2 papers
cs.LG2026
Grokking in Linear Models for Logistic Regression
Nataraj Das, Atreya Vedantam, Chandrashekar Lakshminarayanan
Grokking, the phenomenon of delayed generalization, is often attributed to the depth and compositional structure of deep neural networks. We study grokking in one of the simplest p…
cs.CL2025
ProdRev: A DNN framework for empowering customers using generative pre-trained transformers
Aakash Gupta, Nataraj Das
Following the pandemic, customers, preference for using e-commerce has accelerated. Since much information is available in multiple reviews (sometimes running in thousands) for a s…