6 citations · 23 across the 56 of their papers we have counts for
5 papers · 1 filter
Randomized Matrix Sketching for Neural Network Training and Gradient Monitoring
Harbir Antil, Deepanshu Verma
Neural network training relies on gradient computation through backpropagation, yet memory requirements for storing layer activations present significant scalability challenges. We…
On-Manifold Projected Gradient Descent
Aaron Mahler, Tyrus Berry, Tom Stephens +4
This work provides a computable, direct, and mathematically rigorous approximation to the differential geometry of class manifolds for high-dimensional data, along with nonlinear p…
A Note on Dimensionality Reduction in Deep Neural Networks using Empirical Interpolation Method
Harbir Antil, Madhu Gupta, Randy Price
Empirical interpolation method (EIM) is a well-known technique to efficiently approximate parameterized functions. This paper proposes to use EIM algorithm to efficiently reduce th…
NINNs: Nudging Induced Neural Networks
Harbir Antil, Rainald Löhner, Randy Price
New algorithms called nudging induced neural networks (NINNs), to control and improve the accuracy of deep neural networks (DNNs), are introduced. The NINNs framework can be applie…
Novel DNNs for Stiff ODEs with Applications to Chemically Reacting Flows
Thomas S. Brown, Harbir Antil, Rainald Löhner +2
Chemically reacting flows are common in engineering, such as hypersonic flow, combustion, explosions, manufacturing processes and environmental assessments. For combustion, the num…