Search Results for author:
Found 3 papers, 2 papers with code
SuperSAM: Crafting a SAM Supernetwork via Structured Pruning and Unstructured Parameter Prioritization
Neural Architecture Search (NAS) is a powerful approach of automating the design of efficient neural architectures.
LEFL: Low Entropy Client Sampling in Federated Learning
This enables the server to perform stratified client sampling across clusters in every round.
Exploring Resiliency to Natural Image Corruptions in Deep Learning using Design Diversity
We compare ensembles created with diverse model architectures trained either independently or through a Neural Architecture Search technique and evaluate the correlation of prediction-based and attribution-based diversity to the final ensemble accuracy.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
