1 code implementation • 27 Feb 2024 • Hong T. M. Chu, Subhro Ghosh, Chi Thanh Lam, Soumendu Sundar Mukherjee
In this paper, we explore this problem in the context of more realistic neural networks with a general class of non-linear activation functions, and rigorously demonstrate the implicit regularization phenomenon for such networks in the setting of matrix sensing problems, together with rigorous rate guarantees that ensure exponentially fast convergence of gradient descent. In this vein, we contribute a network architecture called Spectral Neural Networks (abbrv.
no code implementations • 13 Dec 2023 • Subhro Ghosh, Soumendu Sundar Mukherjee, Jing Bin Pan
We demonstrate that the minimax optimal rate of estimation in for the sparse MRA problem in this setting is $\sigma^2/\sqrt{n}$, where $n$ is the sample size.
no code implementations • 4 Aug 2023 • Subhro Ghosh, Soumendu Sundar Mukherjee, Hoang-Son Tran, Ujan Gangopadhyay
In this work, we propose a novel estimator for the weighted network (equivalently, its Laplacian) from repeated measurements of a GFF on the network, based on the Fourier analytic properties of the Gaussian distribution.
no code implementations • NeurIPS 2021 • Remi Bardenet, Subhro Ghosh, Meixia Lin
In particular, we show how specific DPPs and a string of controlled approximations can lead to gradient estimators with a variance that decays faster with the batchsize than under uniform sampling.
no code implementations • 19 Nov 2021 • Subhro Ghosh, Philippe Rigollet
Determinantal point processes (a. k. a.
no code implementations • 24 Jun 2021 • Subhro Ghosh, Philippe Rigollet
Our techniques have implications for the problem of crystallographic phase retrieval, indicating a certain local uniqueness for the recovery of sparse signals from their power spectrum.
no code implementations • 13 Sep 2020 • Subhro Ghosh, Naoto Miyoshi, Tomoyuki Shirai
We demonstrate that the PTL network at this disorder strength can be taken to be an effective substitute for the RMT network model, while at the same time offering the advantages of greater tractability.
no code implementations • 3 Oct 2019 • Subhro Ghosh, Sanjay Chaudhuri
In the Bayesian setting, we rigorously establish the posterior consistency of procedures based on these ideas, where instead of a parametric likelihood, an empirical likelihood is used to define the posterior distribution.
no code implementations • 3 Oct 2018 • Sanjay Chaudhuri, Subhro Ghosh, David J. Nott, Kim Cuc Pham
Many scientifically well-motivated statistical models in natural, engineering and environmental sciences are specified through a generative process, but in some cases it may not be possible to write down a likelihood for these models analytically.