Search Results for author: Soumendu Sundar Mukherjee

Found 16 papers, 3 papers with code

Implicit Regularization via Spectral Neural Networks and Non-linear Matrix Sensing

1 code implementation27 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.

Minimax-optimal estimation for sparse multi-reference alignment with collision-free signals

no code implementations13 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.

Learning Networks from Gaussian Graphical Models and Gaussian Free Fields

no code implementations4 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.

Consistent model selection in the spiked Wigner model via AIC-type criteria

no code implementations24 Jul 2023 Soumendu Sundar Mukherjee

Consider the spiked Wigner model \[ X = \sum_{i = 1}^k \lambda_i u_i u_i^\top + \sigma G, \] where $G$ is an $N \times N$ GOE random matrix, and the eigenvalues $\lambda_i$ are all spiked, i. e. above the Baik-Ben Arous-P\'ech\'e (BBP) threshold $\sigma$.

Model Selection

Wasserstein Projection Pursuit of Non-Gaussian Signals

no code implementations24 Feb 2023 Satyaki Mukherjee, Soumendu Sundar Mukherjee, Debarghya Ghoshdastidar

We consider the general dimensionality reduction problem of locating in a high-dimensional data cloud, a $k$-dimensional non-Gaussian subspace of interesting features.

Dimensionality Reduction

Learning with latent group sparsity via heat flow dynamics on networks

no code implementations20 Jan 2022 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 theoreticians alike.

Stochastic Block Model

Changepoint Analysis of Topic Proportions in Temporal Text Data

no code implementations29 Nov 2021 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.

Time Series Time Series Analysis

Distribution of Eigenvalues of Matrix Ensembles arising from Wigner and Palindromic Toeplitz Blocks

no code implementations11 Feb 2021 Keller Blackwell, Neelima Borade, Arup Bose, Charles Devlin VI, Noah Luntzlara, Renyuan Ma, Steven J. Miller, Soumendu Sundar Mukherjee, Mengxi Wang, Wanqiao Xu

For definiteness we concentrate on the ensemble of palindromic real symmetric Toeplitz (PST) matrices and the ensemble of real symmetric matrices, whose limiting spectral measures are the Gaussian and semi-circular distributions, respectively; these were chosen as they are the two extreme cases in terms of moment calculations.

Probability 15A52 (primary), 60F99, 62H10 (secondary)

Some characterization results on classical and free Poisson thinning

no code implementations11 Jan 2021 Soumendu Sundar Mukherjee

We also prove a free probability analogue of Craig's theorem, another well-known result in multivariate statistics on the independence of quadratic functions of Gaussian random matrices.

Point Processes Probability Operator Algebras Statistics Theory Statistics Theory 46L54, 60E05, 62E10

Graphon Estimation from Partially Observed Network Data

1 code implementation2 Jun 2019 Soumendu Sundar Mukherjee, Sayak Chakrabarti

We consider estimating the edge-probability matrix of a network generated from a graphon model when the full network is not observed---only some overlapping subgraphs are.

Graphon Estimation Matrix Completion

Morphological Network: How Far Can We Go with Morphological Neurons?

no code implementations ICLR 2019 Ranjan Mondal, Sanchayan Santra, Soumendu Sundar Mukherjee, Bhabatosh Chanda

A few works have tried to utilize morphological neurons as a part of classification (and regression) networks when the input is a feature vector.

 Ranked #1 on Representation Learning on Circle Data (using extra training data)

Image Dehazing regression +2

Mean Field for the Stochastic Blockmodel: Optimization Landscape and Convergence Issues

no code implementations NeurIPS 2018 Soumendu Sundar Mukherjee, Purnamrita Sarkar, Y. X. Rachel Wang, Bowei Yan

Variational approximation has been widely used in large-scale Bayesian inference recently, the simplest kind of which involves imposing a mean field assumption to approximate complicated latent structures.

Bayesian Inference Community Detection

On clustering network-valued data

1 code implementation NeurIPS 2017 Soumendu Sundar Mukherjee, Purnamrita Sarkar, Lizhen Lin

Community detection, which focuses on clustering nodes or detecting communities in (mostly) a single network, is a problem of considerable practical interest and has received a great deal of attention in the research community.

Clustering Community Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.