Geant4, but still exhibits the key characteristics and challenges of the detailed simulation. We support this claim experimentally by showing that performance of generative models on data from our simulator reflects the performance on a dataset generated with Geant4. The proposed simulator generates thousands of particle showers per second on a desktop machine, a speed up of up to 6 orders of magnitudes over Geant4, and stores detailed geometric information about the shower propagation. SUPA provides much greater flexibility for setting initial conditions and defining multiple benchmarks for the development of models. Moreover, interpreting particle showers as point clouds creates a connection to geometric machine learning and provides challenging and fundamentally new datasets for the field. The code for SUPA is available at https://github.com/itsdaniele/SUPA.

physics.data-an↗

arXiv2021

Turbo-Sim: a generalised generative model with a physical latent space

We present Turbo-Sim, a generalised autoencoder framework derived from principles of information theory that can be used as a generative model. By maximising the mutual information between the input and the output of both the encoder and the decoder, we are able to rediscover the loss terms usually found in adversarial autoencoders and generative adversarial networks, as well as various more sophisticated related models. Our generalised framework makes these models mathematically interpretable and allows for a diversity of new ones by setting the weight of each loss term separately. The framework is also independent of the intrinsic architecture of the encoder and the decoder thus leaving a wide choice for the building blocks of the whole network. We apply Turbo-Sim to a collider physics generation problem: the transformation of the properties of several particles from a theory space, right after the collision, to an observation space, right after the detection in an experiment.

cs.LG↗

arXiv2021

Information-theoretic stochastic contrastive conditional GAN: InfoSCC-GAN

Conditional generation is a subclass of generative problems where the output of the generation is conditioned by the attribute information. In this paper, we present a stochastic contrastive conditional generative adversarial network (InfoSCC-GAN) with an explorable latent space. The InfoSCC-GAN architecture is based on an unsupervised contrastive encoder built on the InfoNCE paradigm, an attribute classifier and an EigenGAN generator. We propose a novel training method, based on generator regularization using external or internal attributes every $n$-th iteration, using a pre-trained contrastive encoder and a pre-trained classifier. The proposed InfoSCC-GAN is derived based on an information-theoretic formulation of mutual information maximization between input data and latent space representation as well as latent space and generated data. Thus, we demonstrate a link between the training objective functions and the above information-theoretic formulation. The experimental results show that InfoSCC-GAN outperforms the "vanilla" EigenGAN in the image generation on AFHQ and CelebA datasets. In addition, we investigate the impact of discriminator architectures and loss functions by performing ablation studies. Finally, we demonstrate that thanks to the EigenGAN generator, the proposed framework enjoys a stochastic generation in contrast to vanilla deterministic GANs yet with the independent training of encoder, classifier, and generator in contrast to existing frameworks. Code, experimental results, and demos are available online at https://github.com/vkinakh/InfoSCC-GAN.

cs.CV↗

arXiv2021

Funnels: Exact maximum likelihood with dimensionality reduction

Normalizing flows are diffeomorphic, typically dimension-preserving, models trained using the likelihood of the model. We use the SurVAE framework to construct dimension reducing surjective flows via a new layer, known as the funnel. We demonstrate its efficacy on a variety of datasets, and show it improves upon or matches the performance of existing flows while having a reduced latent space size. The funnel layer can be constructed from a wide range of transformations including restricted convolution and feed forward layers.

cs.LG↗

arXiv2021

The Tracking Machine Learning challenge : Throughput phase

This paper reports on the second "Throughput" phase of the Tracking Machine Learning (TrackML) challenge on the Codalab platform. As in the first "Accuracy" phase, the participants had to solve a difficult experimental problem linked to tracking accurately the trajectory of particles as e.g. created at the Large Hadron Collider (LHC): given O($10^5$) points, the participants had to connect them into O($10^4$) individual groups that represent the particle trajectories which are approximated helical. While in the first phase only the accuracy mattered, the goal of this second phase was a compromise between the accuracy and the speed of inference. Both were measured on the Codalab platform where the participants had to upload their software. The best three participants had solutions with good accuracy and speed an order of magnitude faster than the state of the art when the challenge was designed. Although the core algorithms were less diverse than in the first phase, a diversity of techniques have been used and are described in this paper. The performance of the algorithms are analysed in depth and lessons derived.

cs.LG↗

arXiv2021

The Tracking Machine Learning challenge : Accuracy phase

This paper reports the results of an experiment in high energy physics: using the power of the "crowd" to solve difficult experimental problems linked to tracking accurately the trajectory of particles in the Large Hadron Collider (LHC). This experiment took the form of a machine learning challenge organized in 2018: the Tracking Machine Learning Challenge (TrackML). Its results were discussed at the competition session at the Neural Information Processing Systems conference (NeurIPS 2018). Given 100.000 points, the participants had to connect them into about 10.000 arcs of circles, following the trajectory of particles issued from very high energy proton collisions. The competition was difficult with a dozen front-runners well ahead of a pack. The single competition score is shown to be accurate and effective in selecting the best algorithms from the domain point of view. The competition has exposed a diversity of approaches, with various roles for Machine Learning, a number of which are discussed in the document

hep-ex↗

arXiv2021

Hashing and metric learning for charged particle tracking

We propose a novel approach to charged particle tracking at high intensity particle colliders based on Approximate Nearest Neighbors search. With hundreds of thousands of measurements per collision to be reconstructed e.g. at the High Luminosity Large Hadron Collider, the currently employed combinatorial track finding approaches become inadequate. Here, we use hashing techniques to separate measurements into buckets of 20-50 hits and increase their purity using metric learning. Two different approaches are studied to further resolve tracks inside buckets: Local Fisher Discriminant Analysis and Neural Networks for triplet similarity learning. We demonstrate the proposed approach on simulated collisions and show significant speed improvement with bucket tracking efficiency of 96% and a fake rate of 8% on unseen particle events.

hep-ex↗

arXiv2019

Machine Learning in High Energy Physics Community White Paper

Machine learning has been applied to several problems in particle physics research, beginning with applications to high-level physics analysis in the 1990s and 2000s, followed by an explosion of applications in particle and event identification and reconstruction in the 2010s. In this document we discuss promising future research and development areas for machine learning in particle physics. We detail a roadmap for their implementation, software and hardware resource requirements, collaborative initiatives with the data science community, academia and industry, and training the particle physics community in data science. The main objective of the document is to connect and motivate these areas of research and development with the physics drivers of the High-Luminosity Large Hadron Collider and future neutrino experiments and identify the resource needs for their implementation. Additionally we identify areas where collaboration with external communities will be of great benefit.

physics.comp-ph↗

arXiv2019

Searching for long-lived particles beyond the Standard Model at the Large Hadron Collider

Particles beyond the Standard Model (SM) can generically have lifetimes that are long compared to SM particles at the weak scale. When produced at experiments such as the Large Hadron Collider (LHC) at CERN, these long-lived particles (LLPs) can decay far from the interaction vertex of the primary proton-proton collision. Such LLP signatures are distinct from those of promptly decaying particles that are targeted by the majority of searches for new physics at the LHC, often requiring customized techniques to identify, for example, significantly displaced decay vertices, tracks with atypical properties, and short track segments. Given their non-standard nature, a comprehensive overview of LLP signatures at the LHC is beneficial to ensure that possible avenues of the discovery of new physics are not overlooked. Here we report on the joint work of a community of theorists and experimentalists with the ATLAS, CMS, and LHCb experiments --- as well as those working on dedicated experiments such as MoEDAL, milliQan, MATHUSLA, CODEX-b, and FASER --- to survey the current state of LLP searches at the LHC, and to chart a path for the development of LLP searches into the future, both in the upcoming Run 3 and at the High-Luminosity LHC. The work is organized around the current and future potential capabilities of LHC experiments to generally discover new LLPs, and takes a signature-based approach to surveying classes of models that give rise to LLPs rather than emphasizing any particular theory motivation. We develop a set of simplified models; assess the coverage of current searches; document known, often unexpected backgrounds; explore the capabilities of proposed detector upgrades; provide recommendations for the presentation of search results; and look towards the newest frontiers, namely high-multiplicity "dark showers", highlighting opportunities for expanding the LHC reach for these signals.

hep-ex↗

arXiv2018

Charge collection characterisation with the Transient Current Technique of the ams H35DEMO CMOS detector after proton irradiation

This paper reports on the characterisation with Transient Current Technique measurements of the charge collection and depletion depth of a radiation-hard high-voltage CMOS pixel sensor produced at ams AG. Several substrate resistivities were tested before and after proton irradiation with two different sources: the 24 GeV Proton Synchrotron at CERN and the 16.7 MeV Cyclotron at Bern Inselspital.

physics.ins-det↗

arXiv2014

SUSY Simplified Models at 14, 33, and 100 TeV Proton Colliders

Results are presented for a variety of SUSY Simplified Models at the 14 TeV LHC as well as a 33 and 100 TeV proton collider. Our focus is on models whose signals are driven by colored production. We present projections of the upper limit and discovery reach in the gluino-neutralino (for both light and heavy flavor decays), squark-neutralino, and gluino-squark Simplified Model planes. Depending on the model a jets + MET, mono-jet, or same-sign di-lepton search is applied. The impact of pileup is explored. This study utilizes the Snowmass backgrounds and combined detector. Assuming 3000 fb^{-1} of integrated luminosity, a gluino that decays to light flavor quarks can be discovered below 2.3 TeV at the 14 TeV LHC and below 11 TeV at a 100 TeV machine.

hep-ph↗

arXiv2013

A Comparison of Future Proton Colliders Using SUSY Simplified Models: A Snowmass Whitepaper

We present a summary of results for SUSY Simplified Model searches at future proton colliders: the 14 TeV LHC as well as a 33 TeV proton collider and a 100 TeV proton collider. Upper limits and discovery significances are provided for the gluino-neutralino (for both light and heavy flavor decays), squark-neutralino, and gluino-squark Simplified Model planes. Events are processed with the Snowmass combined detector and Standard Model backgrounds are computed using the Snowmass samples. We place emphasis on comparisons between different collider scenarios, along with the lessons learned regarding the impact of systematic errors and pileup. More details are provided in a companion paper.

hep-ph↗