3 papers
cs.LG2025
Decoding Federated Learning: The FedNAM+ Conformal Revolution
Sree Bhargavi Balija, Amitash Nanda, Debashis Sahoo
Federated learning has significantly advanced distributed training of machine learning models across decentralized data sources. However, existing frameworks often lack comprehensi…
cs.DC2025
Exploring Dynamic Load Balancing Algorithms for Block-Structured Mesh-and-Particle Simulations in AMReX
Amitash Nanda, Md Kamal Hossain Chowdhury, Hannah Ross +1
Load balancing is critical for successful large-scale high-performance computing (HPC) simulations. With modern supercomputers increasing in complexity and variability, dynamic loa…
cs.CL2024
CPTQuant - A Novel Mixed Precision Post-Training Quantization Techniques for Large Language Models
Amitash Nanda, Sree Bhargavi Balija, Debashis Sahoo
Large language models have transformed the comprehension and generation of natural language tasks, but they come with substantial memory and computational requirements. Quantizatio…