collaborators

5 papers

stat.ML2026

On the Stability of Spherical Hellinger-Kantorovich Flows and Their Implications for Differential Privacy

Aratrika Mustafi, Soumya Mukherjee

Gradient-flow sampling interprets a Gibbs distribution as the minimizer of an energy functional over probability measures and generates dynamics converging to this target. Under sp…

stat.ML2026

Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer

Aratrika Mustafi, Soumya Mukherjee, Bharath K. Sriperumbudur

We develop a gradient flow on the space of probability measures defined on matrix-valued parameters induced by regularized Muon, an analytically smoothed version of the idealized M…

stat.ML2026

Sinkhorn Based Associative Memory Retrieval Using Spherical Hellinger Kantorovich Dynamics

Aratrika Mustafi, Soumya Mukherjee

We propose a dense associative memory for empirical measures (weighted point clouds). Stored patterns and queries are finitely supported probability measures, and retrieval is defi…

stat.AP2026

Assessing Utility of Differential Privacy for RCTs

Kaitlyn R. Webb, Soumya Mukherjee, Aratrika Mustafi +2

Randomized controlled trials (RCTs) have become powerful tools for assessing the impact of interventions and policies in many contexts. They are considered the gold standard for ca…

stat.ML2025

(De)-regularized Maximum Mean Discrepancy Gradient Flow

Zonghao Chen, Aratrika Mustafi, Pierre Glaser +3

We introduce a (de)-regularization of the Maximum Mean Discrepancy (DrMMD) and its Wasserstein gradient flow. Existing gradient flows that transport samples from source distributio…