Particle physicists have a long history of developing and applying machine learning (ML) techniques. From early applications of neural networks to charged particle tracking in the 1980s [1] to the Higgs boson discovery in 2012, in which boosted decision trees improved the sensitivity to the decay mode [2], ML has changed the way particle physicists conduct searches and measurements. It is an essential and versatile tool that we use to improve existing approaches, and it enables fundamentally new approaches. In recent years, the subfield of ML in particle physics has grown exponentially in the number of publications and expanded to cover a wide variety of topics and use cases, as indexed by the HEP ML Living Review [3]. In these proceedings, we present selected recent results that highlight how LHC experiments are applying novel ML techniques. In particular, we briefly describe the ML techniques and results for improved classification, faster simulation, unfolding, and anomaly detection.

It is well known that ignoring the presence of stochastic disturbances in the identification of stochastic Wiener models leads to asymptotically biased estimators. On the other hand, optimal statistical identification, via likelihood-based methods, is sensitive to the assumptions on the data distribution and is usually based on relatively complex sequential Monte Carlo algorithms. We develop a simple recursive online estimation algorithm based on an output-error predictor, for the identification of continuous-time stochastic parametric Wiener models through stochastic approximation. The method is applicable to generic model parameterizations and, as demonstrated in the numerical simulation examples, it is robust with respect to the assumptions on the spectrum of the disturbance process.

Planning and control for uncertain contact systems is challenging as it is not clear how to propagate uncertainty for planning. Contact-rich tasks can be modeled efficiently using complementarity constraints among other techniques. In this paper, we present a stochastic optimization technique with chance constraints for systems with stochastic complementarity constraints. We use a particle filter-based approach to propagate moments for stochastic complementarity system. To circumvent the issues of open-loop chance constrained planning, we propose a contact-aware controller for covariance steering of the complementarity system. Our optimization problem is formulated as Non-Linear Programming (NLP) using bilevel optimization. We present an important-particle algorithm for numerical efficiency for the underlying control problem. We verify that our contact-aware closed-loop controller is able to steer the covariance of the states under stochastic contact-rich tasks.

In neural network's Literature, Hebbian learning traditionally refers to the procedure by which the Hopfield model and its generalizations store archetypes (i.e., definite patterns that are experienced just once to form the synaptic matrix). However, the term "Learning" in Machine Learning refers to the ability of the machine to extract features from the supplied dataset (e.g., made of blurred examples of these archetypes), in order to make its own representation of the unavailable archetypes. Here, given a sample of examples, we define a supervised learning protocol by which the Hopfield network can infer the archetypes, and we detect the correct control parameters (including size and quality of the dataset) to depict a phase diagram for the system performance. We also prove that, for structureless datasets, the Hopfield model equipped with this supervised learning rule is equivalent to a restricted Boltzmann machine and this suggests an optimal and interpretable training routine. Finally, this approach is generalized to structured datasets: we highlight a quasi-ultrametric organization (reminiscent of replica-symmetry-breaking) in the analyzed datasets and, consequently, we introduce an additional "replica hidden layer" for its (partial) disentanglement, which is shown to improve MNIST classification from 75% to 95%, and to offer a new perspective on deep architectures.

To reduce carbon emissions, electrical power systems are Outside of the power systems community, novel machine increasingly incorporating renewable generation resources into learning techniques for partial differential equations (PDEs) the energy mix. These resources are often dependent on have been used to efficiently learn evolution equations for weather inputs and, as a result, they behave stochastically PDFs of system states. We refer to such equations as PDF in the short and long terms, posing planning and operational equations, and unlike the FPE [9], many are unclosed.

Influence maximization plays a key role in social network viral marketing. Although the problem has been widely studied, it is still challenging to estimate influence spread in big networks with hundreds of millions of nodes. Existing heuristic algorithms and greedy algorithms incur heavy computation cost in big networks and are incapable of processing dynamic network structures. In this paper, we propose an incremental algorithm for influence spread estimation in big networks. The incremental algorithm breaks down big networks into small subgraphs ad continuously estimate influence spread on these subgraphs as data streams. The challenge of the incremental algorithm is that subgraphs derived from a big network are not independent and MC simulations on each subgraph (defined as snapshots) may conflict with each other. In this paper, we assume that different combinations of MC simulations on subgraphs on subgraphs generate independent samples. In so doing, the incremental algorithm on streaming subgraphs can estimate influence spread with fewer simulations. Experimental results demonstrates the performance of the proposed algorithm.

This work presents a non-intrusive surrogate modeling scheme based on machine learning technology for predictive modeling of complex systems, described by parametrized time-dependent PDEs. For these problems, typical finite element approaches involve the spatiotemporal discretization of the PDE and the solution of the corresponding linear system of equations at each time step. Instead, the proposed method utilizes a convolutional autoencoder in conjunction with a feed forward neural network to establish a low-cost and accurate mapping from the problem's parametric space to its solution space. For this purpose, time history response data are collected by solving the high-fidelity model via FEM for a reduced set of parameter values. Then, by applying the convolutional autoencoder to this data set, a low-dimensional representation of the high-dimensional solution matrices is provided by the encoder, while the reconstruction map is obtained by the decoder. Using the latent representation given by the encoder, a feed-forward neural network is efficiently trained to map points from the problem's parametric space to the compressed version of the respective solution matrices. This way, the encoded response of the system at new parameter values is given by the neural network, while the entire response is delivered by the decoder. This approach effectively bypasses the need to serially formulate and solve the system's governing equations at each time increment, thus resulting in a significant cost reduction and rendering the method ideal for problems requiring repeated model evaluations or 'real-time' computations. The elaborated methodology is demonstrated on the stochastic analysis of time-dependent PDEs solved with the Monte Carlo method, however, it can be straightforwardly applied to other similar-type problems, such as sensitivity analysis, design optimization, etc.

Influence maximization (IM) is one of the most important problems in social network analysis. Its objective is to find a given number of seed nodes who maximize the spread of information through a social network. Since it is an NPhard problem, many approximate/heuristic methods have been developed, and a number of them repeats Monte Carlo (MC) simulations over and over, specifically tens of thousands of times or more, to reliably estimate the influence of a seed set, i.e., the number of infected nodes. In this work, we present an inductive machine learning method, called Mon te Carlo S imulator (MONSTOR), to predict the results of MC simulations on networks unseen during training. MONSTOR can greatly accelerate existing IM methods by replacing repeated MC simulations. In our experiments, MONSTOR achieves near-perfect accuracy on unseen real social networks with little sacrifice of accuracy in IM use cases. 1 Introduction Viral marketing via influence maximization has received considerable attention over the last two decades, as social networks have become an essential part of our daily lives. Many people connect to and acquire information from social networks on a daily basis, and thus information diffusion over such social networks is often more effective than that over conventional media, such as newspapers and television. Influence maximization (IM) is to find a certain number of seed nodes who maximize the spread of information through a social network. There exist several real-world applications where influence maximization played a key role, such as 2010 U.S. congressional elections, attempts to raise awareness about HIV among homeless youth, and so on [2, 18].