Machine learning (ML) encompasses a broad range of algorithms and modeling tools used for a vast array of data processing tasks, which has entered most scientific disciplines in recent years. This article reviews in a selective way the recent research on the interface between machine learning and the physical sciences. This includes conceptual developments in ML motivated by physical insights, applications of machine learning techniques to several domains in physics, and cross fertilization between the two fields. After giving a basic notion of machine learning methods and principles, examples are described of how statistical physics is used to understand methods in ML. This review then describes applications of ML methods in particle physics and cosmology, quantum many-body physics, quantum computing, and chemical and material physics. Research and development into novel computing architectures aimed at accelerating ML are also highlighted. Each of the sections describe recent successes as well as domain-specific methodology and challenges.

Machine learning and the physical sciences

A measurement of the ratio of branching fractions of the decays 
B
+
→
K
+
μ
+
μ
−
 and 
B
+
→
K
+
e
+
e
−
is presented. The proton-proton collision data used correspond to an integrated luminosity of 
5.0
 
 
fb
−
1
recorded with the LHCb experiment at center-of-mass energies of 7, 8, and 13 TeV. For the dilepton mass-squared range 
1.1
<
q
2
<
6.0
 
 
GeV
2
/
c
4
 the ratio of branching fractions is measured to be 
R
K
=
0.84
6
+
0.060
−
0.054
+
0.016
−
0.014
, where the first uncertainty is statistical and the second systematic. This is the most precise measurement of 
R
K
 to date and is compatible with the standard model at the level of 2.5 standard deviations.

/pdf/search-for-lepton-universality-violation-in-b-k-l-l-decays-2srktesra7.pdf

Search for Lepton-Universality Violation in B + →K + ℓ+ ℓ- Decays

Our knowledge of the fundamental particles of nature and their interactions is summarized by the standard model of particle physics Advancing our understanding in this field has required experiments that operate at ever higher energies and intensities, which produce extremely large and information-rich data samples The use of machine-learning techniques is revolutionizing how we interpret these data samples, greatly increasing the discovery potential of present and future experiments Here we summarize the challenges and opportunities that come with the use of machine learning at the frontiers of particle physics

/pdf/machine-learning-at-the-energy-and-intensity-frontiers-of-39f23mkiln.pdf

Machine learning at the energy and intensity frontiers of particle physics.

Searches are performed for both promptlike and long-lived dark photons, A^{'}, produced in proton-proton collisions at a center-of-mass energy of 13 TeV, using A^{'}→μ^{+}μ^{-} decays and a data sample corresponding to an integrated luminosity of 1.6  fb^{-1} collected with the LHCb detector. The promptlike A^{'} search covers the mass range from near the dimuon threshold up to 70 GeV, while the long-lived A^{'} search is restricted to the low-mass region 214<m(A^{'})<350  MeV. No evidence for a signal is found, and 90% confidence level exclusion limits are placed on the γ-A^{'} kinetic-mixing strength. The constraints placed on promptlike dark photons are the most stringent to date for the mass range 10.6<m(A^{'})<70  GeV, and are comparable to the best existing limits for m(A^{'})<0.5  GeV. The search for long-lived dark photons is the first to achieve sensitivity using a displaced-vertex signature.

/pdf/search-for-dark-photons-produced-in-13-tev-pp-collisions-4eazk7mb1k.pdf

Search for dark photons produced in 13 TeV $pp$ collisions

A key question for machine learning approaches in particle physics is how to best represent and learn from collider events. As an event is intrinsically a variable-length unordered set of particles, we build upon recent machine learning efforts to learn directly from sets of features or “point clouds”. Adapting and specializing the “Deep Sets” framework to particle physics, we introduce Energy Flow Networks, which respect infrared and collinear safety by construction. We also develop Particle Flow Networks, which allow for general energy dependence and the inclusion of additional particle-level information such as charge and flavor. These networks feature a per-particle internal (latent) representation, and summing over all particles yields an overall event-level latent representation. We show how this latent space decomposition unifies existing event representations based on detector images and radiation moments. To demonstrate the power and simplicity of this set-based approach, we apply these networks to the collider task of discriminating quark jets from gluon jets, finding similar or improved performance compared to existing methods. We also show how the learned event representation can be directly visualized, providing insight into the inner workings of the model. These architectures lend themselves to efficiently processing and analyzing events for a wide variety of tasks at the Large Hadron Collider. Implementations and examples of our architectures are available online in our EnergyFlow
 package.

/pdf/energy-flow-networks-deep-sets-for-particle-jets-3jnzudy72d.pdf

Energy Flow Networks: Deep Sets for Particle Jets

The main b-physics trigger algorithm used by the LHCb experiment is the so- called topological trigger. The topological trigger selects vertices which are a) detached from the primary proton-proton collision and b) compatible with coming from the decay of a b-hadron. In the LHC Run 1, this trigger, which utilized a custom boosted decision tree algorithm, selected a nearly 100% pure sample of b-hadrons with a typical efficiency of 60-70%; its output was used in about 60% of LHCb papers. This talk presents studies carried out to optimize the topological trigger for LHC Run 2. In particular, we have carried out a detailed comparison of various machine learning classifier algorithms, e.g., AdaBoost, MatrixNet and neural networks. The topological trigger algorithm is designed to select all 'interesting" decays of b-hadrons, but cannot be trained on every such decay. Studies have therefore been performed to determine how to optimize the performance of the classification algorithm on decays not used in the training. Methods studied include cascading, ensembling and blending techniques. Furthermore, novel boosting techniques have been implemented that will help reduce systematic uncertainties in Run 2 measurements. We demonstrate that the reoptimized topological trigger is expected to significantly improve on the Run 1 performance for a wide range of b-hadron decays.

/pdf/lhcb-topological-trigger-reoptimization-5umwnah9mu.pdf

LHCb Topological Trigger Reoptimization

The main b-physics trigger algorithm used by the LHCb experiment is the so-called topological trigger. The topological trigger selects vertices which are a) detached from the primary proton-proton collision and b) compatible with coming from the decay of a b-hadron. In the LHC Run 1, this trigger, which utilized a custom boosted decision tree algorithm, selected a nearly 100% pure sample of b-hadrons with a typical efficiency of 60-70%; its output was used in about 60% of LHCb papers. This talk presents studies carried out to optimize the topological trigger for LHC Run 2. In particular, we have carried out a detailed comparison of various machine learning classifier algorithms, e.g., AdaBoost, MatrixNet and neural networks. The topological trigger algorithm is designed to select all "interesting" decays of b-hadrons, but cannot be trained on every such decay. Studies have therefore been performed to determine how to optimize the performance of the classification algorithm on decays not used in the training. Methods studied include cascading, ensembling and blending techniques. Furthermore, novel boosting techniques have been implemented that will help reduce systematic uncertainties in Run 2 measurements. We demonstrate that the reoptimized topological trigger is expected to significantly improve on the Run 1 performance for a wide range of b-hadron decays.

Michael Williams

Papers

LHCb Topological Trigger Reoptimization

LHCb Topological Trigger Reoptimization

LHCb Topological Trigger Reoptimization