4 citations · 14 across the 40 of their papers we have counts for
41 papers
Approximation Theory for Neural Networks: Old and New
Soumendu Sundar Mukherjee, Himasish Talukdar
Universal approximation theorems provide a mathematical explanation for the expressive power of neural networks. They assert that, under mild conditions on the activation function,…
Elephant random walk on the infinite dihedral group
Soumendu Sundar Mukherjee, Himasish Talukdar
Elephant random walks were studied recently in \cite{mukherjee2025elephant} on the groups whose Cayley graphs are infinite -regular tre…
Elephant random walks on infinite Cayley trees
Soumendu Sundar Mukherjee
We introduce a generalisation of Schütz and Trimper's elephant random walk to finitely generated groups. We focus on the simplest non-abelian setting, i.e. groups whose Cayley grap…
Learning under Latent Group Sparsity via Diffusion on Networks
Subhroshekhar Ghosh, Soumendu Sundar Mukherjee
Group or cluster structure on explanatory variables in machine learning problems is a very general phenomenon, which has attracted broad interest from practitioners and theoreticia…
Spectra of contractions of the Gaussian Orthogonal Tensor Ensemble
Soumendu Sundar Mukherjee, Himasish Talukdar
In this article, we study the spectra of matrix-valued contractions of the Gaussian Orthogonal Tensor Ensemble (GOTE). Let denote a random tensor of order and dim…
Filtering through a topological lens: homology for point processes on the time-frequency plane
Juan Manuel Miramont, Kin Aun Tan, Soumendu Sundar Mukherjee +2
We introduce a very general approach to the analysis of signals from their noisy measurements from the perspective of Topological Data Analysis (TDA). While TDA has emerged as a po…
Optimal Transfer Learning for Missing Not-at-Random Matrix Completion
Akhil Jalan, Yassir Jedra, Arya Mazumdar +2
We study transfer learning for matrix completion in a Missing Not-at-Random (MNAR) setting that is motivated by biological problems. The target matrix has entire rows and colum…
A new approach to locally adaptive polynomial regression
Sabyasachi Chatterjee, Subhajit Goswami, Soumendu Sundar Mukherjee
Adaptive bandwidth selection is a fundamental challenge in nonparametric regression. This paper introduces a new bandwidth selection procedure inspired by the optimality criteria f…
Spectra of adjacency and Laplacian matrices of Erdős-Rényi hypergraphs
Soumendu Sundar Mukherjee, Dipranjan Pal, Himasish Talukdar
We study adjacency and Laplacian matrices of Erdős-Rényi -uniform hypergraphs on vertices with hyperedge inclusion probability , in the setting where can vary with $n…
Bulk Spectra of Truncated Sample Covariance Matrices
Subhroshekhar Ghosh, Soumendu Sundar Mukherjee, Himasish Talukdar
Determinantal Point Processes (DPPs), which originate from quantum and statistical physics, are known for modelling diversity. Recent research [Ghosh and Rigollet (2020)] has demon…
Edge spectra of Gaussian random symmetric matrices with correlated entries
Debapratim Banerjee, Soumendu Sundar Mukherjee, Dipranjan Pal
We study the largest eigenvalue of a Gaussian random symmetric matrix , with zero-mean, unit variance entries satisfying the condition $\sup_{(i, j) \ne (i', j')}|\mathbb{E}[X…
Transfer Learning for Latent Variable Network Models
Akhil Jalan, Arya Mazumdar, Soumendu Sundar Mukherjee +1
We study transfer learning for estimation in latent variable network models. In our setting, the conditional edge probability matrices given the latent variables are represented by…
Implicit Regularization via Spectral Neural Networks and Non-linear Matrix Sensing
Hong T. M. Chu, Subhro Ghosh, Chi Thanh Lam +1
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, i…
The "visible" Wigner matrix
Arup Bose, Soumendu Sundar Mukherjee
We consider the ``visible'' Wigner matrix, a Wigner matrix whose -th entry is coerced to zero if are co-prime. Using a recent result from elementary number theory on…
Minimax-optimal estimation for sparse multi-reference alignment with collision-free signals
Subhro Ghosh, Soumendu Sundar Mukherjee, Jing Bin Pan
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 pre…
A dynamic mean-field statistical model of academic collaboration
Soumendu Sundar Mukherjee, Tamojit Sadhukhan, Shirshendu Chatterjee
There is empirical evidence that collaboration in academia has increased significantly during the past few decades, perhaps due to the breathtaking advancements in communication an…
Learning Networks from Gaussian Graphical Models and Gaussian Free Fields
Subhro Ghosh, Soumendu Sundar Mukherjee, Hoang-Son Tran +1
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 conside…
Consistent model selection in the spiked Wigner model via AIC-type criteria
Soumendu Sundar Mukherjee
Consider the spiked Wigner model \[ X = \sum_{i = 1}^k λ_i u_i u_i^\top + σG, \] where is an GOE random matrix, and the eigenvalues are all spiked, i.e. abov…
On a generalisation of the coupon collector problem
Siva Athreya, Satyaki Mukherjee, Soumendu Sundar Mukherjee
We consider a generalisation of the classical coupon collector problem. We define a super-coupon to be any -subset of a universe of coupons. In each round, a random -subs…
Wasserstein Projection Pursuit of Non-Gaussian Signals
Satyaki Mukherjee, Soumendu Sundar Mukherjee, Debarghya Ghoshdastidar
We consider the general dimensionality reduction problem of locating in a high-dimensional data cloud, a -dimensional non-Gaussian subspace of interesting features. We use a pro…
Concentration inequalities for correlated network-valued processes with applications to community estimation and changepoint analysis
Sayak Chatterjee, Shirshendu Chatterjee, Soumendu Sundar Mukherjee +2
Network-valued time series are currently a common form of network data. However, the study of the aggregate behavior of network sequences generated from network-valued stochastic p…
Learning with latent group sparsity via heat flow dynamics on networks
Subhroshekhar Ghosh, Soumendu Sundar Mukherjee
Group or cluster structure on explanatory variables in machine learning problems is a very general phenomenon, which has attracted broad interest from practitioners and theoreticia…
Changepoint Analysis of Topic Proportions in Temporal Text Data
Avinandan Bose, Soumendu Sundar Mukherjee
Changepoint analysis deals with unsupervised detection and/or estimation of time-points in time-series data, when the distribution generating the data changes. In this article, we…
Distribution of Eigenvalues of Matrix Ensembles arising from Wigner and Palindromic Toeplitz Blocks
Keller Blackwell, Neelima Borade, Arup Bose +7
Random Matrix Theory (RMT) has successfully modeled diverse systems, from energy levels of heavy nuclei to zeros of -functions; this correspondence has allowed RMT to successful…