Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed Learning”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness

We report the accuracy of deep learning, i.e., deep neural networks, can be characterized by dividing the total error into three main types: approximation error, optimization error, and generalization error. Whereas there are some satisfactory answers to the problems of approximation and optimization, much less is known about the theory of generalization. Most existing theoretical works for generalization fail to explain the performance of neural networks in practice. To derive a meaningful bound, we study the generalization error of neural networks for classification problems in terms of data distribution and neural network smoothness. We introduce the cover complexity (CC) to measure the difficulty of learning a data set and the inverse of the modulus of continuity to quantify neural network smoothness. A quantitative bound for expected accuracy/error is derived by considering both the CC and neural network smoothness. Although most of the analysis is general and not specific to neural networks, we validate our theoretical assumptions and results numerically for neural networks by several data sets of images. The numerical results confirm that the expected error of trained networks scaled with the square root of the number of classes has a linear relationship with respect to the CC. We also observe a clear consistency between test loss and neural network smoothness during the training process. In addition, we demonstrate empirically that the neural network smoothness decreases when the network size increases whereas the smoothness is insensitive to training dataset size.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A Sequential Model Predictive and Deep Reinforcement Learning-Based Controller for Distribution System Outage Mitigation under Hurricane Events

This paper proposes a proactive outage mitigation framework for power distribution networks to withstand hurricane-induced disruptions. It leverages Model Predictive Control (MPC) to identify safe lines for proactive switching during hurricanes, minimizing the risk of cascading failures and voltage violations. The switching strategies optimized by MPC are sequentially integrated with a Deep Reinforcement Learning agent using the Advantage Actor-Critic algorithm, enabling dynamic line switching to maximize connected buses and minimize voltage violations in real time. Using a probabilistic hurricane model, the framework predicts line failures and adapts to varying conditions to enhance grid resilience. Simulations on the IEEE 123-bus system demonstrate its effectiveness in maintaining high connectivity and minimizing disruptions. Real-time testing with an RTDS confirms the practicality and reliability of the proposed approach.

Selim, Alaa [University of Connecticut]↗
NASA NTRS2004

Product Distributions for Distributed Optimization

With connections to bounded rational game theory, information theory and statistical mechanics, Product Distribution (PD) theory provides a new framework for performing distributed optimization. Furthermore, PD theory extends and formalizes Collective Intelligence, thus connecting distributed optimization to distributed Reinforcement Learning (FU). This paper provides an overview of PD theory and details an algorithm for performing optimization derived from it. The approach is demonstrated on two unconstrained optimization problems, one with discrete variables and one with continuous variables. To highlight the connections between PD theory and distributed FU, the results are compared with those obtained using distributed reinforcement learning inspired optimization approaches. The inter-relationship of the techniques is discussed.

Bieniawski, Stefan R.↗
DOE OSTI2020

A New Approach to Distributed Hypothesis Testing and Non-Bayesian Learning: Improved Learning Rate and Byzantine-Resilience

Here, we study a setting where a group of agents, each receiving partially informative private signals, seek to collaboratively learn the true underlying state of the world (from a finite set of hypotheses) that generates their joint observation profiles. To solve this problem, we propose a distributed learning rule that differs fundamentally from existing approaches, in that it does not employ any form of “belief-averaging”. Instead, agents update their beliefs based on a min-rule. Under standard assumptions on the observation model and the network structure, we establish that each agent learns the truth asymptotically almost surely. As our main contribution, we prove that with probability 1, each false hypothesis is ruled out by every agent exponentially fast, at a network-independent rate that is strictly larger than existing rates. We then develop a computationally-efficient variant of our learning rule that is provably resilient to agents who do not behave as expected (as represented by a Byzantine adversary model) and deliberately try to spread misinformation.

42 ENGINEERING↗
DOE OSTI2020

Machine-learning prediction for quasiparton distribution function matrix elements

There have been rapid developments in the direct calculation in lattice QCD (LQCD) of the Bjorken-x dependence of hadron structure through large-momentum effective theory (LaMET). LaMET overcomes the previous limitation of LQCD to moments (that is, integrals over Bjorken x) of hadron structure, allowing LQCD to directly provide the kinematic regions where the experimental values are least known. LaMET requires large-momentum hadron states to minimize its systematics and allow us to reach small- x reliably. This means that very fine lattice spacing to minimize lattice artifacts at order $(P_za)^n$ will become crucial for next-generation LaMET-like structure calculations. Furthermore, such calculations require operators with long Wilson-link displacements, especially in finer lattice units, increasing the communication costs relative to that of the propagator inversion. In this work, we explore whether machine-learning algorithms can make predictions of correlators to reduce the computational cost of these LQCD calculations. We consider two algorithms, gradient-boosting decision tree and linear models, applied to LaMET data, the matrix elements needed to determine the kaon and $η_s$ unpolarized parton distribution functions (PDFs), meson distribution amplitude (DA), and the nucleon gluon PDF. We find that both algorithms can reliably predict the target observables with different prediction accuracy and systematic errors. The predictions from smaller displacement z to larger ones work better than those for momentum p due to the higher correlation among the data.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Towards FAIR Workflows for Federated Experimental Sciences

A de-centralized, peer-to-peer AI metadata framework is demonstrated which can enable end-to-end metadata & lineage tracking for distributed Machine Learning pipelines spanning edge, High Performance Computing, and cloud environments. With a specific example of end-to-end microscopy algorithm and datasets, the proposed method shows how to enable reproducibility, audit trail, provenance of metadata artifacts. The emerging needs of automation in experimental sciences, ML-centric workflows, and FAIR metadata management across federated compute environments is addressed.

machine learning↗
DOE OSTI2019

Fast neural network training on a cluster of GPUs for action recognition with high accuracy

In this work, we propose algorithms and techniques to accelerate training of deep neural networks for action recognition on a cluster of GPUs. The convergence analysis of our algorithm shows it is possible to reduce communication cost and at the same time minimize the number of iterations needed for convergence. We customize the Adam optimizer for our distributed algorithm to improve efficiency. In addition, we employ transfer-learning to further reduce training time while improving validation accuracy. For the UCF101 and HMDB51 datasets, the validation accuracies achieved are 93.1% and 67.9% respectively. With an additional end-to-end trained temporal stream, the validation accuracies achieved for UCF101 and HMDB51 are 93.47% and 81.24% respectively. As far as we know, these are the highest accuracies achieved with the two-stream approach using ResNet that does not involve computationally expensive 3D convolutions or pretraining on much larger datasets.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Search for New Phenomena in Two-Body Invariant Mass Distributions Using Unsupervised Machine Learning for Anomaly Detection at s = 13 TeV with the ATLAS Detector

Searches for new resonances are performed using an unsupervised anomaly-detection technique. Events with at least one electron or muon are selected from 140 fb − 1 of p p collisions at s = 13 TeV recorded by ATLAS at the Large Hadron Collider. The approach involves training an autoencoder on data, and subsequently defining anomalous regions based on the reconstruction loss of the decoder. Studies focus on nine invariant mass spectra that contain pairs of objects consisting of one light jet or b jet and either one lepton ( e , μ ) , photon, or second light jet or b jet in the anomalous regions. No significant deviations from the background hypotheses are observed. Limits on contributions from generic Gaussian signals with various widths of the resonance mass are obtained for nine invariant masses in the anomalous regions. © 2024 CERN, for the ATLAS Collaboration 2024 CERN

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

Harnessing the power of ab initio calculations, distributed computing and machine learning to efficiently locate extreme molecules for use in carbon-based solar cells (Final Technical Report)

The use of high-throughput virtual screening (HTVS) tools is a powerful tool to expedite the materials discovery of commercially relevant materials. In previous years, our group has developed a molecular discovery platform to generate libraries in order to obtain suitable candidates for different applications, starting from the Harvard Clean Energy Project. This platform is suitable to test in-silico on traditional supercomputing clusters and shared resources, for example, in the IBM World Community Grid. In this project, we used the molecular discovery platform to create and screen a library of candidates of organic photovoltaic (OPVs) molecules. Based on a set of candidates created with combinations of molecular moieties, we were able to filter, by conformation stability, the energy of electronic orbitals and approximated power conversion efficiencies (PCE). To improve the predictions of orbital energies calculated and the PCEs, we used Gaussian Process regression and two sets of molecules. These sets correspond to electronic structure calculations of a higher level of theory and experimental PCE values, respectively. Finally, we selected a subset of the best candidates (molecules with a PCE higher than 10%) to understand its absorbance properties with TD-DFT. This project has demonstrated the capabilities of our molecular discovery platform for HTVS. Finally, machine learning can help us to introduce more complex effects included in bulk conditions and computational intensive calculations on models.

14 SOLAR ENERGY↗
DOE OSTI2022

Anderson Acceleration for Distributed Training of Deep Learning Models

Anderson acceleration (AA) is an extrapolation technique that has recently gained interest in the deep learning (DL) community to speed-up the sequential training of DL models. However, when performed at large scale, the DL training is exposed to a higher risk of getting trapped into steep local minima of the training loss function, and standard AA does not provide sufficient acceleration to escape from these steep local minima. This results in poor generalizability and makes AA ineffective. To restore AA’s advantage to speed-up the training of DL models on large scale computing platforms, we combine AA with an adaptive moving average procedure that boosts the training to escape from steep local minima. By monitoring the relative standard deviation between consecutive iterations, we also introduce a criterion to automatically assess whether the moving average is needed. We applied the method to the following DL instantiations for image classification: (i) ResNet50 trained on the open-source CIFAR100 dataset and (ii) ResNet50 trained on the open-source ImageNet1k dataset. Numerical results obtained using up to 1,536 NVIDIA V100 GPUs on the OLCF supercomputer Summit showed the stabilizing effect of the moving average on AA for all the problems above.

Lupo Pasini, Massimiliano↗
DOE OSTI2022

A Reinforcement Learning Approach to Parameter Selection for Distributed Optimal Power Flow

With the increasing penetration of distributed energy resources, distributed optimization algorithms have attracted significant attention for power systems applications due to their potential for superior scalability, privacy, and robustness to a single point-of-failure. The Alternating Direction Method of Multipliers (ADMM) is a popular distributed optimization algorithm; however, its convergence performance is highly dependent on the selection of penalty parameters, which are usually chosen heuristically. In this work, we use reinforcement learning (RL) to develop an adaptive penalty parameter selection policy for alternating current optimal power flow (ACOPF) problem solved via ADMM with the goal of minimizing the number of iterations until convergence. We train our RL policy using deep Q-learning and show that this policy can result in significantly accelerated convergence (up to a 59% reduction in the number of iterations compared to existing, curvatureinformed penalty parameter selection methods). Furthermore, we show that our RL policy demonstrates promise for generalizability, performing well under unseen loading schemes as well as under unseen losses of lines and generators (up to a 50% reduction in iterations). This work thus provides a proof-of-concept for using RL for parameter selection in ADMM for power systems applications.

alternating current optimal power flow↗
DOE OSTI2025

Generative unfolding with distribution mapping

Machine learning enables unbinned, highly-differential cross section measurements. A recent idea uses generative models to morph a starting simulation into the unfolded data. We show how to extend two morphing techniques, Schrödinger Bridges and Direct Diffusion, in order to ensure that the models learn the correct conditional probabilities. This brings distribution mapping (DM) to a similar level of accuracy as the state-of-the-art conditional generative unfolding methods. Numerical results are presented with a standard benchmark dataset of single jet substructure as well as for a new dataset describing a 22-dimensional phase space of Z+2 -jets.

Butter, Anja↗
DOE OSTI2021

Controlling distributed energy resources via deep reinforcement learning for load flexibility and energy efficiency

Behind-the-meter distributed energy resources (DERs), including building solar photovoltaic (PV) technology and electric battery storage, are increasingly being considered as solutions to support carbon reduction goals and increase grid reliability and resiliency. However, dynamic control of these resources in concert with traditional building loads, to effect efficiency and demand flexibility, is not yet commonplace in commercial control products. Traditional rule-based control algorithms do not offer integrated closed-loop control to optimize across systems, and most often, PV and battery systems are operated for energy arbitrage and demand charge management, and not for the provision of grid services. More advanced control approaches, such as MPC control have not been widely adopted in industry because they require significant expertise to develop and deploy. Recent advances in deep reinforcement learning (DRL) offer a promising option to optimize the operation of DER systems and building loads with reduced setup effort. However, there are limited studies that evaluate the efficacy of these methods to control multiple building subsystems simultaneously. Additionally, most of the research has been conducted in simulated environments as opposed to real buildings. This paper proposes a DRL approach that uses a deep deterministic policy gradient algorithm for integrated control of HVAC and electric battery storage systems in the presence of on-site PV generation. The DRL algorithm, trained on synthetic data, was deployed in a physical test building and evaluated against a baseline that uses the current best-in-class rule-based control strategies. Performance in delivering energy efficiency, load shift, and load shed was tested using price-based signals. The results showed that the DRL-based controller can produce cost savings of up to 39.6% as compared to the baseline controller, while maintaining similar thermal comfort in the building. The project team has also integrated the simulation components developed during this work as an OpenAIGym environment and made it publicly available so that prospective DRL researchers can leverage this environment to evaluate alternate DRL algorithms.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2011

Collaborative Supervised Learning for Sensor Networks

Collaboration methods for distributed machine-learning algorithms involve the specification of communication protocols for the learners, which can query other learners and/or broadcast their findings preemptively. Each learner incorporates information from its neighbors into its own training set, and they are thereby able to bootstrap each other to higher performance. Each learner resides at a different node in the sensor network and makes observations (collects data) independently of the other learners. After being seeded with an initial labeled training set, each learner proceeds to learn in an iterative fashion. New data is collected and classified. The learner can then either broadcast its most confident classifications for use by other learners, or can query neighbors for their classifications of its least confident items. As such, collaborative learning combines elements of both passive (broadcast) and active (query) learning. It also uses ideas from ensemble learning to combine the multiple responses to a given query into a single useful label. This approach has been evaluated against current non-collaborative alternatives, including training a single classifier and deploying it at all nodes with no further learning possible, and permitting learners to learn from their own most confident judgments, absent interaction with their neighbors. On several data sets, it has been consistently found that active collaboration is the best strategy for a distributed learner network. The main advantages include the ability for learning to take place autonomously by collaboration rather than by requiring intervention from an oracle (usually human), and also the ability to learn in a distributed environment, permitting decisions to be made in situ and to yield faster response time.

Wagstaff, Kiri L.↗