M. Alirezaei, T. Tasdizen. Adversarially Robust Classification by Conditional Generative Model Inversion, Subtitled arXiv preprint arXiv:2201.04733, 2022.
Most adversarial attack defense methods rely on obfuscating gradients. These methods are successful in defending against gradient-based attacks; however, they are easily circumvented by attacks which either do not use the gradient or by attacks which approximate and use the corrected gradient. Defenses that do not obfuscate gradients such as adversarial training exist, but these approaches generally make assumptions about the attack such as its magnitude. We propose a classification model that does not obfuscate gradients and is robust by construction without assuming prior knowledge about the attack. Our method casts classification as an optimization problem where we "invert" a conditional generator trained on unperturbed, natural images to find the class that generates the closest sample to the query image. We hypothesize that a potential source of brittleness against adversarial attacks is the high-to-low-dimensional nature of feed-forward classifiers which allows an adversary to find small perturbations in the input space that lead to large changes in the output space. On the other hand, a generative model is typically a low-to-high-dimensional mapping. While the method is related to Defense-GAN, the use of a conditional generative model and inversion in our model instead of the feed-forward classifier is a critical difference. Unlike Defense-GAN, which was shown to generate obfuscated gradients that are easily circumvented, we show that our method does not obfuscate gradients. We demonstrate that our model is extremely robust against black-box attacks and has improved robustness against white-box attacks compared to naturally trained, feed-forward classifiers.
T. M. Athawale, D. Maljovec. L. Yan, C. R. Johnson, V. Pascucci, B. Wang.
Uncertainty Visualization of 2D Morse Complex Ensembles Using Statistical Summary Maps, In IEEE Transactions on Visualization and Computer Graphics, Vol. 28, No. 4, pp. 1955-1966. April, 2022.
Morse complexes are gradient-based topological descriptors with close connections to Morse theory. They are widely applicable in scientific visualization as they serve as important abstractions for gaining insights into the topology of scalar fields. Data uncertainty inherent to scalar fields due to randomness in their acquisition and processing, however, limits our understanding of Morse complexes as structural abstractions. We, therefore, explore uncertainty visualization of an ensemble of 2D Morse complexes that arises from scalar fields coupled with data uncertainty. We propose several statistical summary maps as new entities for quantifying structural variations and visualizing positional uncertainties of Morse complexes in ensembles. Specifically, we introduce three types of statistical summary maps – the probabilistic map , the significance map , and the survival map – to characterize the uncertain behaviors of gradient flows. We demonstrate the utility of our proposed approach using wind, flow, and ocean eddy simulation datasets.
J. Baker, E. Cherkaev, A. Narayan, B. Wang. Learning POD of Complex Dynamics Using Heavy-ball Neural ODEs, Subtitled arXiv:2202.12373, 2022.
Proper orthogonal decomposition (POD) allows reduced-order modeling of complex dynamical systems at a substantial level, while maintaining a high degree of accuracy in modeling the underlying dynamical systems. Advances in machine learning algorithms enable learning POD-based dynamics from data and making accurate and fast predictions of dynamical systems. In this paper, we leverage the recently proposed heavy-ball neural ODEs (HBNODEs) [Xia et al. NeurIPS, 2021] for learning data-driven reduced-order models (ROMs) in the POD context, in particular, for learning dynamics of time-varying coefficients generated by the POD analysis on training snapshots generated from solving full order models. HBNODE enjoys several practical advantages for learning POD-based ROMs with theoretical guarantees, including 1) HBNODE can learn long-term dependencies effectively from sequential observations and 2) HBNODE is computationally efficient in both training and testing. We compare HBNODE with other popular ROMs on several complex dynamical systems, including the von Kármán Street flow, the Kurganov-Petrova-Popov equation, and the one-dimensional Euler equations for fluids modeling.
J. Baker, H. Xia, Y. Wang, E. Cherkaev, A. Narayan, L. Chen, J. Xin, A. L. Bertozzi, S. J. Osher, B. Wang. Proximal Implicit ODE Solvers for Accelerating Learning Neural ODEs, Subtitled arXiv preprint arXiv:2204.08621, 2022.
Learning neural ODEs often requires solving very stiff ODE systems, primarily using explicit adaptive step size ODE solvers. These solvers are computationally expensive, requiring the use of tiny step sizes for numerical stability and accuracy guarantees. This paper considers learning neural ODEs using implicit ODE solvers of different orders leveraging proximal operators. The proximal implicit solver consists of inner-outer iterations: the inner iterations approximate each implicit update step using a fast optimization algorithm, and the outer iterations solve the ODE system over time. The proximal implicit ODE solver guarantees superiority over explicit solvers in numerical stability and computational efficiency. We validate the advantages of proximal implicit solvers over existing popular neural ODE solvers on various challenging benchmark tasks, including learning continuous-depth graph neural networks and continuous normalizing flows.
Electrocardiographic imaging (ECGI) is a noninvasive technique to assess the bioelectric activity of the heart which has been applied to aid in clinical diagnosis and management of cardiac dysfunction. ECGI is built on mathematical models that take into account several patient specific factors including the position of the heart within the torso. Errors in the localization of the heart within the torso, as might arise due to natural changes in heart position from respiration or changes in body position, contribute to errors in ECGI reconstructions of the cardiac activity, thereby reducing the clinical utility of ECGI. In this study we present a novel method for the reconstruction of cardiac geometry utilizing noninvasively acquired body surface potential measurements. Our geometric correction method simultaneously estimates the cardiac position over a series of heartbeats by leveraging an iterative approach which alternates between estimating the cardiac bioelectric source across all heartbeats and then estimating cardiac positions for each heartbeat. We demonstrate that our geometric correction method is able to reduce geometric error and improve ECGI accuracy in a wide range of testing scenarios. We examine the performance of our geometric correction method using different activation sequences, ranges of cardiac motion, and body surface electrode configurations. We find that after geometric correction resulting ECGI solution accuracy is improved and variability of the ECGI solutions between heartbeats is substantially reduced.
The success of the Material Point Method (MPM) in solving many challenging problems nevertheless raises some open questions regarding the fundamental properties of the method such as time integration accuracy and energy conservation. The traditional MPM time integration methods are often based upon the symplectic Euler method or staggered central differences. This raises the question of how to best ensure energy conservation in explicit time integration for MPM. Two approaches are used here, one is to extend the Symplectic Euler method (Cromer Euler) to provide better energy conservation and the second is to use a potentially more accurate symplectic methods, namely the widely-used Stormer-Verlet Method. The Stormer-Verlet method is shown to have locally third order time accuracy of energy conservation in time, in contrast to the second order accuracy in energy conservation of the symplectic Euler methods that are used in many MPM calculations. It is shown that there is an extension to the Symplectic Euler stress-last method that provides better energy conservation that is comparable with the Stormer-Verlet method. This extension is referred to as TRGIMP and also has third order accuracy in energy conservation. When the interactions between space and time errors are studied it is seen that spatial errors may dominate in computed quantities such as displacement and velocity. This connection between the local errors in space and time is made explicit mathematically and explains the observed results that displacement and velocity errors are very similar for both methods. The observed and theoretically predicted third-order energy conservation accuracy and computational costs are demonstrated on a standard MPM test example.
M. Berzins. Computational Error Estimation for The Material Point Method, 2022.
A common feature of many methods in computational mechanics is that there is often a way of estimating the error in the computed solution. The situation for computational mechanics codes based upon the Material Point Method is very different in that there has been comparatively little work on computable error estimates for these methods. This work is concerned with introducing such an approach for the Material Point Method. Although it has been observed that spatial errors may dominate temporal ones at stable time steps, recent work has made more precise the sources and forms of the different MPM errors. There is then a need to estimate these errors computationally through computable estimates of the different errors in the material point method. Estimates of the different spatial errors in the Material Point Method are constructed based upon nodal derivatives of the different physical variables in MPM. These derivatives are then estimated using standard difference approximations calculated on the background mesh. The use of these estimates of the spatial error makes it possible to measure the growth of errors over time. A number of computational experiments are used to illustrate the performance of the computed error estimates. As the key feature of the approach is the calculation of derivatives on the regularly spaced background mesh, the extension to calculating derivatives and hence to error estimates for higher dimensional problems is clearly possible.
M. K. Bruce, W. Tao, J. Beiriger, C. Christensen, M. J. Pfaff, R. Whitaker, J. A. Goldstein. 3D Photography to Quantify the Severity of Metopic Craniosynostosis, In The Cleft Palate-Craniofacial Journal, SAGE Publications, 2022.
This study aims to determine the utility of 3D photography for evaluating the severity of metopic craniosynostosis (MCS) using a validated, supervised machine learning (ML) algorithm.
H. Dai, M. Bauer, P.T. Fletcher, S.C. Joshi. Deep Learning the Shape of the Brain Connectome, Subtitled arXiv preprint arXiv:2203.06122, 2022, 2022.
To statistically study the variability and differences between normal and abnormal brain connectomes, a mathematical model of the neural connections is required. In this paper, we represent the brain connectome as a Riemannian manifold, which allows us to model neural connections as geodesics. We show for the first time how one can leverage deep neural networks to estimate a Riemannian metric of the brain that can accommodate fiber crossings and is a natural modeling tool to infer the shape of the brain from DWMRI. Our method achieves excellent performance in geodesic-white-matter-pathway alignment and tackles the long-standing issue in previous methods: the inability to recover the crossing fibers with high fidelity.
S. Fang, A. Narayan, R.M. Kirby, S. Zhe. Bayesian Continuous-Time Tucker Decomposition, In Proceedings of the 39 th International Conference on Machine Learning, 2022.
Tensor decomposition is a dominant framework for multiway data analysis and prediction. Although practical data often contains timestamps for the observed entries, existing tensor decomposition approaches overlook or under-use this valuable time information. They either drop the timestamps or bin them into crude steps and hence ignore the temporal dynamics within each step or use simple parametric time coefficients. To overcome these limitations, we propose Bayesian Continuous-Time Tucker Decomposition (BCTT). We model the tensor-core of the classical Tucker decomposition as a time-varying function, and place a Gaussian process prior to flexibly estimate all kinds of temporal dynamics. In this way, our model maintains the interpretability while is flexible enough to capture various complex temporal relationships between the tensor nodes. For efficient and high-quality posterior inference, we use the stochastic differential equation (SDE) representation of temporal GPs to build an equivalent state-space prior, which avoids huge kernel matrix computation and sparse/low-rank approximations. We then use Kalman filtering, RTS smoothing, and conditional moment matching to develop a scalable message-passing inference algorithm. We show the advantage of our method in simulation and several real-world applications.
M. Grant, M. R. Kunz, K. Iyer, L. I. Held, T. Tasdizen, J. A. Aguiar, P. P. Dholabhai. Integrating atomistic simulations and machine learning to design multi-principal element alloys with superior elastic modulus, In Journal of Materials Research, Springer International Publishing, pp. 1--16. 2022.
Multi-principal element, high entropy alloys (HEAs) are an emerging class of materials that have found applications across the board. Owing to the multitude of possible candidate alloys, exploration and compositional design of HEAs for targeted applications is challenging since it necessitates a rational approach to identify compositions exhibiting enriched performance. Here, we report an innovative framework that integrates molecular dynamics and machine learning to explore a large chemical-configurational space for evaluating elastic modulus of equiatomic and non-equiatomic HEAs along primary crystallographic directions. Vital thermodynamic properties and machine learning features have been incorporated to establish fundamental relationships correlating Young’s modulus with Gibbs free energy, valence electron concentration, and atomic size difference. In HEAs, as the number of elements increases …
J. Gu, P. Davis, G. Eisenhauer, W. Godoy, A. Huebl, S. Klasky, M. Parashar, N. Podhorszki, F. Poeschel, J. Vay, L. Wan, R. Wang, K. Wu. Organizing Large Data Sets for Efficient Analyses on HPC Systems, In Journal of Physics: Conference Series, Vol. 2224, No. 1, IOP Publishing, pp. 012042. 2022.
Upcoming exascale applications could introduce significant data management challenges due to their large sizes, dynamic work distribution, and involvement of accelerators such as graphical processing units, GPUs. In this work, we explore the performance of reading and writing operations involving one such scientific application on two different supercomputers. Our tests showed that the Adaptable Input and Output System, ADIOS, was able to achieve speeds over 1TB/s, a significant fraction of the peak I/O performance on Summit. We also demonstrated the querying functionality in ADIOS could effectively support common selective data analysis operations, such as conditional histograms. In tests, this query mechanism was able to reduce the execution time by a factor of five. More importantly, ADIOS data management framework allows us to achieve these performance improvements with only a minimal amount …
Time-varying vector fields produced by computational fluid dynamics simulations are often prohibitively large and pose challenges for accurate interactive analysis and exploration. To address these challenges, reduced Lagrangian representations have been increasingly researched as a means to improve scientific time-varying vector field exploration capabilities. This paper presents a novel deep neural network-based particle tracing method to explore time-varying vector fields represented by Lagrangian flow maps. In our workflow, in situ processing is first utilized to extract Lagrangian flow maps, and deep neural networks then use the extracted data to learn flow field behavior. Using a trained model to predict new particle trajectories offers a fixed small memory footprint and fast inference. To demonstrate and evaluate the proposed method, we perform an in-depth study of performance using a well-known analytical data set, the Double Gyre. Our study considers two flow map extraction strategies, the impact of the number of training samples and integration durations on efficacy, evaluates multiple sampling options for training and testing, and informs hyperparameter settings. Overall, we find our method requires a fixed memory footprint of 10.5 MB to encode a Lagrangian representation of a time-varying vector field while maintaining accuracy. For post hoc analysis, loading the trained model costs only two seconds, significantly reducing the burden of I/O when reading data for visualization. Moreover, our parallel implementation can infer one hundred locations for each of two thousand new pathlines in 1.3 seconds using one NVIDIA Titan RTX GPU.
J.D. Hogue, R.M. Kirby, A. Narayan. Dimensionality Reduction in Deep Learning via Kronecker Multi-layer Architectures, Subtitled arXiv:2204.04273, 2022.
Deep learning using neural networks is an effective technique for generating models of complex data. However, training such models can be expensive when networks have large model capacity resulting from a large number of layers and nodes. For training in such a computationally prohibitive regime, dimensionality reduction techniques ease the computational burden, and allow implementations of more robust networks. We propose a novel type of such dimensionality reduction via a new deep learning architecture based on fast matrix multiplication of a Kronecker product decomposition; in particular our network construction can be viewed as a Kronecker product-induced sparsification of an "extended" fully connected network. Analysis and practical examples show that this architecture allows a neural network to be trained and implemented with a significant reduction in computational time and resources, while achieving a similar error level compared to a traditional feedforward neural network.
John Holmen. Portable, Scalable Approaches For Improving Asynchronous Many-Task Runtime Node Use, School of Computing, University of Utah, 2022.
This research addresses node-level scalability, portability, and heterogeneous computing challenges facing asynchronous many-task (AMT) runtime systems. These challenges have arisen due to increasing socket/core/thread counts and diversity among supported architectures on current and emerging high-performance computing (HPC) systems. This places greater emphasis on thread scalability and simultaneous use of diverse architectures to maximize node use and is complicated by architecture-specific programming models.
J.K. Holmen, D. Sahasrabudhe, M. Berzins. Porting Uintah to Heterogeneous Systems, In Proceedings of the Platform for Advanced Scientific Computing Conference (PASC22), ACM, 2022.
The Uintah Computational Framework is being prepared to make portable use of forthcoming exascale systems, initially the DOE Aurora system through the Aurora Early Science Program. This paper describes the evolution of Uintah to be ready for such architectures. A key part of this preparation has been the adoption of the Kokkos performance portability layer in Uintah. The sheer size of the Uintah codebase has made it imperative to have a representative benchmark. The design of this benchmark and the use of Kokkos within it is discussed. This paper complements recent work with additional details and new scaling studies run 24x further than earlier studies. Results are shown for two benchmarks executing workloads representative of typical Uintah applications. These results demonstrate single-source portability across the DOE Summit and NSF Frontera systems with good strong-scaling characteristics. The challenge of extending this approach to anticipated exascale systems is also considered.
Short-Term Natural Course of Esophageal Thermal Injury After Ablation for Atrial Fibrillation, In Journal of Cardiovascular Electrophysiology, Wiley, 2022.
To provide insight into the short-term natural history of esophageal thermal injury (ETI) after radiofrequency catheter ablation (RFCA) for atrial fibrillation (AF) by esophagogastroduodenoscopy (EGD).
Shorter Distance Between The Esophagus And The Left Atrium Is Associated With Higher Rates Of Esophageal Thermal Injury After Radiofrequency Ablation, In Journal of Cardiovascular Electrophysiology, Wiley, 2022.
Esophageal thermal injury (ETI) is a known and potentially serious complication of catheter ablation for atrial fibrillation. We intended to evaluate the distance between the esophagus and the left atrium posterior wall (LAPW) and its association with esophageal thermal injury.
V. Keshavarzzadeh, R.M. Kirby, A. Narayan. Variational Inference for Nonlinear Inverse Problems via Neural Net Kernels: Comparison to Bayesian Neural Networks, Application to Topology Optimization, Subtitled arXiv:2205.03681, 2022.
Inverse problems and, in particular, inferring unknown or latent parameters from data are ubiquitous in engineering simulations. A predominant viewpoint in identifying unknown parameters is Bayesian inference where both prior information about the parameters and the information from the observations via likelihood evaluations are incorporated into the inference process. In this paper, we adopt a similar viewpoint with a slightly different numerical procedure from standard inference approaches to provide insight about the localized behavior of unknown underlying parameters. We present a variational inference approach which mainly incorporates the observation data in a point-wise manner, i.e. we invert a limited number of observation data leveraging the gradient information of the forward map with respect to parameters, and find true individual samples of the latent parameters when the forward map is noise-free and one-to-one. For statistical calculations (as the ultimate goal in simulations), a large number of samples are generated from a trained neural network which serves as a transport map from the prior to posterior latent parameters. Our neural network machinery, developed as part of the inference framework and referred to as Neural Net Kernels (NNK), is based on hierarchical (deep) kernels which provide greater flexibility for training compared to standard neural networks. We showcase the effectiveness of our inference procedure in identifying bimodal and irregular distributions compared to a number of approaches including Markov Chain Monte Carlo sampling approaches and a Bayesian neural network approach.
Z. Li, S. Liu, X. Yu, K. Bhavya, J. Cao, J. Diffenderfer, P.T. Bremer, V. Pascucci. “Understanding Robustness Lottery”: A Comparative Visual Analysis of Neural Network Pruning Approaches, Subtitled arXiv preprint arXiv:2206.07918, 2022.
Deep learning approaches have provided state-of-the-art performance in many applications by relying on extremely large and heavily overparameterized neural networks. However, such networks have been shown to be very brittle, not generalize well to new uses cases, and are often difficult if not impossible to deploy on resources limited platforms. Model pruning, i.e., reducing the size of the network, is a widely adopted strategy that can lead to more robust and generalizable network -- usually orders of magnitude smaller with the same or even improved performance. While there exist many heuristics for model pruning, our understanding of the pruning process remains limited. Empirical studies show that some heuristics improve performance while others can make models more brittle or have other side effects. This work aims to shed light on how different pruning methods alter the network's internal feature representation, and the corresponding impact on model performance. To provide a meaningful comparison and characterization of model feature space, we use three geometric metrics that are decomposed from the common adopted classification loss. With these metrics, we design a visualization system to highlight the impact of pruning on model prediction as well as the latent feature embedding. The proposed tool provides an environment for exploring and studying differences among pruning methods and between pruned and original model. By leveraging our visualization, the ML researchers can not only identify samples that are fragile to model pruning and data corruption but also obtain insights and explanations on how some pruned …