Deepanshu Verma

Deepanshu Verma

Auto-generated profile, based on publicly available information

Deepanshu Verma

George Mason Univ, Dept Math Sci, Fairfax, VA 22030 USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2020 in Machine Learning: Science and Technology
Verified
Journal Article
Open access
HAHarbir Antil
Harbir Antil
RKRatna Khatri
Ratna Khatri
RLRainald Löhner
Rainald Löhner
DVDeepanshu Verma
Deepanshu Verma
This paper introduces a novel algorithmic framework for a deep neural network (DNN), which in a mathematically rigorous manner, allows us to incorporate history (or memory) into the network—it ensures all layers are connected to one another. This DNN, called Fractional-DNN, can be viewed as a time-discretization of a fractional in time non-linear ordinary differential equation (ODE). The learning problem then is a minimization problem subject to that fractional ODE as constraints. We emphasize that an analogy between the existing DNN and ODEs, with standard time derivative, is well-known by now. The focus of our work is the Fractional-DNN. Using the Lagrangian approach, we provide a derivation of the backward propagation and the design equations. We test our network on several datasets for classification problems. Fractional-DNN offers various advantages over the existing DNN. The key benefits are a significant improvement to the vanishing gradient issue due to the memory effect, and better handling of nonsmooth data due to the network’s ability to approximate non-smooth functions.

18 May 2020 in Journal of Optimization Theory and Applications
Verified
Journal Article
Closed access
PDF file
HAHarbir Antil
Harbir Antil
DVDeepanshu Verma
Deepanshu Verma
Mahamadi WarmaMahamadi Warma
Mahamadi Warma

1 April 2020 in arXiv
Verified
Preprint
Open access
PDF file
HAHarbir Antil
Harbir Antil
RKRatna Khatri
Ratna Khatri
RLRainald Löhner
Rainald Löhner
DVDeepanshu Verma
Deepanshu Verma
This paper introduces a novel algorithmic framework for a deep neural network (DNN), which in a mathematically rigorous manner, allows us to incorporate history (or memory) into the network -- it ensures all layers are connected to one another. This DNN, called Fractional-DNN, can be viewed as a time-discretization of a fractional in time nonlinear ordinary differential equation (ODE). The learning problem then is a minimization problem subject to that fractional ODE as constraints. We emphasize that an analogy between the existing DNN and ODEs, with standard time derivative, is well-known by now. The focus of our work is the Fractional-DNN. Using the Lagrangian approach, we provide a derivation of the backward propagation and the design equations. We test our network on several datasets for classification problems. Fractional-DNN offers various advantages over the existing DNN. The key benefits are a significant improvement to the vanishing gradient issue due to the memory effect, and better handling of nonsmooth data due to the network's ability to approximate non-smooth functions.

20 April 2020 in arXiv
Verified
Preprint
Open access
PDF file
HAHarbir Antil
Harbir Antil
TBThomas S. Brown
Thomas S. Brown
DVDeepanshu Verma
Deepanshu Verma
Mahamadi WarmaMahamadi Warma
Mahamadi Warma
This paper considers optimal control of fractional parabolic PDEs with both state and control constraints. The key challenge is how to handle the state constraints. Similarly, to the elliptic case, in this paper, we establish several new mathematical tools in the parabolic setting that are of wider interest. For example, existence of solution to the fractional parabolic equation with measure data on the right-hand-side. We employ the Moreau-Yosida regularization to handle the state constraints. We establish convergence, with rate, of the regularized optimal control problem to the original one. Numerical experiments confirm what we have proven theoretically.

12 April 2019 in arXiv
Verified
Preprint
Open access
PDF file
HAHarbir Antil
Harbir Antil
DVDeepanshu Verma
Deepanshu Verma
Mahamadi WarmaMahamadi Warma
Mahamadi Warma
In this paper we introduce a new notion of optimal control, or source identification in inverse, problems with fractional parabolic PDEs as constraints. This new notion allows a source/control placement outside the domain where the PDE is fulfilled. We tackle the Dirichlet, the Neumann and the Robin cases. For the fractional elliptic PDEs this has been recently investigated by the authors in \cite{HAntil_RKhatri_MWarma_2018a}. The need for these novel optimal control concepts stems from the fact that the classical PDE models only allow placing the source/control either on the boundary or in the interior where the PDE is satisfied. However, the nonlocal behavior of the fractional operator now allows placing the control in the exterior. We introduce the notions of weak and very-weak solutions to the parabolic Dirichlet problem. We present an approach on how to approximate the parabolic Dirichlet solutions by the parabolic Robin solutions (with convergence rates). A complete analysis for the Dirichlet and Robin optimal control problems has been discussed. The numerical examples confirm our theoretical findings and further illustrate the potential benefits of nonlocal models over the local ones.

10 December 2019 in arXiv
Verified
Preprint
Open access
PDF file
HAHarbir Antil
Harbir Antil
TBThomas S. Brown
Thomas S. Brown
DVDeepanshu Verma
Deepanshu Verma
Recently the authors have studied a state and control constrained optimal control problem with fractional elliptic PDE as constraints. The goal of this paper is to continue that program forward and introduce an algorithm to solve such optimal control problems. We shall employ the well-known Moreau-Yosida regularization to handle the state constraints. Similarly to the classical case, we establish the convergence (with rate) of the regularized control problem to the original one. We discretize the problem using a finite element method and establish convergence of our numerical scheme. We emphasize that due to the non-smooth nature of the fractional Laplacian, the proof for the classical case does not apply to the fractional case. The numerical experiments confirm all our theoretical findings.