3 papers
cs.LG2026
Exponential Convergence of (Stochastic) Gradient Descent for Separable Logistic Regression
Sacchit Kale, Piyushi Manupriya, Pierre Marion +2
Gradient descent and stochastic gradient descent are central to modern machine learning, yet their behavior under large step sizes remains theoretically unclear. Recent work sugges…
cs.LG2025
Submodular Framework for Structured-Sparse Optimal Transport
Piyushi Manupriya, Pratik Jawanpuria, Karthik S. Gurumoorthy +2
Unbalanced optimal transport (UOT) has recently gained much attention due to its flexible framework for handling un-normalized measures and its robustness properties. In this work,…
cs.LG2024
Consistent Optimal Transport with Empirical Conditional Measures
Piyushi Manupriya, Rachit Keerti Das, Sayantan Biswas +1
Given samples from two joint distributions, we consider the problem of Optimal Transportation (OT) between them when conditioned on a common variable. We focus on the general setti…