Publications (12)
Slimmable NAM: Neural Amp Models with adjustable runtime computational cost
Steven Atkinson
This work demonstrates "slimmable Neural Amp Models", whose size and computational cost can be changed without additional training and with negligible computational overhead, enabl…
Advances in Bayesian Probabilistic Modeling for Industrial Applications
Sayan Ghosh, Piyush Pandita, Steven Atkinson +5
Industrial applications frequently pose a notorious challenge for state-of-the-art methods in the contexts of optimization, designing experiments and modeling unknown physical resp…
Static Structural Signatures of Nearly Jammed Disordered and Ordered Hard-Sphere Packings: Direct Correlation Function
Steven Atkinson, Frank H. Stillinger, Salvatore Torquato
Dynamical signatures are known to precede jamming in hard-particle systems, but static structural signatures have proven more elusive. The observation that compressing hard-particl…
Maximally dense packings of two-dimensional convex and concave noncircular particles
Steven Atkinson, Yang Jiao, Salvatore Torquato
Dense packings of hard particles have important applications in many fields, including condensed matter physics, discrete geometry and cell biology. In this paper, we employ a stoc…
Inverse Aerodynamic Design of Gas Turbine Blades using Probabilistic Machine Learning
Sayan Ghosh, Govinda A. Padmanabha, Cheng Peng +6
One of the critical components in Industrial Gas Turbines (IGT) is the turbine blade. Design of turbine blades needs to consider multiple aspects like aerodynamic efficiency, durab…
Discovery of Physics and Characterization of Microstructure from Data with Bayesian Hidden Physics Models
Steven Atkinson, Yiming Zhang, Liping Wang
There has been a surge in the interest of using machine learning techniques to assist in the scientific process of formulating knowledge to explain observational data. We demonstra…
Bayesian Hidden Physics Models: Uncertainty Quantification for Discovery of Nonlinear Partial Differential Operators from Data
Steven Atkinson
What do data tell us about physics-and what don't they tell us? There has been a surge of interest in using machine learning models to discover governing physical laws such as diff…
Bayesian task embedding for few-shot Bayesian optimization
Steven Atkinson, Sayan Ghosh, Natarajan Chennimalai-Kumar +2
We describe a method for Bayesian optimization by which one may incorporate data from multiple systems whose quantitative interrelationships are unknown a priori. All general (nonr…
Data-driven discovery of free-form governing differential equations
Steven Atkinson, Waad Subber, Liping Wang +3
We present a method of discovering governing differential equations from data without the need to specify a priori the terms to appear in the equation. The input to our method is a…
Structured Bayesian Gaussian process latent variable model: applications to data-driven dimensionality reduction and high-dimensional inversion
Steven Atkinson, Nicholas Zabaras
We introduce a methodology for nonlinear inverse problems using a variational Bayesian approach where the unknown quantity is a spatial field. A structured Bayesian Gaussian proces…
Critical slowing down and hyperuniformity on approach to jamming
Steven Atkinson, Ge Zhang, Adam B. Hopkins +1
Hyperuniformity characterizes a state of matter that is poised at a critical point at which density or volume-fraction fluctuations are anomalously suppressed at infinite wavelengt…
Structured Bayesian Gaussian process latent variable model
Steven Atkinson, Nicholas Zabaras
We introduce a Bayesian Gaussian process latent variable model that explicitly captures spatial correlations in data using a parameterized spatial kernel and leveraging structure-e…