arXiv subjects

Amit Chakraborty

Publications and source records attributed to Amit Chakraborty.

At least 37 records · Page 2Linked to original sources

arXiv2024

Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control

In this paper, we introduce Symplectic ODE-Net (SymODEN), a deep learning framework which can infer the dynamics of a physical system, given by an ordinary differential equation (ODE), from observed state trajectories. To achieve better generalization with fewer training samples, SymODEN incorporates appropriate inductive bias by designing the associated computation graph in a physics-informed manner. In particular, we enforce Hamiltonian dynamics with control to learn the underlying dynamics in a transparent way, which can then be leveraged to draw insight about relevant physical aspects of the system, such as mass and potential energy. In addition, we propose a parametrization which can enforce this Hamiltonian formalism even when the generalized coordinate data is embedded in a high-dimensional space or we can only access velocity data instead of generalized momentum. This framework, by offering interpretable, physically-consistent models for physical systems, opens up new possibilities for synthesizing model-based control strategies.

cs.LG↗

arXiv2023

RANS-PINN based Simulation Surrogates for Predicting Turbulent Flows

Physics-informed neural networks (PINNs) provide a framework to build surrogate models for dynamical systems governed by differential equations. During the learning process, PINNs incorporate a physics-based regularization term within the loss function to enhance generalization performance. Since simulating dynamics controlled by partial differential equations (PDEs) can be computationally expensive, PINNs have gained popularity in learning parametric surrogates for fluid flow problems governed by Navier-Stokes equations. In this work, we introduce RANS-PINN, a modified PINN framework, to predict flow fields (i.e., velocity and pressure) in high Reynolds number turbulent flow regimes. To account for the additional complexity introduced by turbulence, RANS-PINN employs a 2-equation eddy viscosity model based on a Reynolds-averaged Navier-Stokes (RANS) formulation. Furthermore, we adopt a novel training approach that ensures effective initialization and balance among the various components of the loss function. The effectiveness of the RANS-PINN framework is then demonstrated using a parametric PINN.

cs.LG↗

arXiv2023

Flavon Signatures at the HL-LHC

The detection of a single Higgs boson at the Large Hadron Collider (LHC) has allowed one to probe some properties of it, including the Yukawa and gauge couplings. However, in order to probe the Higgs potential, one has to rely on new production mechanisms, such as Higgs pair production. In this paper, we show that such a channel is also sensitive to the production and decay of a so-called `Flavon' field ($H_F$), a new scalar state that arises in models that attempt to explain the hierarchy of the Standard Model (SM) fermion masses. Our analysis also focuses on the other decay channels involving the Flavon particle, specifically the decay of the Flavon to a pair of $Z$ bosons ($H_F \to Z Z$) and the concurrent production of a top quark and charm quark ($H_F\to tc$), having one or more leptons in the final states. In particular, we show that, with 3000 fb$^{-1}$ of accumulated data at 14 TeV (the Run 3 stage) of the LHC an heavy Flavon $H_F$ with mass $M_{H_F} \simeq 2m_t $ can be explored with $3σ-5σ$ significance through these channels.

hep-ph↗

arXiv2023

Tagging a Boosted Top quark with a $τ$ final state

Boosted top quark tagging is one of the challenging, and at the same time exciting, tasks in high energy physics experiments, in particular in the exploration of new physics signals at the LHC. Several techniques have already been developed to tag a boosted top quark in its hadronic decay channel. Recently tagging the same in the semi-leptonic channel has begun to receive a lot of attention. In the current study, we develop a methodology to tag a boosted top quark ($p_T>$ 200 GeV) in its semi-leptonic decay channel with a $τ$-lepton in the final state. In this analysis, the constituents of the top fatjet are reclustered using jet substructure technique to obtain the subjets, and then $b$- and $τ$- like subjets are identified by applying standard $b$- and $τ$-jet identification algorithms. We show that the dominant QCD background can be rejected effectively using several kinematic variables of these subjects, such as energy sharing among the jets, invariant mass, transverse mass, Nsubjettiness etc., leading to high signal tagging efficiencies. We further assess possible improvements in the results by employing multivariate analysis techniques. We find that using this proposed top-tagger, a signal efficiency of $\sim 77\%$ against a background efficiency of $\sim 3\%$ can be achieved. We also extend the proposed top-tagger to the case of polarized top quarks by introducing a few additional observables calculated in the rest frame of the $b-τ$ system. We comment on how the same methodology will be useful for tagging a boosted heavy BSM particle with a $b$ and $τ$ in the final state.

hep-ph↗

arXiv2023

Benchmarking Energy-Conserving Neural Networks for Learning Dynamics from Data

The last few years have witnessed an increased interest in incorporating physics-informed inductive bias in deep learning frameworks. In particular, a growing volume of literature has been exploring ways to enforce energy conservation while using neural networks for learning dynamics from observed time-series data. In this work, we survey ten recently proposed energy-conserving neural network models, including HNN, LNN, DeLaN, SymODEN, CHNN, CLNN and their variants. We provide a compact derivation of the theory behind these models and explain their similarities and differences. Their performance are compared in 4 physical systems. We point out the possibility of leveraging some of these energy-conserving models to design energy-based controllers.

cs.LG↗

arXiv2023

Fat $b$-Jet Analyses Using Old and New Clustering Algorithms in New Higgs Boson Searches at the LHC

We compare different jet-clustering algorithms in establishing fully hadronic final states stemming from the chain decay of a heavy Higgs state into a pair of the 125 GeV Higgs boson that decays into bottom-antibottom quark pairs. Such 4$b$ events typically give rise to boosted topologies, wherein bottom-antibottom quark pairs emerging from each 125 GeV Higgs boson tend to merge into a single, fat $b$-jet. Assuming Large Hadron Collider (LHC) settings, we illustrate how both the efficiency of selecting the multi-jet final state and the ability to reconstruct from it the masses of all Higgs bosons depend on the choice of jet-clustering algorithm and its parameter settings. We indicate the optimal choice of clustering method for the purpose of establishing such a ubiquitous Beyond the SM (BSM) signal, illustrated via a Type-II 2-Higgs Doublet Model (2HDM).

hep-ph↗

arXiv2022

A Neural ODE Interpretation of Transformer Layers

Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning problems. As the transformer layers use residual connections to avoid the problem of vanishing gradients, they can be viewed as the numerical integration of a differential equation. In this extended abstract, we build upon this connection and propose a modification of the internal architecture of a transformer layer. The proposed model places the multi-head attention sublayer and the MLP sublayer parallel to each other. Our experiments show that this simple modification improves the performance of transformer networks in multiple tasks. Moreover, for the image classification task, we show that using neural ODE solvers with a sophisticated integration scheme further improves performance.

cs.LG↗

arXiv2022

Re-evaluating Jet Reconstruction Techniques for New Higgs Boson Searches

The ultimate motivation of our study is to look for signs of physics beyond the Standard Model (BSM). We investigate whether different jet clustering techniques might be more or less suited to the particular final states of interest. In particular, we are interested in fully hadronic final states emerging from the decay chain of the Standard Model like Higgs boson into pairs of light Higgs states, the latter in turn decaying into bottom-anti bottom pairs. We show that, the ability of selecting the multi-jet final state and to reconstruct invariant masses of the Higgs bosons from it depend strongly on the choice of acceptance cuts, resolution parameters and reconstruction algorithm as well as its settings. Hence, we indicate the optimal choice of the latter for the purpose of establishing such a benchmark as a BSM signal. We then repeat the exercise for a heavy Higgs boson cascading into two SM-like Higgs states, obtaining similar results.

hep-ph↗

arXiv2022

Physics-informed neural networks for modeling rate- and temperature-dependent plasticity

This work presents a physics-informed neural network (PINN) based framework to model the strain-rate and temperature dependence of the deformation fields in elastic-viscoplastic solids. To avoid unbalanced back-propagated gradients during training, the proposed framework uses a simple strategy with no added computational complexity for selecting scalar weights that balance the interplay between different terms in the physics-based loss function. In addition, we highlight a fundamental challenge involving the selection of appropriate model outputs so that the mechanical problem can be faithfully solved using a PINN-based approach. We demonstrate the effectiveness of this approach by studying two test problems modeling the elastic-viscoplastic deformation in solids at different strain rates and temperatures, respectively. Our results show that the proposed PINN-based approach can accurately predict the spatio-temporal evolution of deformation in elastic-viscoplastic materials.

cond-mat.mtrl-sci↗

arXiv2022

EMVLight: A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles

Emergency vehicles (EMVs) play a crucial role in responding to time-critical events such as medical emergencies and fire outbreaks in an urban area. The less time EMVs spend traveling through the traffic, the more likely it would help save people's lives and reduce property loss. To reduce the travel time of EMVs, prior work has used route optimization based on historical traffic-flow data and traffic signal pre-emption based on the optimal route. However, traffic signal pre-emption dynamically changes the traffic flow which, in turn, modifies the optimal route of an EMV. In addition, traffic signal pre-emption practices usually lead to significant disturbances in traffic flow and subsequently increase the travel time for non-EMVs. In this paper, we propose EMVLight, a decentralized reinforcement learning (RL) framework for simultaneous dynamic routing and traffic signal control. EMVLight extends Dijkstra's algorithm to efficiently update the optimal route for the EMVs in real time as it travels through the traffic network. The decentralized RL agents learn network-level cooperative traffic signal phase strategies that not only reduce EMV travel time but also reduce the average travel time of non-EMVs in the network. This benefit has been demonstrated through comprehensive experiments with synthetic and real-world maps. These experiments show that EMVLight outperforms benchmark transportation engineering techniques and existing RL-based signal control methods.

cs.LG↗

arXiv2022

Demystifying the Data Need of ML-surrogates for CFD Simulations

Computational fluid dynamics (CFD) simulations, a critical tool in various engineering applications, often require significant time and compute power to predict flow properties. The high computational cost associated with CFD simulations significantly restricts the scope of design space exploration and limits their use in planning and operational control. To address this issue, machine learning (ML) based surrogate models have been proposed as a computationally efficient tool to accelerate CFD simulations. However, a lack of clarity about CFD data requirements often challenges the widespread adoption of ML-based surrogates among design engineers and CFD practitioners. In this work, we propose an ML-based surrogate model to predict the temperature distribution inside the cabin of a passenger vehicle under various operating conditions and use it to demonstrate the trade-off between prediction performance and training dataset size. Our results show that the prediction accuracy is high and stable even when the training size is gradually reduced from 2000 to 200. The ML-based surrogates also reduce the compute time from ~30 minutes to around ~9 milliseconds. Moreover, even when only 50 CFD simulations are used for training, the temperature trend (e.g., locations of hot/cold regions) predicted by the ML-surrogate matches quite well with the results from CFD simulations.

cs.LG↗

arXiv2022

Revisiting Jet Clustering Algorithms for New Higgs Boson Searches in Hadronic Final States

We assess the performance of different jet-clustering algorithms, in the presence of different resolution parameters and reconstruction procedures, in resolving fully hadronic final states emerging from the chain decay of the discovered Higgs boson into pairs of new identical Higgs states, the latter in turn decaying into bottom-antibottom quark pairs. We show that, at the Large Hadron Collider (LHC), both the efficiency of selecting the multi-jet final state and the ability to reconstruct from it the masses of the Higgs bosons (potentially) present in an event sample depend strongly on the choice of acceptance cuts, jet-clustering algorithm as well as its settings. Hence, we indicate the optimal choice of the latter for the purpose of establishing such a benchmark Beyond the SM (BSM) signal.

hep-ph↗

arXiv2022

On Using Hamiltonian Monte Carlo Sampling for Reinforcement Learning Problems in High-dimension

Value function based reinforcement learning (RL) algorithms, for example, $Q$-learning, learn optimal policies from datasets of actions, rewards, and state transitions. However, when the underlying state transition dynamics are stochastic and evolve on a high-dimensional space, generating independent and identically distributed (IID) data samples for creating these datasets poses a significant challenge due to the intractability of the associated normalizing integral. In these scenarios, Hamiltonian Monte Carlo (HMC) sampling offers a computationally tractable way to generate data for training RL algorithms. In this paper, we introduce a framework, called \textit{Hamiltonian $Q$-Learning}, that demonstrates, both theoretically and empirically, that $Q$ values can be learned from a dataset generated by HMC samples of actions, rewards, and state transitions. Furthermore, to exploit the underlying low-rank structure of the $Q$ function, Hamiltonian $Q$-Learning uses a matrix completion algorithm for reconstructing the updated $Q$ function from $Q$ value updates over a much smaller subset of state-action pairs. Thus, by providing an efficient way to apply $Q$-learning in stochastic, high-dimensional settings, the proposed approach broadens the scope of RL algorithms for real-world applications.

cs.LG↗

arXiv2022

A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles

Emergency vehicles (EMVs) play a critical role in a city's response to time-critical events such as medical emergencies and fire outbreaks. The existing approaches to reduce EMV travel time employ route optimization and traffic signal pre-emption without accounting for the coupling between route these two subproblems. As a result, the planned route often becomes suboptimal. In addition, these approaches also do not focus on minimizing disruption to the overall traffic flow. To address these issues, we introduce EMVLight in this paper. This is a decentralized reinforcement learning (RL) framework for simultaneous dynamic routing and traffic signal control. EMVLight extends Dijkstra's algorithm to efficiently update the optimal route for an EMV in real-time as it travels through the traffic network. Consequently, the decentralized RL agents learn network-level cooperative traffic signal phase strategies that reduce EMV travel time and the average travel time of non-EMVs in the network. We have carried out comprehensive experiments with synthetic and real-world maps to demonstrate this benefit. Our results show that EMVLight outperforms benchmark transportation engineering techniques as well as existing RL-based traffic signal control methods.

cs.AI↗

arXiv2021

Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models

The incorporation of appropriate inductive bias plays a critical role in learning dynamics from data. A growing body of work has been exploring ways to enforce energy conservation in the learned dynamics by encoding Lagrangian or Hamiltonian dynamics into the neural network architecture. These existing approaches are based on differential equations, which do not allow discontinuity in the states and thereby limit the class of systems one can learn. However, in reality, most physical systems, such as legged robots and robotic manipulators, involve contacts and collisions, which introduce discontinuities in the states. In this paper, we introduce a differentiable contact model, which can capture contact mechanics: frictionless/frictional, as well as elastic/inelastic. This model can also accommodate inequality constraints, such as limits on the joint angles. The proposed contact model extends the scope of Lagrangian and Hamiltonian neural networks by allowing simultaneous learning of contact and system properties. We demonstrate this framework on a series of challenging 2D and 3D physical systems with different coefficients of restitution and friction. The learned dynamics can be used as a differentiable physics simulator for downstream gradient-based optimization tasks, such as planning and control.

cs.RO↗

arXiv2021

Extraction of neutrino Yukawa parameters from displaced vertices of sneutrinos

We study displaced signatures of sneutrino pairs potentially emerging at the Large Hadron Collider (LHC) in a Next-to-Minimal Supersymmetric Standard Model supplemented with right-handed neutrinos triggering a Type-I seesaw mechanism. We show how such signatures can be established through a heavy Higgs portal in the presence of both leptonic and hadronic decays of the sneutrinos. We finally illustrate how the Yukawa parameters of the latter can be extracted from fitting kinematical quantities pertaining to the corresponding two displaced vertices, thereby characterising the dynamics of the underlying mechanism of neutrino mass generation. We show our numerical results for the case of both the current and High-Luminosity LHC.

hep-ph↗

arXiv2020

Frequency-compensated PINNs for Fluid-dynamic Design Problems

Incompressible fluid flow around a cylinder is one of the classical problems in fluid-dynamics with strong relevance with many real-world engineering problems, for example, design of offshore structures or design of a pin-fin heat exchanger. Thus learning a high-accuracy surrogate for this problem can demonstrate the efficacy of a novel machine learning approach. In this work, we propose a physics-informed neural network (PINN) architecture for learning the relationship between simulation output and the underlying geometry and boundary conditions. In addition to using a physics-based regularization term, the proposed approach also exploits the underlying physics to learn a set of Fourier features, i.e. frequency and phase offset parameters, and then use them for predicting flow velocity and pressure over the spatio-temporal domain. We demonstrate this approach by predicting simulation results over out of range time interval and for novel design conditions. Our results show that incorporation of Fourier features improves the generalization performance over both temporal domain and design space.

cs.LG↗

arXiv2020

Neural Network-based Top Tagger with Two-Point Energy Correlations and Geometry of Soft Emissions

Deep neural networks trained on jet images have been successful in classifying different kinds of jets. In this paper, we identify the crucial physics features that could reproduce the classification performance of the convolutional neural network in the top jet vs. QCD jet classification. We design a neural network that considers two types of substructural features: two-point energy correlations, and the IRC unsafe counting variables of a morphological analysis of jet images. The new set of IRC unsafe variables can be described by Minkowski functionals from integral geometry. To integrate these features into a single framework, we reintroduce two-point energy correlations in terms of a graph neural network and provide the other features to the network afterward. The network shows a comparable classification performance to the convolutional neural network. Since both networks are using IRC unsafe features at some level, the results based on simulations are often dependent on the event generator choice. We compare the classification results of Pythia 8 and Herwig 7, and a simple reweighting on the distribution of IRC unsafe features reduces the difference between the results from the two simulations.

hep-ph↗