28 citations · 44 across the 12 of their papers we have counts for
5 papers · 1 filter
Data efficient surrogate modeling for engineering design: Ensemble-free batch mode deep active learning for regression
Sarthak Kapoor, Harsh Vardhan, Umesh Timalsina +3
High fidelity design evaluation processes such as Computational Fluid Dynamics and Finite Element Analysis are often replaced with data driven surrogates to reduce computational co…
An Improved Algorithm for Clustered Federated Learning
Harshvardhan, Avishek Ghosh, Arya Mazumdar
In this paper, we address the dichotomy between heterogeneous models and simultaneous training in Federated Learning (FL) via a clustering framework. We define a new clustering mod…
Deep Active Learning for Regression Using -weighted Hybrid Query Strategy
Harsh Vardhan, Janos Sztipanovits
Designing an inexpensive approximate surrogate model that captures the salient features of an expensive high-fidelity behavior is a prevalent approach in design optimization. In re…
Deep Learning-based Finite Element Analysis (FEA) surrogate for sub-sea pressure vessel
Harsh Vardhan, Janos Sztipanovits
During the design process of an autonomous underwater vehicle (AUV), the pressure vessel has a critical role. The pressure vessel contains dry electronics, power sources, and other…
Tackling benign nonconvexity with smoothing and stochastic gradients
Harsh Vardhan, Sebastian U. Stich
Non-convex optimization problems are ubiquitous in machine learning, especially in Deep Learning. While such complex problems can often be successfully optimized in practice by usi…