Skip To Main Content
Debarghya Chaki on Muck Rack

Debarghya Chaki

As seen in: Nature
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile

Get in touch with Debarghya

Contact Debarghya, search articles and posts on X, monitor coverage, and track replies from one place.

Learn more about Muck Rack

Actions

Share this page

Is this you?

As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile

Articles

Computationally efficient decoupled momentum optimization algorithm for medical imaging models

|
By Joshua Joseph, Jasmine Jung, Blake Evans, Hairong Wang, Edward Castillo, Aaron T. Luong, Debarghya Chaki, Yi-Kuan Liu, Amanda Nowacki
| Nature Verified
Abstract The goal of this study is to empirically evaluate the Decoupled Momentum Optimizer (DeMo) in medical image segmentation while demonstrating its extensibility to applications outside LLMs. We aim to characterize the behavior of each parameter group and their adherence to conjectures underlying DeMo’s function. DeMo leverages spatial redundancy in gradients through a spatially partitioned frequency decomposition compression algorithm, reducing network traffic and smoothing gradient noise.
Open in Who Shared Issue with article?
See all 1 articles