15 citations · 21 across the 4 of their papers we have counts for
4 papers
Weight-Decay Turns Transformer Loss Landscapes Villani: Functional-Analytic Foundations for Optimization and Generalization
Abhijit Das, Sayantan Dutta
Weight decay is widely used as a regularizer in large language models, yet its precise role in shaping Transformer loss landscapes remains theoretically underexplored. This paper p…
A novel perspective on denoising using quantum localization with application to medical imaging
Amirreza Hashemi, Sayantan Dutta, Bertrand Georgeot +2
Background noise in many fields such as medical imaging poses significant challenges for accurate diagnosis, prompting the development of denoising algorithms. Traditional methodol…
Automatic Tuning of Denoising Algorithms Parameters Without Ground Truth
Arthur Floquet, Sayantan Dutta, Emmanuel Soubies +2
Denoising is omnipresent in image processing. It is usually addressed with algorithms relying on a set of hyperparameters that control the quality of the recovered image. Manual tu…
Quantum Algorithm for Signal Denoising
Sayantan Dutta, Adrian Basarab, Denis Kouamé +1
This letter presents a novel \textit{quantum algorithm} for signal denoising, which performs a thresholding in the frequency domain through amplitude amplification and using an ada…