no code implementations • 17 Jan 2024 • Nabarun Deb, Debarghya Mukherjee
Our main result shows that a non-trivial trade-off between the complexity of the underlying function class and the dependence among the observations characterizes the learning rate in a large class of nonparametric problems.
no code implementations • 31 Jul 2023 • Nabarun Deb, Young-Heon Kim, Soumik Pal, Geoffrey Schiebinger
This limit, which we call the Sinkhorn flow, is an example of a Wasserstein mirror gradient flow, a concept we introduce here inspired by the well-known Euclidean mirror gradient flows.
no code implementations • NeurIPS 2021 • Nabarun Deb, Promit Ghosal, Bodhisattva Sen
We illustrate the usefulness of this stability estimate by first providing rates of convergence for the natural discrete-discrete and semi-discrete estimators of optimal transport maps.
no code implementations • 10 Dec 2020 • Nabarun Deb, Rajarshi Mukherjee, Sumit Mukherjee, Ming Yuan
In this paper, we study the effect of dependence on detecting a class of signals in Ising models, where the signals are present in a structured way.
Probability Statistics Theory Statistics Theory 62G10, 62G20, 62C20
1 code implementation • 18 Oct 2018 • Nabarun Deb, Sujayam Saha, Adityanand Guntuboyina, Bodhisattva Sen
We propose a tuning parameter-free nonparametric maximum likelihood approach, implementable via the EM algorithm, to estimate the unknown parameters.
Methodology