Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Khara, Biswajit"'
We present a space-time continuous-Galerkin finite element method for solving incompressible Navier-Stokes equations. To ensure stability of the discrete variational problem, we apply ideas from the variational multi-scale method. The finite element
Externí odkaz:
http://arxiv.org/abs/2402.12571
We present a full space-time numerical solution of the advection-diffusion equation using a continuous Galerkin finite element method on conforming meshes. The Galerkin/least-square method is employed to ensure stability of the discrete variational p
Externí odkaz:
http://arxiv.org/abs/2307.00822
Autor:
Khara, Biswajit, Herron, Ethan, Jiang, Zhanhong, Balu, Aditya, Yang, Chih-Hsuan, Saurabh, Kumar, Jignasu, Anushrut, Sarkar, Soumik, Hegde, Chinmay, Krishnamurthy, Adarsh, Ganapathysubramanian, Baskar
Neural network-based approaches for solving partial differential equations (PDEs) have recently received special attention. However, the large majority of neural PDE solvers only apply to rectilinear domains, and do not systematically address the imp
Externí odkaz:
http://arxiv.org/abs/2211.03241
Autor:
Khara, Biswajit, Balu, Aditya, Joshi, Ameya, Sarkar, Soumik, Hegde, Chinmay, Krishnamurthy, Adarsh, Ganapathysubramanian, Baskar
We consider a mesh-based approach for training a neural network to produce field predictions of solutions to parametric partial differential equations (PDEs). This approach contrasts current approaches for "neural PDE solvers" that employ collocation
Externí odkaz:
http://arxiv.org/abs/2110.01601
Autor:
Cho, Minsu, Balu, Aditya, Joshi, Ameya, Prasad, Anjana Deva, Khara, Biswajit, Sarkar, Soumik, Ganapathysubramanian, Baskar, Krishnamurthy, Adarsh, Hegde, Chinmay
The paradigm of differentiable programming has significantly enhanced the scope of machine learning via the judicious use of gradient-based optimization. However, standard differentiable programming methods (such as autodiff) typically require that t
Externí odkaz:
http://arxiv.org/abs/2110.01532
Autor:
Khara, Biswajit, Herron, Ethan, Balu, Aditya, Gamdha, Dhruv, Yang, Chih-Hsuan, Saurabh, Kumar, Jignasu, Anushrut, Jiang, Zhanhong, Sarkar, Soumik, Hegde, Chinmay, Ganapathysubramanian, Baskar, Krishnamurthy, Adarsh
Publikováno v:
In Computer-Aided Design July 2024 172
Autor:
Balu, Aditya, Botelho, Sergio, Khara, Biswajit, Rao, Vinay, Hegde, Chinmay, Sarkar, Soumik, Adavani, Santi, Krishnamurthy, Adarsh, Ganapathysubramanian, Baskar
We consider the distributed training of large-scale neural networks that serve as PDE solvers producing full field outputs. We specifically consider neural solvers for the generalized 3D Poisson equation over megavoxel domains. A scalable framework i
Externí odkaz:
http://arxiv.org/abs/2104.14538
Autor:
Saurabh, Kumar, Gao, Boshun, Fernando, Milinda, Xu, Songzhe, Khanwale, Makrand A., Khara, Biswajit, Hsu, Ming-Chen, Krishnamurthy, Adarsh, Sundar, Hari, Ganapathysubramanian, Baskar
We present a variant of the immersed boundary method integrated with octree meshes for highly efficient and accurate Large-Eddy Simulations (LES) of flows around complex geometries. We demonstrate the scalability of the proposed method up to $\mathca
Externí odkaz:
http://arxiv.org/abs/2009.00706
Autor:
Botelho, Sergio, Joshi, Ameya, Khara, Biswajit, Sarkar, Soumik, Hegde, Chinmay, Adavani, Santi, Ganapathysubramanian, Baskar
Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been recently rep
Externí odkaz:
http://arxiv.org/abs/2007.12792
Autor:
Khara, Biswajit, Balu, Aditya, Joshi, Ameya, Sarkar, Soumik, Hegde, Chinmay, Krishnamurthy, Adarsh, Ganapathysubramanian, Baskar
Publikováno v:
Engineering with Computers; Oct2024, Vol. 40 Issue 5, p2761-2783, 23p