Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Ghosh, Subhro"'
The phenomenon of implicit regularization has attracted interest in recent years as a fundamental aspect of the remarkable generalizing ability of neural networks. In a nutshell, it entails that gradient descent dynamics in many neural nets, even wit
Externí odkaz:
http://arxiv.org/abs/2402.17595
The Multi-Reference Alignment (MRA) problem aims at the recovery of an unknown signal from repeated observations under the latent action of a group of cyclic isometries, in the presence of additive noise of high intensity $\sigma$. It is a more tract
Externí odkaz:
http://arxiv.org/abs/2312.07839
We investigate the problem of estimating the structure of a weighted network from repeated measurements of a Gaussian Graphical Model (GGM) on the network. In this vein, we consider GGMs whose covariance structures align with the geometry of the weig
Externí odkaz:
http://arxiv.org/abs/2308.02344
Gibbsian structure in random point fields has been a classical tool for studying their spatial properties. However, exact Gibbs property is available only in a relatively limited class of models, and it does not adequately address many random fields
Externí odkaz:
http://arxiv.org/abs/2211.01940
Stochastic gradient descent (SGD) is a cornerstone of machine learning. When the number N of data items is large, SGD relies on constructing an unbiased estimator of the gradient of the empirical risk using a small subset of the original dataset, cal
Externí odkaz:
http://arxiv.org/abs/2112.06007
Autor:
Ghosh, Subhro, Rigollet, Philippe
Publikováno v:
Proceedings of the National Academy of Sciences 117, no. 24 (2020): 13207-13213
Determinantal point processes (a.k.a. DPPs) have recently become popular tools for modeling the phenomenon of negative dependence, or repulsion, in data. However, our understanding of an analogue of a classical parametric statistical theory is rather
Externí odkaz:
http://arxiv.org/abs/2111.09990
Autor:
Ghosh, Subhro, Rigollet, Philippe
Motivated by cutting-edge applications like cryo-electron microscopy (cryo-EM), the Multi-Reference Alignment (MRA) model entails the learning of an unknown signal from repeated measurements of its images under the latent action of a group of isometr
Externí odkaz:
http://arxiv.org/abs/2106.12996
Disordered complex networks are of fundamental interest as stochastic models for information transmission over wireless networks. Well-known networks based on the Poisson point process model have limitations vis-a-vis network efficiency, whereas stro
Externí odkaz:
http://arxiv.org/abs/2009.08811
Autor:
Ghosh, Subhro, Chaudhuri, Sanjay
We investigate the problem of semi-parametric maximum likelihood under constraints on summary statistics. Such a procedure results in a discrete probability distribution that maximises the likelihood among all such distributions under the specified c
Externí odkaz:
http://arxiv.org/abs/1910.01396
Autor:
Ghosh, Subhro, Nishry, Alon
We consider particle systems (also known as point processes) on the line and in the plane, and are particularly interested in "hole" events, when there are no particles in a large disk (or some other domain). We survey the extensive work on hole prob
Externí odkaz:
http://arxiv.org/abs/1810.03268