arXiv subjects

Daniel T. Speckhard

Publications and source records attributed to Daniel T. Speckhard.

8 recordsLinked to original sources

arXiv2026

Atompack: A Storage and Distribution Layer for Read-Heavy Atomistic ML Training Datasets

Atomistic machine learning datasets are increasingly used for training: large immutable snapshots are read repeatedly, shuffled across epochs, staged across clusters' storage systems, and republished as reusable scientific artifacts. This workload differs from interactive scientific curation, where mutable records and ad hoc inspection are often more important than random indexed throughput. We present Atompack, an append-oriented storage format and distribution layer designed around a simple workload: training pipelines usually consume complete molecular records, while the order of records is randomized by the learning algorithm. Atompack appends records efficiently during dataset construction, then commits an immutable index and serves records through a memory-mapped read path optimized for training. We compare Atompack with HDF5, LMDB, and ASE baselines representing array stores, key-value records, serialized records, and object-oriented databases. The benchmarks measure sequential reads, shuffled reads, shared-filesystem behavior, write throughput, and artifact size. On a representative 64-atom workload, Atompack is 96x faster than ASE LMDB on shuffled training-style reads while producing artifacts about 79\% smaller. The results indicate that serving complete molecule records, rather than field chunks or reconstructed objects, improves shuffled training throughput while keeping artifacts compact enough for public distribution.

cs.LG↗

arXiv2026

Information-Theoretic Grid Topology Reconstruction using Low-Precision Smart Meter Data

Accurate knowledge of power grid topology is a prerequisite for effective state estimation and grid stability. While data-driven methods for topology reconstruction exist, the minimum requirements for measurement quality, specifically regarding quantization, precision, and sampling frequency, remain under-explored. This study investigates the data fidelity required to reconstruct distribution grid topologies using voltage magnitude measurements. Adopting an information-theoretic approach, we utilize the Chow-Liu algorithm to generate maximum spanning trees based on mutual information. Rather than proposing a new reconstruction algorithm, our primary contribution is a comprehensive sensitivity analysis of the measurement data itself. We systematically evaluate the impact of data bit-depth, significant digit truncation, time-window length, and different mutual information estimators on reconstruction accuracy. We validate this approach using IEEE test cases (via MATPOWER) and time-series data from GridLAB-D. Our results demonstrate that grid topology can be successfully recovered even with highly quantized 8-bit data or millivolt-level precision. However, performance degrades significantly when downsampling intervals exceed 20 minutes or when data availability is limited to short durations. These findings establish an optimistic theoretical lower bound, suggesting that costly high-precision instrumentation may not be strictly necessary for structural inference under ideal conditions. This rigorous baseline provides a foundation for future evaluations of noisy real world smart meter data and hybrid approaches that incorporate existing engineering priors.

physics.soc-ph↗

arXiv2026

Training speedups via batching for geometric learning: an analysis of static and dynamic algorithms

Graph neural networks (GNN) have shown promising results for several domains such as materials science, chemistry, and the social sciences. GNN models often contain millions of parameters, and like other neural network (NN) models, are often fed only a fraction of the graphs that make up the training dataset in batches to update model parameters. The effect of batching algorithms on training time and model performance has been thoroughly explored for NNs but not yet for GNNs. We analyze two different batching algorithms for graph-based models, namely static and dynamic batching for two datasets, the QM9 dataset of small molecules and the AFLOW materials database. Our experiments show that changing the batching algorithm can provide up to a 2.7x speedup, but the fastest algorithm depends on the data, model, batch size, hardware, and number of training steps run. Experiments show that for a select number of combinations of batch size, dataset, and model, significant differences in model learning metrics are observed between static and dynamic batching algorithms.

cs.LG↗

arXiv2026

An exciting approach to theoretical spectroscopy

Theoretical spectroscopy, and more generally, electronic-structure theory, are powerful concepts for describing the complex many-body interactions in materials. They comprise a variety of methods that can capture all aspects, from ground-state properties to lattice excitations to different types of light-matter interaction, including time-resolved variants. Modern electronic-structure codes implement either a few or several of these methods. Among them, exciting is an all-electron full-potential package that has a very rich portfolio of all levels of theory, with a particular focus on excitations. It implements the linearized augmented planewave plus local orbital (LAPW+LO) basis, which is known as the gold standard for solving the Kohn-Sham equations of density-functional theory (DFT). Based on this, it also offers benchmark-quality results for a wide range of excited-state methods. In this review, we provide a comprehensive overview of the features implemented in exciting in recent years, accompanied by short summaries on the state of the art of the underlying methodologies. They comprise DFT and time-dependent DFT (TDDFT), density-functional perturbation theory (DFPT) for phonons and electron-phonon coupling, and many-body perturbation theory in terms of the $GW$ approach and the Bethe-Salpeter equation (BSE). Moreover, exciting can handle resonant inelastic x-ray scattering (RIXS), pump-probe spectroscopy as well as exciton-phonon coupling (EXPC). Finally, we cover workflows and a view on data and machine learning (ML). All aspects are demonstrated with examples for scientifically relevant materials.

cond-mat.mtrl-sci↗

arXiv2024

How big is Big Data?

Big data has ushered in a new wave of predictive power using machine learning models. In this work, we assess what {\it big} means in the context of typical materials-science machine-learning problems. This concerns not only data volume, but also data quality and veracity as much as infrastructure issues. With selected examples, we ask (i) how models generalize to similar datasets, (ii) how high-quality datasets can be gathered from heterogenous sources, (iii) how the feature set and complexity of a model can affect expressivity, and (iv) what infrastructure requirements are needed to create larger datasets and train models on them. In sum, we find that big data present unique challenges along very different aspects that should serve to motivate further work.

stat.ML↗

arXiv2023

Band-gap regression with architecture-optimized message-passing neural networks

Graph-based neural networks and, specifically, message-passing neural networks (MPNNs) have shown great potential in predicting physical properties of solids. In this work, we train an MPNN to first classify materials through density functional theory data from the AFLOW database as being metallic or semiconducting/insulating. We then perform a neural-architecture search to explore the model architecture and hyperparameter space of MPNNs to predict the band gaps of the materials identified as non-metals. The parameters in the search include the number of message-passing steps, latent size, and activation-function, among others. The top-performing models from the search are pooled into an ensemble that significantly outperforms existing models from the literature. Uncertainty quantification is evaluated with Monte-Carlo Dropout and ensembling, with the ensemble method proving superior. The domain of applicability of the ensemble model is analyzed with respect to the crystal systems, the inclusion of a Hubbard parameter in the density functional calculations, and the atomic species building up the materials.

physics.comp-ph↗

arXiv2023

Neural Architecture Search for Energy Efficient Always-on Audio Models

Mobile and edge computing devices for always-on classification tasks require energy-efficient neural network architectures. In this paper we present several changes to neural architecture searches (NAS) that improve the chance of success in practical situations. Our search simultaneously optimizes for network accuracy, energy efficiency and memory usage. We benchmark the performance of our search on real hardware, but since running thousands of tests with real hardware is difficult we use a random forest model to roughly predict the energy usage of a candidate network. We present a search strategy that uses both Bayesian and regularized evolutionary search with particle swarms, and employs early-stopping to reduce the computational burden. Our search, evaluated on a sound-event classification dataset based upon AudioSet, results in an order of magnitude less energy per inference and a much smaller memory footprint than our baseline MobileNetV1/V2 implementations while slightly improving task accuracy. We also demonstrate how combining a 2D spectrogram with a convolution with many filters causes a computational bottleneck for audio classification and that alternative approaches reduce the computational burden but sacrifice task accuracy.

eess.AS↗

arXiv2023

Extrapolation to complete basis-set limit in density-functional theory by quantile random-forest models

The numerical precision of density-functional-theory (DFT) calculations depends on a variety of computational parameters, one of the most critical being the basis-set size. The ultimate precision is reached with an infinitely large basis set, i.e., in the limit of a complete basis set (CBS). Our aim in this work is to find a machine-learning model that extrapolates finite basis-size calculations to the CBS limit. We start with a data set of 63 binary solids investigated with two all-electron DFT codes, exciting and FHI-aims, which employ very different types of basis sets. A quantile-random-forest model is used to estimate the total-energy correction with respect to a fully converged calculation as a function of the basis-set size. The random-forest model achieves a symmetric mean absolute percentage error of lower than 25% for both codes and outperforms previous approaches in the literature. Our approach also provides prediction intervals, which quantify the uncertainty of the models' predictions.

physics.comp-ph↗