Ankit Srivastava

Yiming Wang, Mihindukulasooriya Sheral Crescent Tissera, Haihong Yu et al.

Agile earth observation satellites employ multiple actuators to enable flexible and responsive imaging capabilities. While significant advancements in actuator technology have enhanced satellites' torque and momentum, relatively little attention has been given to control strategies specifically tailored to improve satellite agility. This paper provides a comparative analysis of different Model Predictive Control (MPC) formulations and introduces an augmented-MPC method that effectively balances agility requirements with hardware implementation constraints. The proposed method achieves the high-performance characteristics of nonlinear MPC while preserving the computational simplicity of linear MPC. Numerical simulations and physical experiments are conducted to validate the effectiveness and feasibility of the proposed approach.

Rini J. Gladstone, Mohammad A. Nabian, N. Sukumar et al.

Physics-Informed Neural Networks (PINNs) are a class of deep learning neural networks that learn the response of a physical system without any simulation data, and only by incorporating the governing partial differential equations (PDEs) in their loss function. While PINNs are successfully used for solving forward and inverse problems, their accuracy decreases significantly for parameterized systems. PINNs also have a soft implementation of boundary conditions resulting in boundary conditions not being exactly imposed everywhere on the boundary. With these challenges at hand, we present first-order physics-informed neural networks (FO-PINNs). These are PINNs that are trained using a first-order formulation of the PDE loss function. We show that, compared to standard PINNs, FO-PINNs offer significantly higher accuracy in solving parameterized systems, and reduce time-per-iteration by removing the extra backpropagations needed to compute the second or higher-order derivatives. Additionally, FO-PINNs can enable exact imposition of boundary conditions using approximate distance functions, which pose challenges when applied on high-order PDEs. Through three examples, we demonstrate the advantages of FO-PINNs over standard PINNs in terms of accuracy and training speedup.

Nathanaël Perraudin, Ankit Srivastava, Aurelien Lucchi et al.

Deep generative models, such as Generative Adversarial Networks (GANs) or Variational Autoencoders (VAs) have been demonstrated to produce images of high visual quality. However, the existing hardware severely limits the size of the images that can be generated. The rapid growth of high dimensional data in many fields of science therefore poses a significant challenge for generative models. In cosmology, the large-scale, three-dimensional matter distribution, modeled with N-body simulations, plays a crucial role in understanding the evolution of the universe. As these simulations are computationally very expensive, GANs have recently generated interest as a possible method to emulate these datasets, but they have been, so far, mostly limited to two dimensional data. In this work, we introduce a new benchmark for the generation of three dimensional N-body simulations, in order to stimulate new ideas in the machine learning community and move closer to the practical use of generative models in cosmology. As a first benchmark result, we propose a scalable GAN approach for training a generator of N-body three-dimensional cubes. Our technique relies on two key building blocks, (i) splitting the generation of the high-dimensional data into smaller parts, and (ii) using a multi-scale approach that efficiently captures global image features that might otherwise be lost in the splitting process. We evaluate the performance of our model for the generation of N-body samples using various statistical measures commonly used in cosmology. Our results show that the proposed model produces samples of high visual quality, although the statistical analysis reveals that capturing rare features in the data poses significant problems for the generative models. We make the data, quality evaluation routines, and the proposed GAN architecture publicly available at https://github.com/nperraud/3DcosmoGAN

Ankit Srivastava

In this paper, we exploit the concept of Kolmogorov $n$-widths to establish optimality benchmarks for reduced-order methods used in phononic, acoustic, and photonic band structure calculations. The Bloch-transformed operators are entire holomorphic functions of the wave vector~$\kk$, and by Kato's analytic perturbation theory the eigenpairs inherit this holomorphy wherever the spectral gap is positive. The Kolmogorov $n$-width of the solution manifold therefore decays exponentially, at a rate controlled by the minimum spectral gap between the band of interest and its neighbors. For clusters of bands, we show that working with spectral projectors rather than individual eigenvectors renders all internal crossings -- avoided, symmetry-enforced, or conical -- irrelevant: only the gap separating the cluster from the remaining spectrum matters. These results provide a sharp lower bound on the error of any linear reduction method, against which existing approaches can be measured. Numerical experiments on one- and two-dimensional problems confirm the predicted exponential decay and demonstrate that a greedy algorithm achieves near-optimal convergence. It also provides a principled justification for the choice of basis vectors in highly successful reduced-order models like RBME.

James Bono, Justin Grana, Kleanthis Karakolios et al.

We measure the association between generative AI (GAI) tool adoption and four metrics spanning security operations, information protection, and endpoint management: 1) number of security alerts per incident, 2) probability of security incident reopenings, 3) time to classify a data loss prevention alert, and 4) time to resolve device policy conflicts. We find that GAI is associated with robust and statistically and practically significant improvements in the four metrics. Although unobserved confounders inhibit causal identification, these results are among the first to use observational data from live operations to investigate the relationship between GAI adoption and security operations, data loss prevention, and device policy management.

N. Sukumar, Ankit Srivastava

In this paper, we introduce a new approach based on distance fields to exactly impose boundary conditions in physics-informed deep neural networks. The challenges in satisfying Dirichlet boundary conditions in meshfree and particle methods are well-known. This issue is also pertinent in the development of physics informed neural networks (PINN) for the solution of partial differential equations. We introduce geometry-aware trial functions in artifical neural networks to improve the training in deep learning for partial differential equations. To this end, we use concepts from constructive solid geometry (R-functions) and generalized barycentric coordinates (mean value potential fields) to construct $φ$, an approximate distance function to the boundary of a domain. To exactly impose homogeneous Dirichlet boundary conditions, the trial function is taken as $φ$ multiplied by the PINN approximation, and its generalization via transfinite interpolation is used to a priori satisfy inhomogeneous Dirichlet (essential), Neumann (natural), and Robin boundary conditions on complex geometries. In doing so, we eliminate modeling error associated with the satisfaction of boundary conditions in a collocation method and ensure that kinematic admissibility is met pointwise in a Ritz method. We present numerical solutions for linear and nonlinear boundary-value problems over domains with affine and curved boundaries. Benchmark problems in 1D for linear elasticity, advection-diffusion, and beam bending; and in 2D for the Poisson equation, biharmonic equation, and the nonlinear Eikonal equation are considered. The approach extends to higher dimensions, and we showcase its use by solving a Poisson problem with homogeneous Dirichlet boundary conditions over the 4D hypercube. This study provides a pathway for meshfree analysis to be conducted on the exact geometry without domain discretization.

Ankit Srivastava, Samira Pouyanfar, Joshua Allen et al.

Computation of Mutual Information (MI) helps understand the amount of information shared between a pair of random variables. Automated feature selection techniques based on MI ranking are regularly used to extract information from sensitive datasets exceeding petabytes in size, over millions of features and classes. Series of one-vs-all MI computations can be cascaded to produce n-fold MI results, rapidly pinpointing informative relationships. This ability to quickly pinpoint the most informative relationships from datasets of billions of users creates privacy concerns. In this paper, we present Distributed Differentially Private Mutual Information (DDP-MI), a privacy-safe fast batch MI, across various scenarios such as feature selection, segmentation, ranking, and query expansion. This distributed implementation is protected with global model differential privacy to provide strong assurances against a wide range of privacy attacks. We also show that our DDP-MI can substantially improve the efficiency of MI calculations compared to standard implementations on a large-scale public dataset.