activity
20162026
most citedRates of Estimation of Optimal Transport Maps using Plug-in Estimators via Barycentric Projections

28 citations · 56 across the 33 of their papers we have counts for

collaborators
Showing 2025Show all

7 papers · 1 filter

math-ph2025

The stochastic six vertex model and discrete orthogonal polynomial ensembles

Promit Ghosal, Guilherme L. F. Silva

Stochastic growth models in the Kardar-Parisi-Zhang (KPZ) universality class exhibit remarkable fluctuation phenomena. While a variety of powerful methods have led to a detailed un…

cs.LG2025

Statistical Inference for Linear Functionals of Online Least-squares SGD when

Bhavya Agrawalla, Krishnakumar Balasubramanian, Promit Ghosal

Stochastic Gradient Descent (SGD) has become a cornerstone method in modern data science. However, deploying SGD in high-stakes applications necessitates rigorous quantification of…

cs.LG2025

Clustering by Denoising: Latent plug-and-play diffusion for single-cell data

Dominik Meier, Shixing Yu, Sagnik Nandy +2

Single-cell RNA sequencing (scRNA-seq) enables the study of cellular heterogeneity. Yet, clustering accuracy, and with it downstream analyses based on cell labels, remain challengi…

cs.LG2025

When Additive Noise Meets Unobserved Mediators: Bivariate Denoising Diffusion for Causal Discovery

Dominik Meier, Sujai Hiremath, Promit Ghosal +1

Distinguishing cause and effect from bivariate observational data is a foundational problem in many disciplines, but challenging without additional assumptions. Additive noise mode…

math.NA2025

BOLT: Block-Orthonormal Lanczos for Trace estimation of matrix functions

Kingsley Yeon, Promit Ghosal, Mihai Anitescu

Efficient matrix trace estimation is essential for scalable computation of log-determinants, matrix norms, and distributional divergences. In many large-scale applications, the mat…

stat.ML2025

How Private is Your Attention? Bridging Privacy with In-Context Learning

Soham Bonnerjee, Zhen Wei, Yeon +3

In-context learning (ICL)-the ability of transformer-based models to perform new tasks from examples provided at inference time-has emerged as a hallmark of modern language models.…