Arrival / Registration

Welcome from Lorentz Center

Welcome, Workshop Structure and Objectives

• Sascha Caron (Nikhef National institute for subatomic physics (NL))

Dark Matter overview

• Nicolao Fornengo (University of Torino and INFN)

Introduction into Deep Learning and Image Analysis

• Max Welling

First ideas to connect Astronomical data, Deep Learning and Image Analysis

• German Gomez-Vargas (Pontifical Catholic University of Chile)
• German Arturo Gomez Vargas (Universidad Autonoma de Madrid)

Discussion: First connections ?

Cross link: Deep Learning in High Energy Physics

• Amir Farbin (University of Texas at Arlington (US))

Discussion: New ideas ? Bring up projects --> Bring up a discussion ... We can vote which one we should open. Decide on the projects (darksurvey.com) Suggest new application of Deep Learning / Image Analysis. Suggest topic for brainstorming session.

Work in subgroups : Finding new projects in Deep Learning / Image Analysis Person proposing the subject + Organiser + Participants split up in 2-4 rooms. Work on 5 min presentation about the topic.

The hunt for stellar-mass DM clumps: applying the statistical machine learning techniques to strong microlensing events

• Elena Fedorova

Strong gravitational microlensing (GM) events give us a possibility to determine some characteristics of both microlens and microlensed source. As the role of microlens can be played by a DM clump, GM can give us an important clue to understand the nature of dark matter on comparably small spatial/mass scales. In the same time, fitting the lightcurves of microlensed sources is quite time-consuming process, especially taking into account nonzero lens size. Here we test the possibility to apply the statistical machine learning techniques to distinguish high-amplification microlensing events (HAME) caused by continuously distributed DM clump from star- or black hole- induced microlensing (i.e. microlens is considered as a point-like mass). On this stage we use the set of simulated HAE amplification curves of sources microlensed by point masses and clumps of DM with various density profiles.

Fast model discrimination with Euclideanized signals

• Christoph Weniger (University of Amsterdam)

Results of yesterdays workgroups on Deep Learning, Image Analysis and astronomical Dark Matter data

Astronomical Dark Matter measurements and Challenges

• David Richard Harvey (EPFL - EPF Lausanne)

Introduction into direct and indirect Dark Matter searches and their challenges

• Marco Regis (INFN - National Institute for Nuclear Physics)
• Marco Regis

Introduction into unsupervised learning

• Erzsébet Merényi

Discussion Unsupervised Leaning for Dark Matter

First ideas to use Machine Learning in direct Dark Matter searches

• Christopher Tunnell (Enrico Fermi Institute-University of Chicago-Unknown)
• Andrew Brown (MIT)
• Christopher Tunnell (University of Chicago)
• Andrew Brown (Nikhef)

Discussion: New ideas ?

First ideas to use Machine Learning in indirect detection

• Luc Hendriks (Nikhef)

Discussion: New ideas?

Work in subgroups

Characterization of the Local Universe via angular cross-correlations

• Simone Ammazzalorso (University of Turin)

Dark matter searches in dwarf irregular galaxies

• Viviana Gammaldi (SISSA)

Results of yesterdays workgroups on unsupervised learning, direct and indirect DM searches

New approaches in semi-supervised learning

• Kristiaan Pelckmans

First ideas: Supervised DNNs for reconstruction in LHC data

• Markus Stoye (CERN)

Recent results : Dark Matter searches at LHC

• Renjie Wang (LPNHE-Paris CNRS/IN2P3 (FR))
• Renjie Wang (LPNHE-Paris, CNRS/IN2P3 (FR))

Machine Learning for SHiP and NEWS experiments

• Andrey Ustyuzhanin (Yandex School of Data Analysis (RU))

Emulsion-based detectors such as ones used for OPERA experiment or planned for SHiP and NEWS experiments may reveal important characteristics of WIMP-like particles. However due to the nature of the emulsion, the signal to noise ratio tend to be rather small and hence might require special reconstruction techniques. Thus advanced data analysis approaches based on machine learning approaches might improve «physical» sensitivity of the experiments. In this talk I’ll give brief overview of machine learning techniques that can be applied for dark matter searches in SHiP and NEWS experiments and present current challenges for those experiments both from physical and data analysis points of view.

Miscellaneous thoughts on Machine Learning & Dark Matter

• Kyle Stuart Cranmer (New York University (US))

Discussion: New ideas? Reinforcement Learning?

Work on projects in subgroups

Data-driven constraints on dark matter from dwarf galaxies

• Bryan Zaldivar (LAPTh, Annecy)

Fast Forecasting for Counting Experiments

• Tom Edwards

Estimating the parameters of gravitational lenses with deep learning

• laurence perreault levasseur (Stanford University)

Machine learning methods have seen a rapid expansion in the last few years. In particular, deep learning has made several breakthroughs, including beating a champion of game of Go and outperforming practicing dermatologists in the visual diagnosis of skin cancer. Although in most applications these networks have been used for classification tasks, they can also be made to predict real-valued model parameters. In this talk, I will discuss our results on using deep convolutional neural networks to estimate the parameters of strong gravitational lenses from telescope data. Estimating these parameters with traditional maximum-likelihood modeling methods is a time and resource consuming procedure, involving several data preparation steps and a difficult optimization process. With deep convolutional neural networks we are able to estimate these parameters in a fully automated way 10 million times faster than traditional modeling methods and with a similar accuracy. I will also discuss how to robustly quantify the uncertainties of these networks. This allows them to be a fast alternative to MCMC sampling. With the advent of large volumes of data from upcoming ground and space surveys and the remarkable speed offered by these networks, deep learning promises to become an indispensable tool for the analysis of large survey data.

Results of yesterdays workgroups on supervised learning and DM searches at the LHC

Introduction into theory models for Dark Matter particles

• Andrea de Simone

OpenML/AutoML: Organizing machine learning data and learning to learn better models

• Joaquin Vanschoren

Adversarial Games for Particle Physics

• Gilles Louppe (New York University (US))

Discussion: Further ideas?

Dark Matter model exploration and first ML ideas

• Martin John White (University of Adelaide (AU))

How to find Natural Supersymmetric Dark Matter?

• Melissa van Beekveld (R)

Supersymmetry (SUSY) is able to solve the hierarchy problem and it can provide a perfect dark matter candidate. The non-observation of SUSY particles at the LHC and dark matter particles at dedicated experiments drives the SUSY particles to be heavier and heavier, which is assumed to make it more and more difficult for SUSY to solve the hierarchy problem as it gives rise to the need of fine-tuning of the input parameters of the theory. We are studying the allowed parameter space of several SUSY models. These models typically have a large number of parameters (10-30). We aim to find the set of allowed parameters that minimize the fine-tuning of these SUSY models. This is a resource-consuming process and we would like to discuss on how to do this more efficiently.

BSM-AI (SUSY-AI) and iDarkSurvey: Learning (from) high-dimensional models

• Bob Stienen (Radboud University)

Although the standard model of particle physics is successful in describing physics as we know it, it is known to be incomplete. Many models have been developed to extend the standard model, none of which have been experimentally verified. One of the main hurdles in this effort is the dimensionality of these models, yielding problems in analysing, visualising and communicating results. Because of this, most current day analyses are done using simplified models, but in this process descriptive power is lost. However, by using machine learning on simulated model points, we show that we can overcome these problems and predict both binary exclusion an continuous likelihood in any parameter space. This simulated data will be stored in our new webbased database and model visualisation tool iDarkSurvey. This tool will be open to the scientific to store all calculated model data.

Using Deep Learning to predict Electroweakino production cross-sections at the LHC

• Sydney Otten (RWTH Aachen)

Discussion: New ideas?

Work in subgroups

Open discussion: what have we leart? What next?