S
Soumik Sarkar
Researcher at Iowa State University
Publications - 288
Citations - 7113
Soumik Sarkar is an academic researcher from Iowa State University. The author has contributed to research in topics: Deep learning & Computer science. The author has an hindex of 31, co-authored 258 publications receiving 4542 citations. Previous affiliations of Soumik Sarkar include Indian Institute of Science & Raytheon.
Papers
More filters
Differentiable Programming for Piecewise Polynomial Functions
Minsu Cho,Ameya Joshi,Xian Yeow Lee,Aditya Balu,Adarsh Krishnamurthy,Baskar Ganapathysubramanian,Soumik Sarkar,Chinmay Hegde +7 more
TL;DR: In this paper, a principled approach to extend gradient-based optimization to piecewise smooth models, such as k-histograms, splines, and segmentation maps, is introduced.
Posted Content
Distributed Multigrid Neural Solvers on Megavoxel Domains
Aditya Balu,Sergio Botelho,Biswajit Khara,Vinay Rao,Chinmay Hegde,Soumik Sarkar,Santi Adavani,Adarsh Krishnamurthy,Baskar Ganapathysubramanian +8 more
TL;DR: In this paper, a distributed training of large-scale neural networks for the generalized 3D Poisson equation over megavoxel domains is presented. But the authors focus on the problem of predicting output full-field solutions.
Proceedings ArticleDOI
Damage Detection of Bridge Network With Spatiotemporal Pattern Network
TL;DR: Results show significant capa bilities of the proposed approach in: capturing spatiotemporal features to discover causality between bridges, robustness to noise in data for feature extract ion, and detecting and localizing damage via the comparison of behaviors within the bridge network.
Journal ArticleDOI
On Consensus-Optimality Trade-offs in Collaborative Deep Learning
TL;DR: In this paper, the authors propose incremental consensus-based distributed stochastic gradient descent (i-CDSGD) algorithm, which involves multiple consensus steps (where each agent communicates information with its neighbors) within each SGD iteration.
Distributed Decision Propagation in Mobile-agent Proximity Networks F
TL;DR: In this paper, a distributed algorithm for decision/awareness propagation in mobile-agent networks is developed, where a time-dependent proximity network topology is adopted to represent a mobile agent scenario and the agent-interaction policy formulated here is inspired from the recently developed language-measure-theory.