Litu Rout

Understanding the Role of Adversarial Regularization in Supervised\n Learning

2020 · arXiv (Cornell University)

Despite numerous attempts sought to provide empirical evidence of adversarial\nregularization outperforming sole supervision, the theoretical understanding of\nsuch phenomena remains elusive. In this study, we aim to resolve whether\nadversarial regularization indeed performs better than sole supervision …

Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGD

2023 · arXiv (Cornell University)

This work considers the problem of finding a first-order stationary point of a non-convex function with potentially unbounded smoothness constant using a stochastic gradient oracle. We focus on the class of $(L_0,L_1)$-smooth functions proposed by …

Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations

2024 · arXiv (Cornell University)

Generative models transform random noise into images; their inversion aims to transform images back to structured noise for recovery and editing. This paper addresses two key tasks: (i) inversion and (ii) editing of a real …