12 citations · 14 across the 6 of their papers we have counts for
8 papers
Tucker Tensor Train Taylor Series
Nick Alger, Blake Christierson, Peng Chen +1
Learning derivative-accurate surrogates for implicit simulators is a key challenge in scientific machine learning. High-order Taylor surrogates have long been considered intractabl…
Accelerating seismic inversion and uncertainty quantification with efficient high-rank Hessian approximations
Mathew Hu, Nick Alger, Rami Nammour +1
Efficient high-rank approximations of the Hessian can accelerate seismic full waveform inversion (FWI) and uncertainty quantification (UQ). In FWI, approximations of the inverse of…
Point spread function approximation of high rank Hessians with locally supported non-negative integral kernels
Nick Alger, Tucker Hartland, Noemi Petra +1
We present an efficient matrix-free point spread function (PSF) method for approximating operators that have locally supported non-negative integral kernels. The method computes im…
Tensor train construction from tensor actions, with application to compression of large high order derivative tensors
Nick Alger, Peng Chen, Omar Ghattas
We present a method for converting tensors into tensor train format based on actions of the tensor as a vector-valued multilinear function. Existing methods for constructing tensor…
Low Rank Saddle Free Newton: A Scalable Method for Stochastic Nonconvex Optimization
Thomas O'Leary-Roseberry, Nick Alger, Omar Ghattas
In modern deep learning, highly subsampled stochastic approximation (SA) methods are preferred to sample average approximation (SAA) methods because of large data sets as well as g…
Inexact Newton Methods for Stochastic Nonconvex Optimization with Applications to Neural Network Training
Thomas O'Leary-Roseberry, Nick Alger, Omar Ghattas
We study stochastic inexact Newton methods and consider their application in nonconvex settings. Building on the work of [R. Bollapragada, R. H. Byrd, and J. Nocedal, IMA Journal o…
Scalable matrix-free adaptive product-convolution approximation for locally translation-invariant operators
Nick Alger, Vishwas Rao, Aaron Myers +2
We present an adaptive grid matrix-free operator approximation scheme based on a "product-convolution" interpolation of convolution operators. This scheme is appropriate for operat…
A data scalable augmented Lagrangian KKT preconditioner for large scale inverse problems
Nick Alger, Umberto Villa, Tan Bui-Thanh +1
Current state of the art preconditioners for the reduced Hessian and the Karush-Kuhn-Tucker (KKT) operator for large scale inverse problems are typically based on approximating the…