18 papers
Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors
Alexander Scheinker
Autoregressive models accumulate error over long rollouts, yet at deployment there is no ground truth to measure it against. We train a single conditional latent diffusion model th…
Bidirectional Autoregressive Latent Diffusion for Forward and Inverse Magnetohydrodynamics
Alexander Scheinker
This work presents a new bidirectional autoregressive latent diffusion approach for predicting the evolution of multiple fields (mass density, pressure, velocity, and magnetic fiel…
Mahalanobis-Guided Latent OOD Detection for Hybrid ES-DRL Control in Time-Varying Systems
Shaifalee Saxena, Alexander Scheinker
In this paper, we study Mahalanobis-guided latent out-of-distribution (OOD) detection for test-time RL controller switching in nonlinear time-varying systems. RL controllers can qu…
Planning for Change: Reinforcement Learning Combined with Bounded Extremum Seeking for Robotic Control under Distribution Shift
Shaifalee Saxena, Rafael Fierro, Alexander Scheinker
Reinforcement learning has shown strong performance in robotic manipulation, but learned policies often degrade in performance when test conditions differ from the training distrib…
Nested Extremum Seeking Converges to Stackelberg Equilibrium
Brad Ratto, Alan Williams, Miroslav Krstić +2
The nested Extremum Seeking (nES) algorithm is a model-free optimization method that has been shown to converge to a neighborhood of a Nash equilibrium. In this work, we demonstrat…
PDE foundation model-accelerated inverse estimation of system parameters in inertial confinement fusion
Mahindra Rautela, Alexander Scheinker, Bradley Love +4
PDE foundation models are typically pretrained on large, diverse corpora of PDE datasets and can be adapted to new settings with limited task-specific data. However, most downstrea…
Out-of-distribution transfer of PDE foundation models to material dynamics under extreme loading
Mahindra Rautela, Alexander Most, Siddharth Mansingh +9
Most PDE foundation models are pretrained and fine-tuned on fluid-centric benchmarks. Their utility under extreme-loading material dynamics remains unclear. We benchmark out-of-dis…
Advancing accelerator virtual beam diagnostics through latent evolution modeling: an integrated solution to forward, inverse, tuning, and UQ problems
Mahindra Rautela, Alexander Scheinker
Virtual beam diagnostics relies on computationally intensive beam dynamics simulations where high-dimensional charged particle beams evolve through the accelerator. We propose Late…
Generalized Multi-Constraint Extremum Seeking
Alan Williams, Jorge Cortés, Alexander Scheinker
We generalize the Safe Extremum Seeking algorithm to address the minimization of an unknown objective function subject to multiple unknown inequality and equality constraints, rely…
Improved Robustness of Deep Reinforcement Learning for Control of Time-Varying Systems by Bounded Extremum Seeking
Shaifalee Saxena, Alan Williams, Rafael Fierro +1
In this paper, we study the use of robust model independent bounded extremum seeking (ES) feedback control to improve the robustness of deep reinforcement learning (DRL) controller…
MORPH: PDE Foundation Models with Arbitrary Data Modality
Mahindra Singh Rautela, Alexander Most, Siddharth Mansingh +6
We introduce MORPH, a modality-agnostic, autoregressive foundation model for partial differential equations (PDEs). MORPH is built on a convolutional vision transformer backbone th…
Using Convolutional Neural Networks to Accelerate 3D Coherent Synchrotron Radiation Computations
Christopher Leon, Petr M. Anisimov, Nikolai Yampolsky +1
Calculating the effects of Coherent Synchrotron Radiation (CSR) is one of the most computationally expensive tasks in accelerator physics. Here, we use convolutional neural network…
Adaptive conditional latent diffusion maps beam loss to 2D phase space projections
Alexander Scheinker, Alan Williams
Beam loss (BLM) and beam current monitors (BCM) are ubiquitous at particle accelerator around the world. These simple devices provide non-invasive high level beam measurements, but…
Physics-Informed Super-Resolution Diffusion for 6D Phase Space Diagnostics
Alexander Scheinker
Adaptive physics-informed super-resolution diffusion is developed for non-invasive virtual diagnostics of the 6D phase space density of charged particle beams. An adaptive variatio…
QP Based Constrained Optimization for Reliable PINN Training
Alan Williams, Christopher Leon, Alexander Scheinker
Physics-Informed Neural Networks (PINNs) have emerged as a powerful tool for integrating physics-based constraints and data to address forward and inverse problems in machine learn…
Classifier-pruned Bayesian optimization for particle accelerator tuning: Exploring temporally structured manifold of 6D beam phase space
Mahindra Rautela, Alan Williams, Alexander Scheinker
Complex dynamical systems, such as particle accelerators, require tuning over high-dimensional, nonlinear state and parameter spaces while experimental measurements and high-fideli…
cDVAE: Multimodal Generative Conditional Diffusion Guided by Variational Autoencoder Latent Embedding for Virtual 6D Phase Space Diagnostics
Alexander Scheinker
Imaging the 6D phase space of a beam in a particle accelerator in a single shot is currently impossible. Single shot beam measurements only exist for certain 2D beam projections an…
Conditional Guided Generative Diffusion for Particle Accelerator Beam Diagnostics
Alexander Scheinker
Advanced accelerator-based light sources such as free electron lasers (FEL) accelerate highly relativistic electron beams to generate incredibly short (10s of femtoseconds) coheren…